CN107726560B

CN107726560B - Image acquisition equipment, air conditioner and control method of air conditioner

Info

Publication number: CN107726560B
Application number: CN201710922763.5A
Authority: CN
Inventors: 刘光有; 毛跃辉; 伍衍亮; 莫宗蒸; 梁博
Original assignee: Gree Electric Appliances Inc of Zhuhai
Current assignee: Gree Electric Appliances Inc of Zhuhai
Priority date: 2017-09-30
Filing date: 2017-09-30
Publication date: 2024-01-30
Anticipated expiration: 2037-09-30
Also published as: CN107726560A

Abstract

The invention discloses an image acquisition device, an air conditioner and a control method thereof, wherein the device comprises: a driving mechanism (10), a linkage mechanism (20) and a camera (30); wherein the driving mechanism (10) is used for driving the linkage mechanism (20); the linkage mechanism (20) is used for driving the camera (30) to rotate under the driving of the driving mechanism (10) and enabling the camera (30) to stay at the set at least one stop motion position; and the camera (30) is used for acquiring first image information in a first acquisition range of the view angle center by taking the stop-motion position as the view angle center when the camera stays at the stop-motion position. The technical scheme of the invention can overcome the defects of large field of view adjustment difficulty, small application range, inconvenient use and the like in the prior art, and has the beneficial effects of small field of view adjustment difficulty, large application range and convenient use.

Description

Image acquisition equipment, air conditioner and control method of air conditioner

Technical Field

The invention belongs to the technical field of air conditioners, and particularly relates to an image acquisition device, an air conditioner and a control method thereof, in particular to a camera capable of rotatably acquiring images, the air conditioner with the camera and an intelligent control method of the air conditioner.

Background

With the diversification of air conditioning functions, applications have been gradually started on air conditioners based on the image recognition function of cameras. However, the image recognition function of the current air conditioner basically collects pictures through a single camera.

The general camera has a smaller visual field, and cannot capture a complete scene image, because a dead zone causes a plurality of functions to be not effectively implemented, such as unmanned shutdown. If a camera with a larger field of view (namely, a field of view) is selected, the camera is required to be more clearly realized at a longer distance, and the size, the size and the like of the camera module are quite large, so that the appearance, the structural design and the like of the air conditioner are poor.

In the prior art, the defects of large field of view adjustment difficulty, small application range, inconvenient use and the like exist.

Disclosure of Invention

The invention aims to overcome the defects, and provides image acquisition equipment, an air conditioner and a control method thereof, so as to solve the problems of large field adjustment difficulty caused by acquisition blind areas when a single camera is small in field of view and large occupied space when the field of view is large in the prior art, and achieve the effect of reducing the field of view adjustment difficulty.

The present invention provides an image acquisition apparatus including: the device comprises a driving mechanism, a linkage mechanism and a camera; wherein the driving mechanism is used for driving the linkage mechanism; the linkage mechanism is used for driving the camera to rotate under the drive of the driving mechanism and enabling the camera to stay at the set at least one stop motion position; and the camera is used for collecting first image information in a first collection range which the view angle center belongs to by taking the stop-motion position as the view angle center when the camera stays at the stop-motion position.

Optionally, the camera is inclined downwards by a first set angle or inclined upwards by a second set angle in the vertical direction; and/or the camera is further used for acquiring second image information in a second acquisition range entering the self visual field when the camera is driven to rotate by the linkage mechanism; and/or the linkage mechanism is also used for moving the visual angle center of the camera to the stop-motion position so that the camera stays at the stop-motion position.

Optionally, the driving mechanism includes: a motor; and/or, the linkage mechanism comprises: a gear set and a connecting rod; the gear set is arranged between the first end of the connecting rod and the driving mechanism in an adapting mode; the second end of the connecting rod is arranged in a matching way with the camera.

Optionally, the gear set includes: a first gear and a second gear; wherein the first gear is arranged in a matching way with the driving mechanism; the second gear is meshed with the first gear; the first end of the connecting rod is matched with the second gear.

Optionally, the motor includes: at least one of a drive motor and a rotary motor; and/or, the first gear comprises: a drive gear; and/or, the second gear comprises: a driven gear.

Optionally, the method further comprises: a protective mechanism; the protection mechanism is used for at least one of accommodating, supporting, reinforcing, dampproofing, waterproofing and dustproof at least one of the motor, the gear set, the connecting rod and the camera.

Optionally, the protection mechanism includes: at least one of the first protective structure, the second protective structure and the third protective structure; the first protection structure is used for protecting the camera; the second protection structure is arranged between the first protection structure and the second protection structure in an adapting mode and is used for protecting the connecting rod; the third protection structure is used for protecting at least one of the motor and the gear set.

Optionally, the protection mechanism further includes: at least one of the clamping groove structure and the clamping structure; the camera is arranged in the first protection structure in an adapting mode through at least one of the clamping groove structure and the buckling structure.

Optionally, the first protection structure includes: a front cover and a rear cover; the front cover and the rear cover are arranged in an adapting way; an opening is arranged on the front cover; the opening is matched with an image acquisition hole of the camera; and/or, the second protective structure comprises: a vertical guard; the vertical protection piece is vertically arranged below the first protection structure.

Optionally, the method further comprises: a controller; the controller is used for realizing corresponding control on at least one current rotation state of the camera in the starting rotation, the rotating speed, the rotating direction and the stopping rotation by controlling at least one of the starting operation, the operating speed, the operating direction and the stopping operation of the driving mechanism so as to adapt the current rotation state of the camera to the current scene requirement; and/or when the camera is inclined downwards by a first set angle or is inclined upwards by a second set angle, controlling at least one current inclination state of the upward inclination or the downward inclination direction of the camera, the first set angle when the camera is inclined upwards and the second set angle when the camera is inclined downwards; wherein, the current scene requirement includes: when the camera is arranged in an adaptive manner with the air conditioner, the air conditioner adaptively outputs air supply control of corresponding air supply according to at least one of the position, the number of people, the sex, the face and the age of a user in the environment of the air conditioner, and/or the air conditioner performs limb control of running according to at least one of the gesture and the posture of the user in the environment of the air conditioner, and/or the air conditioner performs security monitoring according to whether an illegal invader exists in the environment of the air conditioner.

Optionally, the controller controls the corresponding state of at least one of the current rotation state of the camera, including: when the camera is also used for collecting second image information, receiving the second image information collected by the camera, and determining whether a set non-human body active area exists in the second image information through a convolutional neural algorithm; when the non-human body active area exists in the second image information, controlling the camera to rotate at a speed increasing speed so as to bypass the non-human body active area or controlling the camera to stop rotating to the non-human body active area; or when the second image information does not have the non-human body active area, maintaining the current rotation state of the camera; wherein the non-human activity area comprises: based on the convolutional neural algorithm, at least one of a wall body in a network and/or an environment to which the camera belongs, furniture and household appliances with occupied space larger than a set value is learned and/or trained in advance, and at least one of the set wall body, the set furniture and the set household appliances is obtained; and/or the controller correspondingly controls at least one current rotation state of the camera in the modes of starting rotation, rotating speed, rotating direction and stopping rotation, and the method specifically further comprises the following steps: determining whether the camera rotates to the stop-motion position; when the camera rotates to the stop-motion position, enabling the camera to stay at the stop-motion position for a first set time period, and/or enabling the camera to stay at the stop-motion position and then collect a second set time period; or when the camera is not rotated to the stop-motion position, continuing to rotate; the first set duration is longer than the second set duration.

Optionally, the controller controls the corresponding state of at least one of the current rotation state of the camera, including: determining the angle of a human body activity area in the environment of the camera; determining the required freeze position of the camera in the environment according to the relation between the angle of the human body movement area and the set horizontal visible angle of the camera so as to determine whether the camera rotates to the freeze position; and/or at least one of redetermining, self-learning and storing the angle of the human body active area according to a set period.

Optionally, the human body movement area angle includes: at least one of a first human body movement area angle and a second human body movement area angle; determining the angle of a human body activity area in the environment of the camera comprises the following steps: when the camera starts to rotate, the camera rotates to the maximum positions of the left side and the right side of the horizontal plane where the camera is positioned respectively to stay for acquisition, so that leftmost image information and rightmost image information are obtained; determining a leftmost human body activity area position and a rightmost human body activity area position except the non-human body activity area according to the leftmost image information and the rightmost image information, and determining an angle range between the leftmost human body activity area position and the rightmost human body activity area position as the first human body activity area angle; and/or determining the angle of the human body activity area in the environment where the camera belongs, and further comprising: when the camera starts to rotate, the camera is enabled to collect a human body movement angle set of user movements in the environment of the camera according to a third set duration; regarding an included angle range interval between the left boundary position and the right boundary position of the horizontal plane where the human body activity angle set is positioned as the angle of the second human body activity area; and/or determining the freeze position required by the camera in the environment, including: when the horizontal visual angle is more than or equal to the angle of the human body active area, determining that the number of the stop-motion positions required by the camera is one, and determining that one stop-motion position is specifically located: the central line of the angle of the human body activity area; or when the horizontal visual angle is less than 1/(n-1) of the human body active area angle and the horizontal visual angle is more than or equal to 1/n of the human body active area angle, determining that the number of the stop-motion positions required by the camera is n, and determining that the n stop-motion positions are specifically located respectively: dividing the human body movement region angle n equally, and obtaining the central line of each sub-region angle in the n sub-region angles; wherein n is a natural number, and n is not less than 2.

In accordance with another aspect of the present invention, there is provided an air conditioner including: the image acquisition apparatus described above.

Optionally, the air conditioner includes: at least one of a cabinet machine and a wall-mounted machine; and/or when the camera of the image acquisition device in the air conditioner is inclined downwards by a first set angle, if the air conditioner comprises a cabinet, the first set angle of the downward inclination of the camera in the cabinet comprises: 10-20 degrees; and/or, if the air conditioner includes a wall mounted machine, the first set angle of the camera downward tilting in the wall mounted machine includes: 20-40 degrees.

In accordance with another aspect of the present invention, there is provided a control method of an air conditioner, including: when the air conditioner comprises a driving mechanism, a linkage mechanism and a camera, the corresponding control of at least one current rotation state of the camera, namely the starting rotation, the rotation speed, the rotation direction and the stopping rotation, is realized by controlling at least one of the starting operation, the operation speed, the operation direction and the stopping operation of the driving mechanism and driving the linkage mechanism through the driving mechanism, so that the current rotation state of the camera is adapted to the current scene requirement; and/or when the camera is inclined downwards by a first set angle or is inclined upwards by a second set angle, controlling at least one current inclination state of the upward inclination or the downward inclination direction of the camera, the first set angle when the camera is inclined upwards and the second set angle when the camera is inclined downwards; wherein, the current scene requirement includes: when the camera is arranged in an adaptive manner with the air conditioner, the air conditioner adaptively outputs air supply control of corresponding air supply according to at least one of the position, the number of people, the sex, the face and the age of a user in the environment of the air conditioner, and/or the air conditioner performs limb control of running according to at least one of the gesture and the posture of the user in the environment of the air conditioner, and/or the air conditioner performs security monitoring according to whether an illegal invader exists in the environment of the air conditioner.

Optionally, the corresponding control of the current rotation state of at least one of the start rotation, the rotation speed, the rotation direction and the stop rotation of the camera specifically includes: when the camera is also used for collecting second image information, receiving the second image information collected by the camera, and determining whether a set non-human body active area exists in the second image information through a convolutional neural algorithm; when the non-human body active area exists in the second image information, controlling the camera to rotate at a speed increasing speed so as to bypass the non-human body active area or controlling the camera to stop rotating to the non-human body active area; or when the second image information does not have the non-human body active area, maintaining the current rotation state of the camera; wherein the non-human activity area comprises: based on the convolutional neural algorithm, at least one of a wall body in a network and/or an environment to which the camera belongs, furniture and household appliances with occupied space larger than a set value is learned and/or trained in advance, and at least one of the set wall body, the set furniture and the set household appliances is obtained; and/or, corresponding control of at least one current rotation state of the camera, including: determining whether the camera rotates to the stop-motion position; when the camera rotates to the stop-motion position, enabling the camera to stay at the stop-motion position for a first set time period, and/or enabling the camera to stay at the stop-motion position and then collect a second set time period; or when the camera is not rotated to the stop-motion position, continuing to rotate; the first set duration is longer than the second set duration.

Optionally, the corresponding control of the current rotation state of at least one of the start rotation, the rotation speed, the rotation direction and the stop rotation of the camera specifically further includes: determining the angle of a human body activity area in the environment of the camera; determining the required freeze position of the camera in the environment according to the relation between the angle of the human body movement area and the set horizontal visible angle of the camera so as to determine whether the camera rotates to the freeze position; and/or at least one of redetermining, self-learning and storing the angle of the human body active area according to a set period.

According to the scheme, the camera can rotate left and right through the motor dragging mechanism, so that the recognition visual field is increased; the problem that the effect of image recognition function is poor due to the fact that the single camera is small in visual angle and large in blind area is solved.

Furthermore, according to the scheme of the invention, the meaningless identification caused by shielding of the wall body, furniture and household appliances is realized by actively identifying the wall body or large furniture and the like according to the detected picture and automatically adapting the control mode of the rotation angle and the rotation speed.

Further, according to the scheme, the problem of small view of the existing camera is solved by detecting the scene wall and the shielding object and reasonably controlling the rotation of the camera; the intelligent air conditioner can realize the collection of a large-scale scene picture, can realize the wide-angle recognition of scene picture information under the condition that an air conditioner is placed at a corner or vertically close to a wall, has no blind area basically in the field of view, improves the accuracy of unmanned energy conservation, security monitoring and other functions, and realizes wide-angle intelligent air supply and wide-angle gesture control of the air conditioner.

Therefore, the technical scheme of the invention can adjust the view field of the camera by rotating the camera, controlling the rotating speed, angle, stop-motion position (i.e. the stop-motion position) and the like of the camera, and solves the problems of large view field adjustment difficulty caused by large acquisition blind area and large occupied space when the view field of a single camera is small in the prior art, thereby overcoming the defects of large view field adjustment difficulty, small application range and inconvenient use in the prior art and realizing the beneficial effects of small view field adjustment difficulty, large application range and convenient use.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.

The technical scheme of the invention is further described in detail through the drawings and the embodiments.

Drawings

FIG. 1 is a schematic diagram of an embodiment of an image capturing device according to the present invention;

FIG. 2 is a schematic view of another embodiment of an image capturing device according to the present invention;

FIG. 3 is a schematic view of an image capturing device according to still another embodiment of the present invention;

FIG. 4 is a structural diagram of an embodiment of a motor-driven camera of an air conditioner according to the present invention;

FIG. 5 is a schematic diagram illustrating an embodiment of a camera of an air conditioner according to the present invention;

FIG. 6 is a schematic diagram of a calculation process of the rotation angle and position of the camera of an embodiment of the air conditioner according to the present invention;

FIG. 7 is a flowchart illustrating an embodiment of determining whether to stop rotating according to second image information in the control method of the air conditioner according to the present invention;

FIG. 8 is a flow chart illustrating an embodiment of stopping and collecting when rotating to a stop-motion position in the control method of the air conditioner according to the present invention;

FIG. 9 is a flowchart illustrating an embodiment of a method for determining a freeze position or updating a freeze position according to an angle of a human body movement area in a control method of an air conditioner according to the present invention;

FIG. 10 is a flowchart illustrating an embodiment of determining an angle of a first human body movement area in a control method of an air conditioner according to the present invention;

fig. 11 is a flowchart illustrating an embodiment of determining an angle of a second body movement area in the control method of the air conditioner according to the present invention.

In the embodiment of the present invention, reference numerals are as follows, in combination with the accompanying drawings:

10-a driving mechanism; 11-motors (e.g., drive motor, rotary motor); 20-linkage mechanism; 21-a first gear (e.g., a drive gear); 22-a second gear (e.g., a driven gear); 23-connecting rod; 30-a camera; 40-a protection mechanism; 41-front cover; 42-a rear cover; 43-vertical guard; 50-controller.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to specific embodiments of the present invention and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

According to an embodiment of the present invention, there is provided an image capturing apparatus, a schematic structural diagram of an embodiment of the apparatus of the present invention as shown in fig. 1. The image acquisition device may include: a driving mechanism 10, a linkage mechanism 20 and a camera 30.

In an alternative example, the driving mechanism 10 may be used to drive the linkage mechanism 20.

Alternatively, the driving mechanism 10 may include: a motor 11.

For example: the camera is driven to rotate left and right through the motor, so that wide-angle detection is realized, and the problem of small field of view of the camera is solved. The rotation means the speed, angle, position (e.g., stop-motion position, etc.) of rotation.

For example: the camera (for example, the camera 30) is driven to rotate by a motor (for example, the motor 11), so that multi-point stay collection is realized, and the visual angle is increased.

Therefore, the motor is used for driving the linkage mechanism, the driving mode is convenient, and the reliability is high.

More optionally, the motor 11 may include: at least one of a driving motor and a rotating motor.

For example: when no other shielding objects exist on the wall surface where the air conditioner is located, the camera can be driven to rotate left and right through the rotating motor, and the visual range of the air conditioner is about 180 degrees.

For example: the motor drives the camera to rotate left and right at the installation position by taking the shaft as the center.

Therefore, the driving of the linkage mechanism can be more flexible and more convenient by using various types of motors.

In an alternative example, the linkage mechanism 20 is adapted to the driving mechanism 10, and may be used to drive the camera 30 to rotate (e.g. rotate left and right in a horizontal direction) under the driving of the driving mechanism 10, so as to increase the acquisition range of the camera 30; and the camera 30 is stopped at least one set stop-motion position, so that the camera can acquire by taking the stop-motion position as a visual angle center.

For example: the camera is driven to rotate, so that the problem that the single camera is small in visual angle, large in blind area and poor in image recognition function effect can be solved.

For example: the camera can rotate left and right through a motor dragging mechanism (for example, a mechanism consisting of a rotating motor, a gear set and a connecting rod), so that the recognition visual field is increased; the rotation angle and the rotation speed of the camera can be adaptively changed; the problems that the rotation of the invalid visual field acquires invalid or nonsensical images, hysteresis is generated and the like can be solved.

Optionally, the linkage mechanism 20 may include: gear sets and links 23.

In an alternative specific example, the gear set is adapted to be disposed between the first end of the connecting rod 23 and the driving mechanism 10.

In an alternative specific example, the second end of the connecting rod 23 is adapted to be disposed with the camera 30. For example: the second end of the connecting rod 23 is fixedly mounted with the camera 30.

Therefore, through the adaptation setting of gear train and connecting rod, form link gear, simple structure, and based on actuating mechanism's drive, drive rotatory linkage reliability height of camera.

More optionally, the gear set may include: a first gear 21 and a second gear 22.

In a more alternative specific example, the first gear 21 is adapted to be disposed with the driving mechanism 10. For example: when the driving mechanism 10 may include the motor 11, the first gear 21 is fixedly mounted to a shaft of the motor 11.

In a more alternative specific example, the second gear 22 is disposed in meshing engagement with the first gear 21 (i.e., the first gear 21 and the second gear 22 cooperate with each other).

In a more alternative embodiment, the first end of the connecting rod 23 is adapted to be positioned with the second gear 22. For example: the first end of the connecting rod 23 is fixedly mounted with the second gear 22.

For example: the shaft of the motor 11 drives the first gear 21 to rotate, the first gear 21 drives the second gear 22 to rotate, the second gear 22 drives the connecting rod 23 to rotate, and the connecting rod 23 drives the camera 30 to rotate.

Therefore, through the adaptive arrangement of the first gear and the second gear, the gear set acts between the driving mechanism and the connecting rod more reliably.

Wherein, the first gear 21 may include: a drive gear; and/or, the second gear 22 may include: a driven gear.

For example: the connecting rod 23 is fixedly arranged with a second gear (e.g. driven gear) 22. The motor (such as a driving motor, a rotating motor, etc.) 11 is fixedly arranged with the first gear (such as a driving gear) 21, and the rotation of the motor 11 to drive the mounting box can be realized through the cooperation of the first gear 21 and the second gear 22, namely, the rotation of the camera increases the visual angle.

From this, through the adaptation setting of drive gear and driven gear for the gear train is based on actuating mechanism's drive, can more reliably, more stably drive the camera rotatory through the connecting rod, and the security is good.

In an alternative example, the camera 30, which is adapted to the linkage 20, may be configured to collect (for example, collect statically) the first image information in the first collection range to which the view center belongs, with the freeze position as the view center when the camera stays at the freeze position.

Therefore, the camera stays at the stop-motion position for acquisition, so that the image acquisition at the stop-motion position is more stable, and the image acquisition effect is ensured.

In an alternative example, the camera 30 is tilted downward by a first set angle or tilted upward by a second set angle in a vertical direction.

For example: referring to the example shown in fig. 5, the camera has a certain declination angle (e.g., declination angle Q) in combination with the overall machine (e.g., air conditioner) structure.

For example: the downward inclination angle of the cabinet machine is between 10 and 20 degrees relative to the horizontal plane. The declination angle of the wall-mounted machine is 20-40 degrees, the camera can be guaranteed to detect the ground human body movement area as much as possible by declination, and the effective identification area of the air conditioner based on images is increased.

Therefore, the camera is inclined in the vertical direction, so that the acquisition range is enlarged, the flexibility is good, and the reliability is high.

In an alternative example, the camera 30 may be further configured to acquire (e.g., dynamically acquire) second image information within a second acquisition range of the self-vision when the camera is rotated under the driving of the linkage 20.

Therefore, the camera is enabled to collect images when rotating, so that the image collection range is larger, the image collection content is more comprehensive, and the humanization is good.

In an alternative example, the linkage 20 may be further configured to move the view center of the camera 30 to the freeze position (i.e., at least one freeze position set within the acquisition range of the camera 30) before at least one freeze position of the camera 30 is predetermined or set, and/or before the camera 30 is caused to stay at the set at least one freeze position, so that the camera 30 stays at the freeze position.

Therefore, the view angle center of the camera is moved to the stop-motion position, the image acquisition range at the stop-motion position is enlarged, and the accuracy is good.

In an alternative embodiment, the method may further include: a protective mechanism 40 (e.g., a mounting box).

In an alternative example, the protection mechanism 40 may be configured to at least one of house, support, strengthen, dampproof, waterproof, and dustproof at least one of the motor 11, the gear set, the link 23, and the camera 30.

For example: the upper part and the lower part of the mounting box are combined together, so that the camera module (namely the camera) can be sealed and fixed, the mounting is convenient, and the sealing is good.

For example: the PCB board of camera can be sealed and protected, such as dustproof, waterproof, dampproofing.

Therefore, the image acquisition equipment can be better protected through the adaptation setting of the protection mechanism, the operation reliability and the safety of the image acquisition equipment are improved, and the service life of the image acquisition equipment is prolonged.

Optionally, the protection mechanism 40 may include: at least one of the first protective structure, the second protective structure and the third protective structure.

In an alternative specific example, the first protection structure may be used to protect the camera 30.

More optionally, the first protection structure may include: a front cover 41 and a rear cover 42. The front cover 41 and the rear cover 42 are adapted.

In a more alternative specific example, an opening is provided in the front cover 41. For example: front cameras, rear cameras and the like can be arranged to enlarge the acquisition range, improve the acquisition flexibility and the like.

The opening is adapted to an image acquisition hole (for example, a visual hole) of the camera 30, so as not to block the visual hole of the camera, and make the acquisition range of the camera as large as possible.

For example: the camera's visual hole may be a hole exposing the camera on the front cover 41 for exposing the camera's lens.

From this, form first protection machanism through protecgulum and hou gai adaptation setting to set up the trompil on first protection machanism, guaranteed the protection to the camera on the one hand, guaranteed the convenience that the camera carried out image acquisition on the other hand.

In an alternative specific example, the second protection structure, which is adapted to be disposed between the first protection structure and the second protection structure, may be used to protect the connecting rod 23.

For example: the mounting box has a connecting rod 23.

More optionally, the second protection structure may include: vertical guard 43. The vertical guard 43 is vertically disposed below the first guard structure.

For example: the mounting box is formed by integrating an upper part and a lower part.

From this, through the second protective structure of vertical setting, there is the protection connecting rod more, it is good to use the convenience.

In an alternative specific example, the third protection structure may be used to protect at least one of the motor 11 and the gear set.

Therefore, any part in the image acquisition equipment can be respectively subjected to adaptive protection through the arrangement of the plurality of protection mechanisms, so that the flexibility is good, and the humanization is good.

Optionally, the protection mechanism 40 may further include: at least one of a clamping groove structure and a clamping structure.

In an alternative specific example, the camera 30 is adapted to be disposed in the first protection structure through at least one of the clamping groove structure and the fastening structure.

For example: referring to the example shown in fig. 4, a camera (for example, a camera 30) is assembled in a mounting box, the mounting box is composed of an upper part and a lower part, the camera is fixed in an upper part in the mounting box in a clamping groove and buckling mode, the upper part is provided with an opening, and after the camera is mounted, a camera visible hole is exactly aligned to the opening of the mounting box.

Therefore, the image acquisition device is beneficial to improving the stability and reliability of installation between the image acquisition device and the protection mechanism through the structures such as the clamping groove and the buckle which are matched with the protection mechanism, and further the working safety of the image acquisition device can be ensured.

In an alternative embodiment, the method may further include: and a controller 50.

In an alternative example, the controller 50 is configured to adapt to the driving mechanism 10, and may be configured to implement corresponding control on the current rotation state of at least one of the start rotation, the rotation speed, the rotation direction, and the stop rotation of the camera 30 by controlling at least one of the start operation, the operation speed, the operation direction, and the stop operation of the driving mechanism 10, so as to adapt the current rotation state of the camera 30 to the current scene requirement.

Wherein, the current scene requirement may include: when the camera 30 is adapted to the air conditioner, the air conditioner adaptively outputs the air supply control of the corresponding air supply according to at least one of the position, the number of people, the sex, the face and the age of the user in the environment of the air conditioner, and/or the air conditioner performs the limb control according to at least one of the gesture and the posture of the user in the environment of the air conditioner, and/or the air conditioner performs the security monitoring according to whether the illegal intruder is prompted in the environment of the air conditioner.

For example: different functions in different functional cameras may include: intelligent air supply, gesture control, security monitoring and the like, and the application functions of the air conditioner have different logic requirements on rotation of the camera.

In an alternative specific example, the intelligent air supply may include: human body angles, human-machine distances, the number of people, human face attributes (gender, age), room layout and the like are detected, and comfortable air supply and energy saving of the air conditioner are realized.

Such as: after detecting that the child approaches the air conditioner, the wind speed automatically adjusts the low wind level or does not blow the child.

For example: detecting human body angles, human-machine distances, number of people, face attributes (gender, age), room layout, etc., may include: the image recognition module picks up the image through a Camera (Camera), after the image recognition algorithm operated by the image recognition module (for example, CPU) calculates, the recognition results of the gesture, the face, the human body and the face attribute are generated, corresponding air conditioning scene strategies are added to the recognition results according to the requirements of air conditioning scenes, the recognition results are structured, serial port commands corresponding to the recognition results are sent to the control board through the hardware serial port, the control board receives the control commands sent by the serial port, and corresponding control operation is correspondingly executed.

For example: after the intelligent air supply function is started, the rotating motor drives the camera to perform single-point or multi-point stop motion detection within the range of the effective active area of the human body.

In an alternative specific example, gesture recognition may include: the on-off, temperature, wind speed and air supply mode of the air conditioner can be adjusted through specific gestures. After the gesture recognition function is started, other recognition functions are still detected at the freeze position, and only the gesture has recognition awakening gesture actions in the freeze position and the rotating process. If the awakened gesture is recognized, the rotating motor immediately stops rotating, and the image recognition gesture control function wakes up, so that the camera keeps gesture recognition on the user operating by the gesture. And when the gesture function of the user is finished and the gesture function is maintained for a certain time, the rotary motor continues to work.

In an alternative specific example, security monitoring may include: the arming can be started through the mobile phone APP or the air conditioner key. After the defense is distributed, the rotating motor drives the camera to perform single-point or multi-point stop motion detection within the range of the effective active area of the human body. When a human intrusion is detected, the human body angle is locked. If a single person is invaded, the human body angle is locked, the camera is locked and points to the invader, at the moment, the camera is used for photographing at fixed time and uploading videos to the server, and the invasion reminding can be pushed to the mobile phone of the home owner. When the face recognition function is provided, the optimal face recognition angle position can be fixed, and whether the face recognition is a stranger or a registered family member is achieved through face recognition. If the user is a stranger, the user still invades the reminding device.

Therefore, the current rotation state of the camera is adaptively controlled through the controller, so that the image acquisition equipment works more flexibly and accurately.

Optionally, the corresponding control of the current rotation state of at least one of the start rotation, the rotation speed, the rotation direction and the stop rotation of the camera 30 by the controller 50 may specifically include: when the camera 30 may also be used to collect second image information, the second image information collected by the camera 30 is received, and whether the second image information has a set non-human body active area is determined through a convolutional neural algorithm.

In an alternative specific example, the corresponding control of the current rotation state of at least one of the start rotation, the rotation speed, the rotation direction, and the stop rotation of the camera 30 by the controller 50 may specifically further include: when the non-human body active area exists in the second image information, controlling the camera 30 to rotate at a speed increasing speed so as to bypass the non-human body active area or controlling the camera 30 to stop rotating to the non-human body active area; or when the non-human body active region is not present in the second image information, maintaining the current rotation state of the camera 30.

For example: the camera can rotate left and right through the motor dragging mechanism, and the recognition visual field is increased. The nonsensical recognition caused by shielding of the wall body, furniture and household appliances is realized by actively recognizing the wall body or large furniture and the like according to the detected picture and automatically adapting the control mode of the rotation angle and the rotation speed.

For example: according to the detected pictures, the wall body or large furniture and the like can be actively identified, the control mode of the rotation angle and the rotation speed can be automatically adapted, and meaningless identification caused by shielding of the wall body, furniture and household appliances can be realized. The rotation modes of cameras with different functions are different, reasonable control is realized, and the reasonable scene requirement of the adaptation of corresponding function points is met.

For example: the detected pictures are acquired, the pictures in the scene can be acquired through a camera mounted in the air conditioner, and the pictures are transmitted to an image module for analysis and processing.

For example: the detected picture can be a scene picture acquired by the image recognition module, for example, the picture of the camera is acquired at the rate of 1s10 frames.

For example: the image recognition module is used for analyzing and processing the image frames. For example: and judging whether the obtained image picture has large furniture, wall body and the like or not through a convolution neural algorithm. Based on the convolutional neural algorithm, training and recognition can be performed on large furniture in advance. If the large furniture or the wall is identified, the rotating mechanism of the camera rapidly bypasses or does not drive the camera to rotate to a position where the wall and the large furniture can be seen.

For example: when the effective angle A (namely the angle A of the first human body movable area) is detected, and the large household appliance shields the visual field, and the shielding visual angle range is larger than a certain angle, the motor rotating mechanism rotates more rapidly in the area.

Wherein, the non-human body activity area may include: based on the convolutional neural algorithm, at least one of a wall body in a network and/or an environment where the camera 30 belongs, furniture and household appliances with occupied space larger than a set value is learned and/or trained in advance, and at least one of the set wall body, the set furniture and the set household appliances is obtained.

For example: air conditioners are typically installed in corners (e.g., 90 ° corners), and if the camera view is larger, it is possible that the camera view is a wall or a blocked cabinet during rotation, rather than a human activity area. Such walls or blocked cabinets, etc. in the camera view can be considered as invalid views.

For example: by detecting scene walls and shielding objects (such as large furniture, household appliances and the like), the problem of small view of the existing camera is solved by reasonably controlling the rotation of the camera.

Therefore, the second image information can be identified, the work of the image acquisition equipment can be better controlled, and the reliability and the accuracy are high.

Optionally, the corresponding control of the current rotation state of at least one of the start rotation, the rotation speed, the rotation direction and the stop rotation of the camera 30 by the controller 50 may specifically further include: it is determined whether the camera 30 is rotated to the freeze position.

For example: referring to the example shown in fig. 6, the rotation control manner of the camera may include: and the method is applicable to a stop-motion position.

In an alternative specific example, the corresponding control of the current rotation state of at least one of the start rotation, the rotation speed, the rotation direction, and the stop rotation of the camera 30 by the controller 50 may specifically further include: when the camera 30 rotates to the stop-motion position, enabling the camera 30 to stay at the stop-motion position for a first set time period, and/or enabling the camera 30 to stay at the stop-motion position and then collecting a second set time period; or continue to rotate when the camera 30 is not rotated to the freeze position.

The first set duration is longer than the second set duration.

For example: the residence time of the stop-motion position is longer than the acquisition time of the camera, so that the image acquisition is performed after the stop-motion of the camera, and the acquired image is not blurred.

Therefore, whether the camera rotates to the stop-motion position or not is determined, and the adaptation processing is carried out according to the determination result, so that the reliability is high and the accuracy is good.

Optionally, the corresponding control of the current rotation state of at least one of the start rotation, the rotation speed, the rotation direction and the stop rotation of the camera 30 by the controller 50 may specifically further include: before determining whether the camera 30 rotates to the freeze position, determining an angle of a human body active area in an environment where the camera 30 belongs.

More optionally, the human body movement area angle may include: at least one of the first human body movement region angle and the second human body movement region angle.

Therefore, through the angles of the human body movable areas in various forms, the rotation mode of the camera is more diversified, and the image acquisition mode is more flexible.

More optionally, determining the angle of the human body active area in the environment where the camera 30 belongs may include: when the camera 30 starts to rotate, the camera 30 is made to rotate to the maximum positions of the left and right sides of the horizontal plane where the camera 30 is located respectively to stay for collection, and the leftmost image information and the rightmost image information are obtained.

In a more optional specific example, determining the angle of the human body active area in the environment where the camera 30 belongs may further include: and determining a leftmost human body activity area position and a rightmost human body activity area position except the non-human body activity area according to the leftmost image information and the rightmost image information, and determining an angle range between the leftmost human body activity area position and the rightmost human body activity area position as the first human body activity area angle (namely a first human body activity area angle A).

For example: after the air conditioner is initially electrified and an image recognition algorithm is started, the rotating mechanism rotates to the left maximum position and the right maximum position and stays, the image recognition module analyzes the image pictures at the left maximum position and the right maximum position, judges the horizontal critical angles of the wall area position and the non-wall area (for example, the left furniture, the right furniture and the like are used as the wall, the left furniture and the right furniture are used as shielding visual fields), the angle range of the left critical angle and the right furniture is regarded as a first human body movable area angle A, and the horizontal visual angle of the camera module body is K.

Therefore, the first human body moving area angle is determined based on the second image information in the rotation process, timeliness is high, and reliability is high.

More optionally, determining the angle of the human body active area in the environment where the camera 30 belongs may further include: when the camera 30 starts to rotate, the camera 30 is enabled to collect a set of human body movement angles of user movements in the environment of the camera according to a third set duration.

In a more optional specific example, determining the angle of the human body active area in the environment where the camera 30 belongs may further include: and regarding an included angle range interval between the left boundary position and the right boundary position (such as the leftmost position of the belonging environment and the rightmost position of the belonging environment) of the human body activity angle set, as the second human body activity area angle (namely a second human body activity area angle L).

For example: after the air conditioner is initially electrified, an angle set of human body movement in a certain time D is collected, and the angle range interval at the leftmost side and the rightmost side of the human body movement angle is regarded as a second human body movement area angle L.

Therefore, the angle of the second human body movement area is determined according to the human body movement area in the rotation process, so that the efficiency is high and the accuracy is good.

In an alternative specific example, the corresponding control of the current rotation state of at least one of the start rotation, the rotation speed, the rotation direction, and the stop rotation of the camera 30 by the controller 50 may specifically further include: according to the relation between the human body movement area angle (such as a first human body movement area angle A, a second human body movement area angle L and the like) and the set horizontal visual angle (such as a horizontal visual angle K) of the camera 30, the stop-motion position required by the camera 30 in the environment is determined, so that whether the camera 30 rotates to the stop-motion position is determined.

For example: for the second human body movement area angle L, it is inferred how much freeze and the freeze angle position are needed with reference to the effective angle a (i.e., the first human body movement area angle a).

Therefore, the fixed stop-motion position of the camera is determined according to the relation between the angle of the human body movement area and the horizontal visual angle of the camera, and the method is high in reliability and good in accuracy.

More optionally, determining the freeze position required by the camera 30 in the environment may include: when the horizontal visual angle is greater than or equal to the human body active area angle, determining that the number of the freeze positions required by the camera 30 is one, and determining that one of the freeze positions is specifically located: the central line of the angle of the human body movement area.

For example: if K is more than or equal to A, the camera is larger than the actual effective demand angle in visual angle, and the camera is fixed at 1 position without rotation. At this time, the center angle of the first human body movable area angle A is taken as a fixed point, and the center angle of the camera is adjusted to the center angle of the movable area A through the rotating mechanism.

In a more alternative specific example, determining the freeze position required by the camera 30 in the environment may include: when the horizontal visual angle is less than 1/(n-1) of the human body active area angle and the horizontal visual angle is greater than or equal to 1/n of the human body active area angle, determining that the number of the freeze positions required by the camera 30 is n, and determining that the n freeze positions are specifically located respectively: and equally dividing the angle n of the human body movement region, and obtaining the central line of each sub-region angle in the n sub-region angles.

Wherein n is a natural number, and n is not less than 2.

For example: when the horizontal visual angle is smaller than the human body movement area angle and is larger than or equal to 1/2 of the human body movement area angle, determining that the number of the stop-motion positions required by the camera 30 is two, and determining that the two stop-motion positions are specifically located respectively: dividing the angle of the human body movement area into two equal parts, and obtaining the central line of each of the two sub-area angles.

For example: if K is less than A and A/2 is less than or equal to K, the visual angle of the camera is describedThe angle is smaller than the angle A of the actual first human body moving area, and the angle interval only needs to fix 2 positions. At this time, the effective angle A (i.e. the first human body movement area angle A) is divided into left and right areas, and two central angles B of the left and right areas are used _{Left center} 、B _{Right center} As a freeze position. The rotating motor only needs to rotate the camera to the two positions for stopping.

For example: when the horizontal visual angle is smaller than 1/2 of the angle of the human body movement area and the horizontal visual angle is larger than or equal to 1/3 of the angle of the human body movement area, determining that the number of the stop-motion positions required by the camera 30 is three, and determining that the three stop-motion positions are specifically located in the following positions: and trisecting the angle of the human body movement region to obtain the center line of each of the two sub-region angles.

For example: similarly, when the view angle of the camera is smaller and a plurality of stop-motion positions are needed to realize that the effective stop-motion interval can be completely identified, the method is referred to as the above. If K is less than A.cndot.A/2 > K.cndot.A/3 < K, then dividing into 3 fixed-point.

Therefore, the number and the specific positions of the stop-motion positions of the camera are determined according to different relations between the horizontal visual angle and the angle of the human body active area, so that the reliability is high, and the humanization is good.

In an alternative specific example, the corresponding control of the current rotation state of at least one of the start rotation, the rotation speed, the rotation direction, and the stop rotation of the camera 30 by the controller 50 may specifically further include: and at least one of redetermining, self-learning and storing the angle of the human body active area according to a set period.

For example: the active area determination and self-learning memory are performed once every D cycles and the active area determination is stored in a memory (e.g., EEPROM).

Therefore, the image acquisition device can acquire the images of the angles of the human body active areas more accurately and reliably by updating the angles of the human body active areas regularly.

In an alternative example, the controller 50 may also be adapted to at least one of the linkage 20 and the camera 30. If the controller 50 is configured to be adapted to the camera 30, when the camera 30 is tilted downward by a first set angle or is tilted upward by a second set angle, at least one current tilt state of the camera 30 is controlled in a tilt direction of the camera 30 that is tilted upward or downward, the first set angle when tilted upward, and the second set angle when tilted downward.

Therefore, the controller is used for adaptively controlling the current tilting state of the camera, so that the flexibility is good and the reliability is high.

Through a large number of experiments, the technical scheme of the embodiment is adopted, and the camera can rotate left and right through the motor dragging mechanism, so that the recognition field of view is increased; the problem that the effect of image recognition function is poor due to the fact that the single camera is small in visual angle and large in blind area is solved.

According to an embodiment of the present invention, there is also provided an air conditioner corresponding to an image pickup apparatus. The air conditioner may include: an image acquisition device as described above.

Therefore, the air conditioner is controlled based on image recognition by using the image acquisition equipment, the image acquisition is more accurate, and the recognition control is more reliable.

In an alternative example, the air conditioner may include: at least one of a cabinet machine and a wall hanging machine.

In an alternative example, referring to the example shown in fig. 4 and 5, when the camera 30 of the image capturing device in the air conditioner is inclined downward by a first set angle, if the air conditioner may include a cabinet, the first set angle in which the camera 30 is inclined downward in the cabinet may include: 10-20 degrees.

Optionally, if the air conditioner may include a wall mounted device, the first set angle of the camera 30 tilting downward in the wall mounted device may include: 20-40 degrees.

For example: the intelligent air conditioner can realize the collection of a large-scale scene picture, can realize the wide-angle recognition of scene picture information under the condition that an air conditioner is placed at a corner or vertically close to a wall, has no blind area basically in the field of view, improves the accuracy of unmanned energy conservation, security monitoring and other functions, and realizes wide-angle intelligent air supply and wide-angle gesture control of the air conditioner

From this, through setting up different declining angles to different grade type air conditioner, the flexibility is better, and the accuracy and the convenience of control are better.

In an alternative embodiment, the air conditioner can realize that the camera can rotate left and right by a motor dragging mechanism (for example, a mechanism consisting of a rotating motor, a gear set and a connecting rod), so that the recognition field of view is increased; the rotation angle and the rotation speed of the camera can be adaptively changed; the problems that the rotation of the invalid visual field acquires invalid or nonsensical images, hysteresis is generated and the like can be solved.

For example: because the camera is rotated to an area of invalid field of view to collect, such as a wall, it is entirely a white wall picture, and the dwell time to detect this is of little significance. If the area where people move is updated in a state, the camera can not be seen in time because the visual angle of the camera rotates into the wall, and hysteresis is inevitably caused.

In an alternative example, a camera rotation mechanism includes: a drive mechanism 10, a linkage mechanism 20 and a mounting box.

Optionally, referring to the example shown in fig. 4, a camera (for example, a camera 30) is assembled in the mounting box, the mounting box is composed of an upper part and a lower part, the camera is fixed in an upper part in the mounting box in a clamping groove and buckling mode, the upper part is provided with an opening, and after the camera is mounted, a camera visible hole is exactly aligned to the opening of the mounting box. The upper part and the lower part of the mounting box are combined together, so that the camera module (namely the camera) can be sealed and fixed, the mounting is convenient, and the sealing is good. The mounting box has a connecting rod 23, the connecting rod 23 being fixedly arranged with a second gear (e.g. driven gear) 22. The motor (such as a driving motor, a rotating motor, etc.) 11 is fixedly arranged with the first gear (such as a driving gear) 21, and the rotation of the motor 11 to drive the mounting box can be realized through the cooperation of the first gear 21 and the second gear 22, namely, the rotation of the camera increases the visual angle.

Wherein, the shaft of the motor 11 drives the first gear 21 to rotate, the first gear 21 drives the second gear 22 to rotate, the second gear 22 drives the connecting rod 23 to rotate, and the connecting rod 23 drives the camera 30 to rotate.

Optionally, referring to the example shown in fig. 5, the camera has a certain declination angle (e.g., declination angle Q) in combination with the overall machine (e.g., air conditioner) structure.

In an alternative embodiment, the control mode of the rotation angle and the rotation speed can be automatically adapted according to detected pictures to actively identify the wall body or large furniture and the like, so that meaningless identification caused by shielding of the wall body, furniture and household appliances is realized. The rotation modes of cameras with different functions are different, reasonable control is realized, and the reasonable scene requirement of the adaptation of corresponding function points is met.

For example: the rotation modes of cameras with different functions can comprise: the camera is driven to rotate left and right through the motor, so that wide-angle detection is realized, and the problem of small field of view of the camera is solved. The rotation means the speed, angle, position (e.g., stop-motion position, etc.) of rotation.

In an alternative example, the rotation control manner of the camera may include: the air conditioner is generally arranged at a corner or a single-sided wall-leaning position of a living room, and the visible range of the air conditioner is required to be about 180 degrees, so that various application conditions of scenes can be basically met. The visual range of the general camera is 50-90 degrees, and if the camera is fixed, a large part of blind areas exist. According to the technical scheme, the motor (for example, the motor 11) drives the camera (for example, the camera 30) to rotate, so that multi-point stay collection is realized, and the visual angle is increased.

Wherein, the rotation angle of 50-90 degrees refers to a horizontal detection angle.

For example: the multi-point location stay collection may be: the stop position is taken as the stop point, the stop point is acquired, namely, the stop point is positioned, the rotating motor stops for a certain time, and at the moment, the camera is used for capturing the scene image picture, so that the problem of blurring of the capturing picture of the camera in rotation can be solved.

In an alternative example, referring to the example shown in fig. 6, the rotation control manner of the camera may include: and the method is applicable to a stop-motion position.

Optionally, after the air conditioner is initially powered on to start an image recognition algorithm, the rotating mechanism rotates to the left maximum position and the right maximum position and stays, the image recognition module analyzes the image pictures at the left maximum position and the right maximum position, judges the horizontal critical angles of the wall area position and the non-wall area (for example, large furniture and other shielding visual fields are left and right to be regarded as the wall), and regards the angle range of the left critical angle and the right critical angle as a first human body movable area angle A, and the horizontal visual angle of the camera module body is K.

(1) If K is more than or equal to A, the camera is larger than the actual effective demand angle in visual angle, and the camera is fixed at 1 position without rotation. At this time, the center angle of the first human body movable area angle A is taken as a fixed point, and the center angle of the camera is adjusted to the center angle of the movable area A through the rotating mechanism. When K is more than or equal to A, the central angle is the central angle of the human body active area.

(2) If K is less than A and A/2 is less than or equal to K, the camera visibility angle is smaller than the angle A of the actual first human body movable area, and the angle interval is only needed to fix 2 positions. At this time, the effective angle A (i.e. the first human body movement area angle A) is divided into left and right areas, and two central angles B of the left and right areas are used _{Left center} 、B _{Right center} As a freeze position. The rotating motor only needs to rotate the camera to the two positions for stopping.

(3) Similarly, when the view angle of the camera is smaller and a plurality of stop-motion positions are needed to realize that the effective stop-motion interval can be completely identified, the method is referred to as the above. If K is less than A.cndot.A/2 > K.cndot.A/3 < K, then dividing into 3 fixed-point.

The retention time of the stop-motion position is longer than the acquisition time of the camera, so that the image acquisition is performed after the camera stops motion, and the acquired image is not blurred.

Optionally, after the air conditioner is initially powered on, an angle set of human body movement in a certain time D is collected, and the angle range interval at the leftmost and rightmost angles of the human body movement is regarded as a second human body movement area angle L. At this time, it is inferred how much freeze and the freeze angle position are needed with reference to the effective angle a (i.e., the first human body movement area angle a). The active area determination and self-learning memory are performed once every D cycles and the active area determination is stored in a memory (e.g., EEPROM).

In an alternative example, the rotation control manner of the camera may include: and (3) controlling the rotation speed.

Optionally, when the effective angle a (i.e. the angle a of the first human body active area) is detected, and the large household appliance blocks the view, and the range of the blocking view is larger than a certain angle, the wind sweeping structure rotates more rapidly in the area.

In an alternative example, the rotation control manner of the camera may include: application of different image functions.

Optionally, based on the image recognition of the camera, the air conditioner can be applied in various aspects.

(1) Intelligent air supply: human body angles, human-machine distances, the number of people, human face attributes (gender, age), room layout and the like are detected, and comfortable air supply and energy saving of the air conditioner are realized.

(2) Gesture recognition: the on-off, temperature, wind speed and air supply mode of the air conditioner can be adjusted through specific gestures. After the gesture recognition function is started, other recognition functions are still detected at the freeze position, and only the gesture has recognition awakening gesture actions in the freeze position and the rotating process. If the awakened gesture is recognized, the rotating motor immediately stops rotating, and the image recognition gesture control function wakes up, so that the camera keeps gesture recognition on the user operating by the gesture. And when the gesture function of the user is finished and the gesture function is maintained for a certain time, the rotary motor continues to work.

(3) And (3) security monitoring: the arming can be started through the mobile phone APP or the air conditioner key. After the defense is distributed, the rotating motor drives the camera to perform single-point or multi-point stop motion detection within the range of the effective active area of the human body. When a human intrusion is detected, the human body angle is locked. If a single person is invaded, the human body angle is locked, the camera is locked and points to the invader, at the moment, the camera is used for photographing at fixed time and uploading videos to the server, and the invasion reminding can be pushed to the mobile phone of the home owner. When the face recognition function is provided, the optimal face recognition angle position can be fixed, and whether the face recognition is a stranger or a registered family member is achieved through face recognition. If the user is a stranger, the user still invades the reminding device.

In an alternative example, based on the image recognition function of the camera, the air conditioner can detect the position of the human body through the camera, and intelligently brings a comfortable air supply mode for the user. The sex and age can be detected, and if the child is identified, cold and the like can not be caused by blowing cold air. Can recognize the gesture of human body, and further realize the limb control of air conditioner. And detecting whether a person invades indoors, and early warning if the person invades.

Since the processes and functions implemented by the air conditioner of the present embodiment substantially correspond to the embodiments, principles and examples of the apparatus shown in fig. 1 to 3, the description of the present embodiment is not exhaustive, and reference may be made to the related descriptions in the foregoing embodiments, which are not repeated herein.

Through a large number of experiments, the technical scheme of the invention is adopted to realize meaningless recognition caused by shielding of walls, furniture and household appliances by actively recognizing the walls, large furniture and the like according to detected pictures and automatically adapting to the control mode of the rotation angle and the rotation speed.

According to an embodiment of the present invention, there is also provided a control method of an air conditioner corresponding to the air conditioner. The control method of the air conditioner may include: when the air conditioner described above may include the driving mechanism 10, the linkage mechanism 20 and the camera 30, by controlling at least one of the starting operation, the operating speed, the operating direction and the stopping operation of the driving mechanism 10, and driving the linkage mechanism 20 through the driving mechanism 10, the corresponding control of the current rotation state of at least one of the starting rotation, the rotating speed, the rotating direction and the stopping rotation of the camera 30 is implemented, so that the current rotation state of the camera 30 is adapted to the current scene requirement.

In an alternative example, a specific process of determining whether to stop rotating according to the second image information, that is, corresponding control of at least one current rotation state of the camera 30, including:

step S110, when the camera 30 may be further configured to collect second image information, the second image information collected by the camera 30 is received, and whether the second image information has a set non-human body active area is determined by a convolutional neural algorithm.

Step S120, when the non-human body activity area exists in the second image information, controlling the camera 30 to rotate at a speed increasing speed so as to bypass the non-human body activity area or controlling the camera 30 to stop rotating to the non-human body activity area; or when the non-human body active region is not present in the second image information, maintaining the current rotation state of the camera 30.

In an alternative example, a specific process of stopping and collecting when rotating to the freeze position may be further described with reference to a flowchart of an embodiment of stopping and collecting when rotating to the freeze position in the control method of the air conditioner of the present invention shown in fig. 8, that is, the corresponding control of at least one current rotation state of starting rotation, rotation speed, rotation direction, and stopping rotation of the camera 30 may specifically further include:

step S210, determining whether the camera 30 rotates to the freeze position.

Step S220, when the camera 30 rotates to the freeze position, making the camera 30 stay at the freeze position for a first set period of time, and/or making the camera 30 stay at the freeze position and then collecting a second set period of time; or continue to rotate when the camera 30 is not rotated to the freeze position.

The first set duration is longer than the second set duration.

In an alternative example, a flowchart of an embodiment of determining the freeze position or update process according to the human body activity area angle in the control method of the air conditioner of the present invention shown in fig. 9 may be further described, where the specific process of determining the freeze position or update process according to the human body activity area angle, that is, the corresponding control of the current rotation state of at least one of the start rotation, the rotation speed, the rotation direction, and the stop rotation of the camera 30 may specifically further include:

step S310, before determining whether the camera 30 rotates to the stop-motion position, determining an angle of a human body active area in the environment where the camera 30 belongs.

Optionally, the human body movement area angle may include: at least one of the first human body movement region angle and the second human body movement region angle.

Optionally, a specific process of determining the first human body active area angle may be further described with reference to a flowchart of an embodiment of determining the first human body active area angle in the control method of the air conditioner of the present invention shown in fig. 10, that is, determining the human body active area angle in the environment where the camera 30 belongs in step S310 may include:

In step S410, when the camera 30 starts to rotate, the camera 30 is rotated to the maximum positions on the left and right sides of the horizontal plane where the camera is located, and the left-most image information and the right-most image information are acquired.

Step S420, determining a leftmost human activity area position and a rightmost human activity area position except the non-human activity area according to the leftmost image information and the rightmost image information, and determining an angle range between the leftmost human activity area position and the rightmost human activity area position as the first human activity area angle (i.e., a first human activity area angle a).

Optionally, the following is a flowchart of an embodiment of determining the second human body activity area angle in the control method of the air conditioner according to the present invention shown in fig. 11, further describing a specific process of determining the second human body activity area angle, that is, determining the human body activity area angle in the environment where the camera 30 belongs in step S310, and may further include:

step S510, when the camera 30 starts to rotate, the camera 30 is enabled to collect a set of human body movement angles of the user movement in the environment of the camera according to a third set duration.

Step S520, regarding the range of the included angle between the left and right boundary positions (e.g., the leftmost position in the belonging environment and the rightmost position in the belonging environment) of the horizontal plane of the human body activity angle set as the second human body activity area angle (i.e., the second human body activity area angle L).

Step S320, determining the freeze position of the camera 30 required in the environment according to the relationship between the human body movement area angle (e.g. the first human body movement area angle a, the second human body movement area angle L, etc.) and the set horizontal visual angle (e.g. the horizontal visual angle K) of the camera 30, so as to determine whether the camera 30 rotates to the freeze position.

Optionally, determining the freeze position required by the camera 30 in the environment in step S320 may include: when the horizontal visual angle is greater than or equal to the human body active area angle, determining that the number of the freeze positions required by the camera 30 is one, and determining that one of the freeze positions is specifically located: the central line of the angle of the human body movement area.

In an optional specific example, determining the freeze position of the camera 30 required in the environment in step S320 may further include: when the horizontal visual angle is less than 1/(n-1) of the human body active area angle and the horizontal visual angle is greater than or equal to 1/n of the human body active area angle, determining that the number of the freeze positions required by the camera 30 is n, and determining that the n freeze positions are specifically located respectively: and equally dividing the angle n of the human body movement region, and obtaining the central line of each sub-region angle in the n sub-region angles.

Wherein n is a natural number, and n is not less than 2.

For example: if K is less than A and A/2 is less than or equal to K, the camera has a visual angle smaller than the angle A of the actual first human body moving area, and the angle interval is fixed by 2 positionsAnd (3) obtaining the product. At this time, the effective angle A (i.e. the first human body movement area angle A) is divided into left and right areas, and two central angles B of the left and right areas are used _{Left center} 、B _{Right center} As a freeze position. The rotating motor only needs to rotate the camera to the two positions for stopping.

And step S330, at least one of redetermining, self-learning and storing is carried out on the angle of the human body active area according to a set period.

In an alternative embodiment, the method may further include: when the camera 30 is tilted downward by a first set angle or is tilted upward by a second set angle, at least one current tilt state of the tilt direction of the upward tilt or downward tilt of the camera 30, the first set angle at the time of upward tilt, and the second set angle at the time of downward tilt is controlled.

Since the processes and functions implemented by the method of the present embodiment substantially correspond to the embodiments, principles and examples of the air conditioner shown in fig. 4 to 5, the description of the present embodiment is not exhaustive, and reference may be made to the related descriptions of the foregoing embodiments, which are not repeated herein.

Through a large number of experiments, the technical scheme of the invention is adopted, and the problem of small view field of the existing camera is solved by detecting the scene wall body and the shielding object and reasonably controlling the rotation of the camera; the intelligent air conditioner can realize the collection of a large-scale scene picture, can realize the wide-angle recognition of scene picture information under the condition that an air conditioner is placed at a corner or vertically close to a wall, has no blind area basically in the field of view, improves the accuracy of unmanned energy conservation, security monitoring and other functions, and realizes wide-angle intelligent air supply and wide-angle gesture control of the air conditioner.

In summary, it is readily understood by those skilled in the art that the above-described advantageous ways can be freely combined and superimposed without conflict.

The above description is only an example of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. An image capturing apparatus, comprising: a driving mechanism (10), a linkage mechanism (20) and a camera (30); wherein,

The driving mechanism (10) is used for driving the linkage mechanism (20);

the linkage mechanism (20) is used for driving the camera (30) to rotate under the driving of the driving mechanism (10) and enabling the camera (30) to stay at the set at least one stop motion position;

the camera (30) is used for acquiring first image information in a first acquisition range to which the view angle center belongs by taking the stop-motion position as the view angle center when the camera stays at the stop-motion position; the camera (30) is inclined downwards by a first set angle or is inclined upwards by a second set angle in the vertical direction; the camera (30) is further configured to acquire second image information in a second acquisition range that enters the self-vision field when driven by the linkage mechanism (20) to rotate; the linkage mechanism (20) is further used for moving the visual angle center of the camera (30) to the stop-motion position so that the camera (30) stays at the stop-motion position; the camera is rotated, the rotation speed, the rotation angle and the stop-motion position of the camera, namely the stop-motion position, are controlled, and the view field of the camera is adjusted; the nonsensical identification caused by shielding of the wall body, furniture and household appliances is realized by actively identifying the wall body or large furniture according to the detected picture and automatically adapting the control mode of the rotation angle and the rotation speed; the scene wall body and the shielding object are detected, so that the acquisition of a large-scale scene picture can be realized aiming at the reasonable control of the rotation of the camera, the situation that an air conditioner is placed at a corner or vertically close to the wall is met, scene picture information is recognized in a wide angle, the visual field is basically free of blind areas, the accuracy of unmanned energy conservation, security monitoring and other functions is improved, and the air conditioner is controlled by wide-angle intelligent air supply and wide-angle gestures;

Further comprises: a controller (50);

the controller (50) is configured to implement corresponding control of at least one current rotation state of the camera (30) by controlling at least one of a start operation, an operation speed, an operation direction, and a stop operation of the driving mechanism (10), so as to adapt the current rotation state of the camera (30) to a current scene requirement;

when the camera (30) is inclined downwards by a first set angle or is inclined upwards by a second set angle, controlling at least one current inclination state of the upward inclination or the downward inclination direction of the camera (30), the first set angle when the camera is inclined upwards and the second set angle when the camera is inclined downwards; wherein, the current scene requirement includes: when the camera (30) is adaptively arranged with the air conditioner, the air conditioner adaptively outputs air supply control of corresponding air supply quantity according to the position, the number of people, the gender, the face and the age of the users in the environment of the air conditioner; the air conditioner performs limb control running according to at least one of gestures and postures of a user in the environment of the air conditioner, and the air conditioner performs prompt security monitoring according to whether an illegal invader exists in the environment of the air conditioner;

The controller (50) controls at least one of the current rotation state of the camera (30) including:

when the camera (30) is further used for collecting second image information, the second image information collected by the camera (30) is received, and whether a set non-human body active area exists in the second image information is determined through a convolutional neural algorithm;

when the non-human body active area exists in the second image information, controlling the camera (30) to rotate at a speed increasing speed so as to bypass the non-human body active area or controlling the camera (30) to stop rotating to the non-human body active area; or when the non-human body active area is not in the second image information, maintaining the current rotation state of the camera (30);

wherein the non-human activity area comprises:

based on the convolutional neural algorithm, at least one of a wall body in a network and/or an environment where the camera (30) belongs, furniture and household appliances with occupied space larger than a set value is learned and/or trained in advance, and at least one of the wall body, the furniture and the household appliances is set;

The controller (50) controls at least one of the current rotation state of the camera (30) including the start rotation, the rotation speed, the rotation direction and the stop rotation, and specifically further includes:

determining whether the camera (30) rotates to the freeze position;

when the camera (30) rotates to the stop-motion position, enabling the camera (30) to stay at the stop-motion position for a first set time period, and enabling the camera (30) to stay at the stop-motion position and then collect a second set time period; or continuing to rotate when the camera (30) does not rotate to the stop-motion position; the first set duration is longer than the second set duration.

2. The apparatus of claim 1, wherein the device comprises a plurality of sensors,

the drive mechanism (10) includes: a motor (11);

and/or the number of the groups of groups,

the linkage mechanism (20) includes: a gear set and a connecting rod (23); wherein,

the gear set is arranged between the first end of the connecting rod (23) and the driving mechanism (10) in an adapting way;

the second end of the connecting rod (23) is arranged in a matching way with the camera (30).

3. The apparatus of claim 2, wherein the gear set comprises: a first gear (21) and a second gear (22); wherein,

The first gear (21) is matched with the driving mechanism (10);

the second gear (22) is meshed with the first gear (21);

the first end of the connecting rod (23) is matched with the second gear (22).

4. The apparatus of claim 3, wherein,

the motor (11) comprises: at least one of a drive motor and a rotary motor;

and/or the number of the groups of groups,

the first gear (21) comprises: a drive gear; and/or the number of the groups of groups,

the second gear (22) comprises: a driven gear.

5. The apparatus according to one of claims 2-4, further comprising: a protection mechanism (40);

the protection mechanism (40) is used for at least one of accommodating, supporting, reinforcing, dampproofing, waterproofing and dustproof at least one of the motor (11), the gear set, the connecting rod (23) and the camera (30).

6. The apparatus according to claim 5, wherein the shielding mechanism (40) comprises: at least one of the first protective structure, the second protective structure and the third protective structure; wherein,

the first protection structure is used for protecting the camera (30);

The second protection structure is arranged between the first protection structure and the second protection structure in an adapting way and is used for protecting the connecting rod (23);

the third protection structure is used for protecting at least one of the motor (11) and the gear set.

7. The apparatus of claim 6, wherein the guard mechanism (40) further comprises: at least one of the clamping groove structure and the clamping structure;

the camera (30) is arranged in the first protection structure in an adapting way through at least one of the clamping groove structure and the buckling structure.

8. The apparatus of claim 6 or 7, wherein,

the first guard structure includes: a front cover (41) and a rear cover (42); the front cover (41) and the rear cover (42) are arranged in an adapting way;

an opening is arranged on the front cover (41); the opening is matched with an image acquisition hole of the camera (30);

and/or the number of the groups of groups,

the second guard structure includes: a vertical guard (43); the vertical guard (43) is vertically disposed below the first guard structure.

9. The apparatus according to claim 1, wherein the controller (50) performs a corresponding control of at least one current rotation state of the camera (30) from among a start rotation, a rotation speed, a rotation direction, and a stop rotation, and in particular further comprises:

Determining the angle of a human body activity area in the environment of the camera (30);

determining the stop-motion position required by the camera (30) in the environment according to the relation between the human body movement area angle and the set horizontal visible angle of the camera (30) so as to determine whether the camera (30) rotates to the stop-motion position; and/or the number of the groups of groups,

and at least one of redetermining, self-learning and storing the angle of the human body active area according to a set period.

10. The apparatus of claim 9, wherein the human body active area angle comprises: at least one of a first human body movement area angle and a second human body movement area angle;

determining an angle of a human body active area in an environment where the camera (30) is located, comprising:

when the camera (30) starts to rotate, the camera (30) rotates to the maximum positions of the left side and the right side of the horizontal plane where the camera is positioned respectively to stay for acquisition, so that leftmost image information and rightmost image information are obtained;

determining a leftmost human body activity area position and a rightmost human body activity area position except the non-human body activity area according to the leftmost image information and the rightmost image information, and determining an angle range between the leftmost human body activity area position and the rightmost human body activity area position as the first human body activity area angle;

And/or the number of the groups of groups,

determining an angle of a human body activity area in an environment where the camera (30) is located, further comprising:

when the camera (30) starts to rotate, the camera (30) is enabled to collect a human body movement angle set of user movements in the environment of the camera according to a third set duration;

regarding an included angle range interval between the left boundary position and the right boundary position of the horizontal plane where the human body activity angle set is positioned as the angle of the second human body activity area;

and/or the number of the groups of groups,

determining the freeze position required by the camera (30) in the environment comprises:

when the horizontal visual angle is more than or equal to the angle of the human body movement area, determining that the number of the stop-motion positions required by the camera (30) is one, and determining that one stop-motion position is specifically located: the central line of the angle of the human body activity area;

or when the horizontal visual angle is less than 1/(n-1) of the human body active area angle and the horizontal visual angle is more than or equal to 1/n of the human body active area angle, determining that the number of the freeze positions required by the camera (30) is n, and determining that the n freeze positions are specifically located respectively: dividing the human body movement region angle n equally, and obtaining the central line of each sub-region angle in the n sub-region angles;

Wherein n is a natural number, and n is not less than 2.

11. An air conditioner, comprising: the image acquisition apparatus according to any one of claims 1 to 10.

12. The air conditioner according to claim 11, wherein the air conditioner comprises: at least one of a cabinet machine and a wall-mounted machine;

and/or the number of the groups of groups,

when a camera (30) of the image pickup apparatus in the air conditioner is inclined downward by a first set angle,

if the air conditioner includes a cabinet, the first set angle of the downward inclination of the camera (30) in the cabinet includes:

10-20 degrees; and/or the number of the groups of groups,

if the air conditioner includes a wall mounted device, the first set angle of the camera (30) tilting downward in the wall mounted device includes:

20°~40°。

13. a control method of an air conditioner, comprising:

when the air conditioner according to any one of claims 11-12 comprises a driving mechanism (10), a linkage mechanism (20) and a camera (30), by controlling the starting operation, the operating speed, the operating direction and the stopping operation of the driving mechanism (10) and driving the linkage mechanism (20) through the driving mechanism (10), the corresponding control of at least one current rotation state of the starting rotation, the rotating speed, the rotating direction and the stopping rotation of the camera (30) is realized, so that the current rotation state of the camera (30) is adapted to the current scene requirement;

When the camera (30) is inclined downwards by a first set angle or is inclined upwards by a second set angle, controlling at least one current inclination state of the upward inclination or the downward inclination direction of the camera (30), the first set angle when the camera is inclined upwards and the second set angle when the camera is inclined downwards;

wherein, the current scene requirement includes:

when the camera (30) is arranged in an adaptive manner with the air conditioner, the air conditioner outputs air supply control of corresponding air supply quantity in an adaptive manner according to the position, the number of people, the gender, the face and the age of the users in the environment of the air conditioner,

the air conditioner performs limb control of running according to at least one of the gestures and the postures of the user in the environment of the air conditioner,

the air conditioner carries out the security monitoring of prompt according to whether an illegal invader exists in the environment of the air conditioner;

the corresponding control of at least one current rotation state of the camera (30) in the starting rotation, the rotation speed, the rotation direction and the stopping rotation specifically comprises the following steps:

wherein the non-human activity area comprises:

the corresponding control of at least one current rotation state of the camera (30) in the starting rotation, the rotation speed, the rotation direction and the stopping rotation specifically further comprises:

determining whether the camera (30) rotates to the freeze position;

14. The method according to claim 13, wherein the corresponding control of at least one current rotation state of the camera (30) from among start rotation, rotation speed, rotation direction, stop rotation, in particular further comprises:

15. The method of claim 14, wherein the human body active area angle comprises: at least one of a first human body movement area angle and a second human body movement area angle;

and/or the number of the groups of groups,

wherein n is a natural number, and n is not less than 2.