CN114071013A - Target capturing and tracking method and device for vehicle-mounted camera - Google Patents
Target capturing and tracking method and device for vehicle-mounted camera Download PDFInfo
- Publication number
- CN114071013A CN114071013A CN202111191031.6A CN202111191031A CN114071013A CN 114071013 A CN114071013 A CN 114071013A CN 202111191031 A CN202111191031 A CN 202111191031A CN 114071013 A CN114071013 A CN 114071013A
- Authority
- CN
- China
- Prior art keywords
- target
- camera
- detail camera
- tracking
- detail
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000011217 control strategy Methods 0.000 claims abstract description 24
- 230000001133 acceleration Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 11
- 230000036461 convulsion Effects 0.000 claims description 9
- 230000003068 static effect Effects 0.000 claims description 8
- 239000013589 supplement Substances 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 7
- 230000035945 sensitivity Effects 0.000 claims description 4
- 230000006641 stabilisation Effects 0.000 claims description 4
- 238000011105 stabilization Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 238000005286 illumination Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000001502 supplementing effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/90—Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The application relates to a target capturing and tracking method for a vehicle-mounted camera, wherein the vehicle-mounted camera comprises a panoramic camera and a detail camera, and the method comprises the steps of controlling the panoramic camera to identify a target to be captured; after the panoramic camera determines the target to be snapped, acquiring the position of the target to be snapped, and adjusting the position of the detail camera according to the position of the target to be snapped; detecting a real-time relative motion state between the target to be snapshotted and the detail camera; and selecting different tracking control strategies to control the detail camera to perform tracking snapshot on the target to be snapshot based on the real-time relative motion state. According to the method, the panoramic camera and the detail camera work in a cooperative mode, after the panoramic camera identifies and selects the target to be snapshot, the detail camera is controlled to lock and track the target to be snapshot, the snapshot quality of the target to be snapshot is improved, and the problem that the snapshot quality of the target to be snapshot is poor in the prior art is solved.
Description
Technical Field
The application relates to the field of image processing, in particular to a target capturing and tracking method and device for a vehicle-mounted camera.
Background
At present, artificial intelligence is increasingly widely applied in the law enforcement field, and in order to strengthen monitoring management on motor vehicles and pedestrians on road surfaces, intelligent monitoring systems are installed on a plurality of law enforcement devices, so that objects to be snapshotted are snapshotted, if human faces or vehicles are snapshotted, subsequent management and tracking are facilitated. The existing intelligent monitoring system is often in a process of moving and capturing a snapshot by a law enforcement device, so that a target to be captured is blurred or lost due to too high moving speed or bumping driving, and the effect of capturing the snapshot by law enforcement is seriously influenced.
Aiming at the problem that the snapshot quality of the target to be snapshot is poor in the prior art, no effective solution is provided at present.
Disclosure of Invention
The embodiment provides a target snapshot and tracking method, a target snapshot and tracking device, a target snapshot and tracking system, an electronic device and a storage medium for a vehicle-mounted camera, so as to solve the problem that the snapshot quality of a target to be snapshot is poor in the related art.
In a first aspect, there is provided in this embodiment a method for object capture and tracking for a vehicle-mounted video camera, the vehicle-mounted video camera including a panoramic camera and a detail camera, the method comprising,
controlling the panoramic camera to identify a target to be snapshotted;
after the panoramic camera determines the target to be snapped, acquiring the position of the target to be snapped, and adjusting the position of the detail camera according to the position of the target to be snapped;
detecting a real-time relative motion state between the target to be snapshotted and the detail camera;
and selecting different tracking control strategies to control the detail camera to perform tracking snapshot on the target to be snapshot based on the real-time relative motion state.
In some of these embodiments, the detecting a real-time relative motion state between the object to be captured and the detail camera includes,
and determining the real-time relative motion state between the target to be captured and the detail camera according to the change of pixel points of the target to be captured in two adjacent image frames acquired by the detail camera.
In some embodiments, the determining a real-time relative motion state between the object to be captured and the detail camera according to changes of pixel points of the object to be captured in two adjacent image frames acquired by the detail camera includes,
when the change of pixel points of a target to be captured in two adjacent image frames acquired by the detail camera is larger than a preset first threshold value, determining that the real-time relative motion state is relative motion;
and when the change of pixel points of the target to be captured in two adjacent image frames acquired by the detail camera is smaller than or equal to the first threshold value, determining that the real-time relative motion state is relatively static.
In some embodiments, when the real-time relative motion state is relative motion, selecting different tracking control strategies to control the detail camera to perform tracking snapshot on the target to be snapshot based on the real-time relative motion state includes,
calculating the position coordinate value of the target to be captured in the image frame of the detail camera, calculating the position deviation value of the target to be captured at the ith moment according to the position coordinate value of the target to be captured in the image frame of the detail camera acquired at the ith moment and the ith-1 moment, obtaining the tracking speed of the detail camera according to the position deviation value, and adjusting the movement speed of the detail camera according to the tracking speed.
In some of these embodiments, said deriving a tracking speed of said detail camera from said position deviation values comprises,
the tracking speed of the detail camera includes a horizontal tracking speed VxAnd a vertical tracking velocity VySaid horizontal tracking velocity VxAnd a vertical tracking velocity VyRespectively calculating according to the following formulas;
Vx＝Kp*eix+Ki*∑eik+Kd*(eik-e(i-1)x)
Vy＝Kp*eiy+Ki*∑eiy+Kd*(eiy-e(i-1)x)
wherein,ixa horizontal position deviation value e of the target to be snapshotted at the ith momentiyA vertical position deviation value e of the target to be snapshotted at the ith moment(i-1)xThe horizontal position deviation value e of the target to be snapshotted at the i-1 th moment(i-1)yThe vertical position deviation value of the target to be snapshotted at the i-1 th moment, i is an integer larger than 1, Kp、Ki、KdThe parameters are adjusted for speed.
In some embodiments, the vehicle-mounted video camera further includes a gyroscope, and when the real-time relative motion state is relatively static, based on the real-time relative motion state, selecting different tracking control strategies to control the detail camera to perform tracking snapshot on the target to be snapshot, including,
acquiring the motion speed of the detail camera and the angular speed of the gyroscope at the ith moment, calculating the target speed of the detail camera according to the motion speed of the detail camera and the angular speed of the gyroscope, and adjusting the motion speed of the detail camera according to the target speed.
In some of these embodiments, after the adjusting the position of the detail camera according to the position of the object to be captured, the method further comprises,
detecting whether a curve or an obstacle exists in a moving path of a vehicle mounted with the vehicle-mounted camera;
if the vehicle motion path exists, the motion path of the vehicle is predicted, and motion compensation is performed on the detail camera according to the prediction result.
In some embodiments, when an obstacle exists in a motion path of the vehicle, predicting the motion path of the vehicle, and performing motion compensation on the detail camera according to a prediction result includes identifying the obstacle in the motion path of the vehicle, detecting a distance between the vehicle and the obstacle, and calculating a time when the vehicle reaches the obstacle according to a motion speed of the vehicle; and calculating the compensation acceleration and the compensation speed of the detail camera according to the time of the vehicle reaching the obstacle and the position deviation value of the target to be captured, and adjusting the motion parameters of the detail camera according to the compensation acceleration and the compensation speed.
In some of these embodiments, the compensated acceleration and compensated speed of the detail camera are calculated based on the time when the vehicle reaches the obstacle and the position deviation value of the target to be captured, including,
calculating a compensated acceleration and a compensated speed of the detail camera according to the following formulas;
jerk＝Amax/
ak＝ak-1+jerk*T
vk＝vk-1+ak*T
k＝t/T
Vk-1＝Kp*ek-1+Ki*∑ek-1+Kd*(ek-1-e(k-2))
wherein Amax is the maximum acceleration allowed by the detail camera, t is the time for the vehicle to reach the obstacle, jerk is an intermediate variable, akFor compensating acceleration, v, of the detail camerakFor the compensation speed of the detail camera, T is the discrete sampling period, Kp、Ki、KdFor adjusting the parameters, ekAnd k is the position deviation value of the target to be snapshotted at the kth moment, and k is an integer larger than 2.
In some of these embodiments, further comprising after the panoramic camera determines the target to be snapped,
identifying a target contour of the target to be captured in the image acquired by the panoramic camera to obtain a first position coordinate of the target contour in the image acquired by the panoramic camera;
obtaining a second position coordinate of the target contour in an image collected by the detail camera according to a preset corresponding relation of the position coordinates of the panoramic camera and the detail camera;
obtaining a target position coordinate according to the second position coordinate and a first included angle, wherein the first included angle is an included angle between the light supplement lamp and the detail camera;
and controlling the detail camera to move to the target position coordinate.
In some of these embodiments, the method further comprises,
when the detail camera is detected to shake, calculating the moving distance of an anti-shake device of the detail camera according to the following formula;
wherein f is the focal length of the detail camera, D is the moving distance of the anti-shake device, alpha is the shake angle of the detail camera, and SR is the image stabilization sensitivity;
and controlling the anti-shake device to move reversely according to the moving distance of the anti-shake device.
In a second aspect, there is provided in this embodiment a target capture and tracking apparatus for a vehicle-mounted camera, the apparatus comprising:
the identification module is used for controlling the panoramic camera to identify a target to be captured;
the position adjusting module is used for acquiring the position of the target to be snapped after the panoramic camera determines the target to be snapped, and adjusting the position of the detail camera according to the position of the target to be snapped;
the detection module is used for detecting the real-time relative motion state between the target to be snapshotted and the detail camera;
and the tracking snapshot module is used for selecting different tracking control strategies to control the detail camera to perform tracking snapshot on the target to be snapshot based on the real-time relative motion state.
In a third aspect, there is provided in this embodiment, a target capture and tracking system for a vehicle-mounted camera, the system comprising,
the mounting seat supports in the cloud platform of mounting seat, install panorama camera and detail camera on the cloud platform and set up in the inside control unit of cloud platform, control unit is used for carrying out the first aspect a target snapshot and tracking method for on-vehicle camera.
In a fourth aspect, an electronic device is provided in the present embodiment, and includes a memory and a processor, where the memory stores therein a computer program, and the processor is configured to execute the computer program to execute the target capturing and tracking method for a vehicle-mounted camera according to the first aspect.
In a fifth aspect, there is provided in this embodiment a computer-readable storage medium having stored thereon a computer program, characterized in that the computer program, when executed by a processor, comprises the steps of the method for object capture and tracking for a vehicle camera of the first aspect.
Compared with the related art, the target snapshot and tracking method, device, system, electronic device and storage medium for the vehicle-mounted camera provided in the embodiment control the detail camera to lock and track the target to be snapshot after the panoramic camera identifies and selects the target to be snapshot in a way that the panoramic camera and the detail camera work cooperatively, so that the snapshot quality of the target to be snapshot is improved.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a block diagram of a system for object capture and tracking of an onboard camera according to the present embodiment.
Fig. 2 is a block diagram of another object capturing and tracking system for an on-vehicle camera according to the present embodiment.
Fig. 3 is a flowchart of a target capturing and tracking method for a vehicle-mounted camera according to the present embodiment.
Fig. 4 is a flowchart of a method for detecting a real-time relative motion state between an object to be captured and a detail camera according to this embodiment.
Fig. 5 is a flowchart of another target capturing and tracking method for a vehicle-mounted camera according to the embodiment.
Detailed Description
For a clearer understanding of the objects, aspects and advantages of the present application, reference is made to the following description and accompanying drawings.
Unless defined otherwise, technical or scientific terms used herein shall have the same general meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The use of the terms "a" and "an" and "the" and similar referents in the context of this application do not denote a limitation of quantity, either in the singular or the plural. The terms "comprises," "comprising," "has," "having," and any variations thereof, as referred to in this application, are intended to cover non-exclusive inclusions; for example, a process, method, and system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or modules, but may include other steps or modules (elements) not listed or inherent to such process, method, article, or apparatus. Reference throughout this application to "connected," "coupled," and the like is not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. Reference to "a plurality" in this application means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. In general, the character "/" indicates a relationship in which the objects associated before and after are an "or". The terms "first," "second," "third," and the like in this application are used for distinguishing between similar items and not necessarily for describing a particular sequential or chronological order.
In the present embodiment, a system for capturing and tracking a target of a vehicle-mounted camera is provided, and fig. 1 is a block diagram of the system for capturing and tracking a target of a vehicle-mounted camera in the present embodiment, as shown in fig. 1, the system includes:
the mount pad supports in the cloud platform 2 of this mount pad, installs panorama camera 1, detail camera 3 and light filling device 4 on this cloud platform, and this system passes through the mount pad and installs on the vehicle, and cloud platform 2 inside is provided with system main control unit, and this system main control unit is used for accomplishing the target snapshot and the tracking of on-vehicle camera.
According to the target snapshot and tracking system provided by the embodiment, the target to be snapshot is identified and selected in a cooperative working mode of the panoramic camera and the detail camera, and then the target to be snapshot is locked and tracked, so that the detail snapshot effect is improved.
In some of these embodiments, the vehicle may be a law enforcement vehicle.
In this embodiment, a system for capturing and tracking a target of a vehicle-mounted camera is further provided, and fig. 2 is a block diagram of another system for capturing and tracking a target of a vehicle-mounted camera according to this embodiment, as shown in fig. 2, the system includes:
the mount pad supports in the cloud platform 2 of this mount pad, installs panorama camera 1, detail camera 3 and light filling device 4 on this cloud platform, and this system passes through the mount pad and installs on the vehicle, and cloud platform 2 inside is provided with system main control unit, and this system main control unit is used for accomplishing the target snapshot and the tracking of on-vehicle camera.
The panoramic camera 1 includes a sensor, a stitching unit, and a panoramic camera main control unit. The splicing unit is connected with the sensor, and the panoramic camera main control unit is connected with the splicing unit. The image collected by the sensor is spliced by the splicing unit and then transmitted to the main control unit of the panoramic camera, and the splicing unit can be realized by adopting an FPGA (Field Programmable Gate Array) chip. The panoramic camera main control unit can provide various intelligent rules, and according to preset target characteristics, the panoramic camera 1 recognizes that the target with the corresponding target characteristics is the target to be snapped. If the target feature is set as a person or a vehicle, after the panoramic camera 1 identifies the person or the vehicle, the identified object is preferably selected as a target to be snapshot, and the target to be snapshot is sent to the system main control unit for further snapshot and tracking. The panoramic camera main control unit can be realized by adopting an SOC (System-on-a-Chip) Chip.
The detail camera 3 comprises a zoom lens and a sensor, wherein the zoom lens can change focal length within a certain range so as to obtain different angles of view, images with different sizes and different scene ranges, the zoom lens is connected with the sensor, the sensor is connected with the system main control unit, and the acquired images are sent to the system main control unit.
The cradle head 2 is internally provided with a system main control unit, a cradle head single chip microcomputer, a motor and a gyroscope. The system main control unit is connected with the panoramic camera main control unit to acquire an image of a target to be snapshotted; the holder singlechip is connected with the system main control unit to control the motor according to the instruction of the system main control unit, so as to control the movement of the detail camera 3 and the light supplement device 4. The inside a plurality of motors that can set up of cloud platform 2, including horizontal motor and perpendicular motor, these a plurality of motors are connected with detail camera 3 and light filling device 4 respectively, and light filling device 4 can be light filling lamp or flash light etc. for the motion of the horizontal direction and the motion of vertical direction that receive cloud platform singlechip's command and control detail camera 3 and light filling device 4. The gyroscope is connected with the holder single chip microcomputer, the gyroscope is used for monitoring the motion parameters of the vehicle, the motion parameters of the vehicle are sent to the system main control unit through the holder single chip microcomputer, and the system main control unit determines the motion state of the vehicle through the motion parameters, such as whether the motion of the vehicle is stable or not. The method comprises the steps that after a system main control unit collects a target to be captured collected by a panoramic camera main control unit, the position of the target to be captured is obtained, a pan-tilt single chip microcomputer is controlled according to the position of the target to be captured, the pan-tilt single chip microcomputer controls a motor to adjust the position of a detail camera 3, so that the target to be captured is located in the center of an image shot by the detail camera 3, the real-time relative motion state between the target to be captured and the detail camera 3 is detected, and different tracking control strategies are selected to control the detail camera 3 to track and capture the target to be captured based on the real-time relative motion state. The system main control unit can be realized by adopting an SOC chip.
According to the target snapshot and tracking system provided by the embodiment, in a way that the panoramic camera and the detail camera work cooperatively, after the system main control unit collects the target to be snapshot, which is collected by the panoramic camera main control unit, the position of the target to be snapshot is obtained, the position of the detail camera is adjusted according to the position of the target to be snapshot, so that the target to be snapshot is at the central position of an image shot by the detail camera, the real-time relative motion state between the target to be snapshot and the detail camera is further detected, different tracking control strategies are selected to control the detail camera to track and snapshot the target to be snapshot based on the real-time relative motion state, the target to be snapshot is locked and tracked, and the detail snapshot effect is improved.
In some embodiments, the detail camera and the fill-in light device share a rotation axis, so that the vertical rotation angle of the detail camera and the rotation angle of the fill-in light device are the same. The light supplement device can be a light supplement lamp or a flash lamp.
In the present embodiment, a target capturing and tracking method for a vehicle-mounted camera is provided, and fig. 3 is a flowchart of the target capturing and tracking method for a vehicle-mounted camera according to the present embodiment, as shown in fig. 3, the flowchart includes the following steps:
and step S302, controlling the panoramic camera to identify the target to be snapped. And the system main control unit controls the panoramic camera to identify the target to be snapshotted. It should be noted that the panoramic camera may provide a plurality of intelligent rules, and according to preset target features, the panoramic camera recognizes that the target with the corresponding target features is the target to be captured. If the target characteristics are set as people or vehicles, after the panoramic camera identifies the people or the vehicles, the identified target object is preferably selected as a target to be snapshot, and the target to be snapshot is sent to the system main control unit for further snapshot and tracking.
And step S304, after the panoramic camera determines the target to be snapped, acquiring the position of the target to be snapped, and adjusting the position of the detail camera according to the position of the target to be snapped. And the system main control unit enters a detail tracking snapshot mode after the panoramic camera determines the target to be snapshot, and acquires the position of the target to be snapshot. The position of the target to be snapshotted can be sent to the system main control unit after the panoramic camera calculates the position coordinates of the target to be snapshotted according to the collected image of the target to be snapshotted. And the system main control unit adjusts the position of the detail camera according to the position class of the target to be captured, so that the detail camera faces the target to be captured, and the target to be captured is positioned in the center of the image shot by the detail camera.
In one embodiment, after the position of the target to be captured is acquired, the position of the detail camera and the zoom ratio of the detail camera are adjusted according to the position of the target to be captured, so that the target to be captured is located in the center of an image shot by the detail camera, and the adjusted zoom ratio is kept unchanged in the whole capturing and tracking process. Adjusting the magnification of the detail camera may be achieved by setting a magnification of a focal length change of a zoom lens of the detail camera.
And step S306, detecting the real-time relative motion state between the target to be captured and the detail camera. The system main control unit detects the real-time relative motion state between the target to be captured and the detail camera, and can determine the real-time relative motion state between the target to be captured and the detail camera through the change of pixel points of the target to be captured in two adjacent image frames collected by the detail camera.
And S308, selecting different tracking control strategies to control the detail cameras to track and snapshot the target to be snapshot based on the real-time relative motion state. And the system main control unit selects different tracking control strategies to control the detail cameras to perform tracking snapshot on the target to be snapshot based on the real-time relative motion state in the step S306. After the steps are processed, the position of the target to be snapshot is always in the center of the picture of the detail camera and the target snapshot is triggered and completed.
Through the steps, in a mode that the panoramic camera and the detail camera work cooperatively, the system main control unit acquires the target to be captured and acquired by the panoramic camera main control unit, acquires the position of the target to be captured, adjusts the position of the detail camera according to the position of the target to be captured, enables the target to be captured to be in the central position of an image shot by the detail camera, further detects the real-time relative motion state between the target to be captured and the detail camera, selects different tracking control strategies to control the detail camera to track and capture the target to be captured based on the real-time relative motion state, locks and tracks the target to be captured, and improves the detail capturing effect.
In this embodiment, a method for detecting a real-time relative motion state between an object to be captured and a detail camera is provided, and fig. 4 is a flowchart of the method for detecting a real-time relative motion state between an object to be captured and a detail camera in this embodiment, as shown in fig. 4, the flowchart includes the following steps:
s402, keeping the zooming rate of the detail camera unchanged; in the foregoing embodiment, after the position of the target to be captured is acquired, the position of the detail camera and the zoom ratio of the detail camera are adjusted according to the position of the target to be captured, so that the target to be captured is located in the center of the image captured by the detail camera. And keeping the adjusted zoom ratio unchanged, and judging the real-time relative motion state between the target to be captured and the detail camera in the subsequent step.
S404, when the output data of the gyroscope has small fluctuation, recording the pixel point size M1 of the picture occupied by the target to be snapped selected in the current frame image of the detail camera; the gyroscope is used for monitoring the motion condition of the vehicle, and when the output data of the gyroscope has small fluctuation, the current motion stability is indicated so as to reduce the influence of factors such as new jitter on the judgment of the subsequent target size.
S406, updating the pixel point size M2 of the picture occupied by the same target to be snapshot in the monitored image in real time according to the sampling time T;
s408, comparing the profile size change conditions of the front sampling moment and the rear sampling moment of the same target to be snapshotted, and judging whether the pixel point variation exceeds a given threshold value N, namely the relation between | M2-M1| and N; wherein, the N value can be an empirical value and is related to the parameter of the camera;
and S410, if the absolute value of M2-M1 absolute value is larger than N, judging that the real-time relative motion state of the selected target to be snapped and the detail camera is relative motion, and otherwise, judging that the real-time relative motion state of the selected target to be snapped and the detail camera is relative still. If the absolute value of M2-M1 absolute value is larger than N, the change of the outline size of the object to be snapped in the front and back two images is larger, and the relative motion of the object to be snapped and the detail camera is shown.
In some embodiments, when the real-time relative motion state between the target to be captured and the detail camera is relative motion, the detail camera is controlled to perform tracking capture on the target to be captured according to the following tracking control strategy, so as to ensure the capturing effect of the target:
calculating the position coordinate value of the target to be captured in the image frame of the detail camera, calculating the position deviation value of the target to be captured at the ith moment according to the position coordinate value of the target to be captured in the image frame of the detail camera acquired at the ith moment and the ith-1 moment, obtaining the tracking speed of the detail camera according to the position deviation value, and adjusting the movement speed of the detail camera according to the tracking speed.
In some embodiments, when the real-time relative motion state between the target to be captured and the detail camera is relative motion, the detail camera is controlled to perform tracking capture on the target to be captured according to the following tracking control strategy, so as to ensure the capturing effect of the target:
in the process of moving the target to be captured, firstly calculating a horizontal coordinate position value and a vertical coordinate position value of the target to be captured in two frames of images before and after the target to be captured by a three-dimensional positioning method, and then obtaining the current sampling time and the previous time to be capturedShooting a position deviation value of a target in front and back two frames of images; then respectively calculating to obtain the horizontal tracking speed V according to the following formulaxAnd a vertical tracking velocity Vy。
Vx＝Kp*eix+Ki*∑eik+Kd*(eik-e(i-1)x)
Vy＝Kp*eiy+Ki*∑eiy+Kd*(eiy-e(i-1)y)
Wherein,ixa horizontal position deviation value e of the target to be snapshotted at the ith momentiyA vertical position deviation value e of the target to be snapshotted at the ith moment(i-1)xThe horizontal position deviation value e of the target to be snapshotted at the i-1 th moment(i-1)yThe vertical position deviation value, K, of the target to be snapshotted at the i-1 th momentp、Ki、KdThe parameters are adjusted for speed.
The system main control unit tracks the speed V according to the levelxAnd a vertical tracking velocity VyControlling acceleration and deceleration of detail camera, generating speed from 0 to target speed V according to selected curve model, such as S curvexAnd VyTo adjust the detail camera position in real time so that the target can remain centered in the detail camera image without being lost.
In some embodiments, when the real-time relative motion state between the target to be captured and the detail camera is relatively static, the detail camera is controlled to perform tracking capture on the target to be captured according to the following tracking control strategy, so as to ensure the capturing effect of the target:
acquiring the motion speed of the detail camera and the angular speed of the gyroscope at the ith moment, calculating the target speed of the detail camera according to the motion speed of the detail camera and the angular speed of the gyroscope, and adjusting the motion speed of the detail camera according to the target speed.
In some embodiments, when the real-time relative motion state between the target to be captured and the detail camera is relatively static, the detail camera is controlled to perform tracking capture on the target to be captured according to the following tracking control strategy, so as to ensure the capturing effect of the target:
the influence of the fact that the object to be captured is not in the picture due to vehicle vibration and the like is eliminated by adopting a speed or position real-time reverse compensation mode. Firstly, acquiring angular velocity values V output by a gyroscope in real time in an X axis and a Y axisGxAnd VGyAnd the current horizontal velocity V of the detail camera at the same timeCxAnd a vertical velocity VCy(ii) a Then controlling the horizontal direction movement speed of the detail camera according to the X-axis angular velocity value of the gyroscope, controlling the vertical direction movement of the detail camera according to the Y-axis angular velocity value of the gyroscope, and updating the current horizontal target velocity value V of the detail camera in real time according to the following formulaTxAnd a vertical target velocity value VTy。
VTx＝VCx-VGx
VTy＝VCy-VGy
The strategy directly calculates the tracking speed of the detail camera by means of the existing gyroscope speed information for anti-shake, and does not need to calculate the speed control method of the detail camera in real time according to the condition that the real-time relative motion state between the target to be captured and the detail camera is the relative motion state in the embodiment; the calculation amount can be saved, and the method is convenient and simple.
Fig. 5 is a flowchart of another target capturing and tracking method for a vehicle-mounted camera according to this embodiment, and as shown in fig. 5, the flowchart includes the following steps:
s502, controlling the panoramic camera to identify a target to be captured and identify obstacles or curves on a driving path;
s504, judging whether an obstacle or a curve exists on a driving path; judging whether an obstacle exists on a vehicle driving path or a large-amplitude turn exists according to images acquired by the panoramic camera and the detail camera;
s506, if an obstacle or a curve exists, predicting the motion estimation of the target to be snapshot, and adopting a tracking control strategy of advance compensation; if no obstacle or bend exists, further judging the relative motion state of the target to be snapshotted and the detail camera;
s508, when the real-time relative motion state between the target to be snapshotted and the detail camera is relative motion, a tracking control strategy during the relative motion is adopted to control the detail camera to perform tracking snapshotting on the target to be snapshotted; the specific tracking control strategy has been described in detail in the above embodiments, and will not be described herein.
S510, when the real-time relative motion state between the target to be snapshotted and the detail camera is relatively static, a tracking control strategy in the relative static state is adopted to control the detail camera to perform tracking snapshotting on the target to be snapshotted; the specific tracking control strategy has been described in detail in the above embodiments, and will not be described herein.
In some embodiments, curve and obstacle recognition is introduced when aiming at a curve or avoiding an obstacle scene, and the following tracking snapshot strategy is adopted:
the instantaneous speed and acceleration change generated in the scene is increased, and the corresponding position deviation e of the target to be captured in the front and back two frames of images in the picturekAnd the instantaneous output speed of the gyroscope is so high that the camera tracking speed calculated from the preceding details is too high and may exceed the maximum speed V in the horizontal or vertical direction allowed by the devicemaxAnd the target to be captured is lost due to tracking lag caused by too slow whole acceleration process due to the fact that the target cannot be accelerated to the required target speed instantaneously due to the limitation of the maximum acceleration of the detail camera. Therefore, target motion track prediction is introduced, compensation control is performed in advance, the track and the motion direction of a moving target are recognized in advance, and the cradle head is controlled to move in the target motion direction in advance. The specific process is as follows:
firstly, the obstacles on the advancing road of the vehicle are identified through images collected by a panoramic camera and a detail camera, and the current distance S between the obstacles and the vehicle is measured by means of a binocular distance measuring principle.
And calculating the time t of reaching the obstacle according to a formula S-V t, wherein the time t is the time which can be used for compensating the tracking speed of the detail camera before reaching the obstacle or turning, and V is the speed of the vehicle.
And (5) calculating and processing the motion parameters of the detail camera under the advance compensation strategy. Considering that the acceleration can not change suddenly, in order to ensure that the acceleration can be accelerated to a larger compensation speed quickly to complete the compensation of the speed of the gyroscope under the condition of bypassing the obstacle and the like, the acceleration of the pan-tilt head of the detail camera is controlled to just reach the maximum acceleration A allowed by the detail camera when the vehicle reaches the obstacle or meets a large-scale turnmax(ii) a Calculating a compensated acceleration and a compensated velocity of the detail camera according to the following formulas:
jerk＝Amax/
ak＝ak-1+jerk*T
vk＝vk-1+ak*T
k＝t/T
Vk-1＝Kp*ek-1+Ki*∑ek-1+Kd*(ek-1-e(k-2))
wherein A ismaxMaximum acceleration allowed for the detail camera, t is the time for the vehicle to reach the obstacle, jerk is an intermediate variable, akFor compensating acceleration, v, of the detail camerakFor the compensation speed of the detail camera, T is the discrete sampling period, Kp、Ko、KdFor adjusting the parameters, ekAnd the position deviation value of the target to be snapshotted at the kth moment is obtained.
The parameters are recorded and stored in real time, and the detail camera is controlled to move according to the motion parameters, so that the compensation effect can be achieved.
In the embodiment, for complex scenes such as large-amplitude turning or needing to avoid obstacles, an advance motion compensation strategy is adopted for tracking compensation, and the tracking snapshot effect and the scene applicability in such scenes are improved.
In some embodiments, for a low-illumination scene at night, in order to clearly capture an object to be captured, a tracking capture strategy is adopted in which the following detail cameras and light supplement devices are cooperatively processed:
firstly, the illumination condition of the current scene is identified according to devices such as a photosensitive device, and the panoramic phase is obtained in the low-illumination scene at nightThe objects in the 360 scene seen by the machine are not very clear. At the moment, the panoramic camera intelligent processing module can only recognize the approximate outline information of each target in the panoramic camera firstly, obtain the coordinate position of each target outline in the panoramic camera, and then convert the coordinate position according to a coordinate calibration algorithm to obtain the horizontal position coordinate p of each target outline in the detail camera1And a vertical position coordinate p2Controlling fine camera level pinpointing to target position (p)1+θ， p2) I.e. to control the movement of the detail camera to the target position. Wherein, the angle theta is an included angle between the light supplement device and the detail camera. After the detail camera moves to the target position, the light supplementing device aims at the target recognized by the panoramic camera at the moment, the light supplementing device is started, so that the panoramic camera can capture clear targets, the target to be snapshotted is accurately and preferably interested in from a plurality of targets to be snapshotted and stored after the light supplementing operation of each target is completed in sequence, the panoramic camera is triggered to complete the snapshotting after the light supplementing light is aligned to the optimal target, the detail camera is immediately controlled to move in the reverse direction by the current coordinate position to theta degrees, the detail camera can be aligned to the optimal target to be snapshotted, and then the optimal target to be snapshotted is tracked and snapshotted under low illumination according to the tracking snapshotting step.
In the embodiment, for a complex scene with low illumination, a detail camera and a light supplement device are adopted to cooperatively control a strategy for tracking compensation, so that the tracking snapshot effect and the scene applicability in the scene are improved.
In some embodiments, in the process of tracking a preferred target to be captured in real time by the detail camera, the lens in the movement of the detail camera is controlled to move in parallel to perform optical anti-shake so as to ensure that the target can be always kept in the center of a picture and the image quality is stable and does not shake in the tracking capture process. The lens in the detail camera is provided with an optical anti-shake element. When the system main control unit detects that the gyroscope data changes, the compensation distance of the optical anti-shake piece in the lens is calculated according to the variable quantity of the gyroscope data and the current focal length of the detail camera, so that the anti-shake lens is driven, and the final imaging is stable.
When the detail camera shake is detected, calculating the moving distance of the anti-shake lens of the detail camera according to the following formula;
wherein f is the focal length of the detail camera, D is the moving distance of the anti-shake device, and alpha is the shake angle of the detail camera; SR is image stabilization sensitivity. f is the focal length of the camera equipment when shaking occurs, the image stabilization sensitivity SR is the distance that the intersection point of the optical axis of the OIS lens group and the focal plane moves on the focal plane every time the OIS lens group moves by 1mm, and when the lens is fixed, SR is a constant. The value of f/SR is therefore a set of preset data relating to the focal length.
Further analyzing, α is a shake angle of shake when the image pickup apparatus, i.e., the detail camera shakes, i.e., shake data obtained by the gyroscope. In most cases less than 0.2 deg., according to the formula
It can be inferred that tan α ═ α, and therefore
And controlling the anti-shake lens to move for the distance D according to the moving distance D, wherein the direction is opposite to the shaking direction, and outputting a stable image.
In the embodiment, in the process of tracking the optimal target to be snapshot by the detail camera in real time, the anti-shake is performed by controlling the lens in the movement of the detail camera in parallel, so that the target to be snapshot can be always ensured to be in the center of the picture and the image quality is stable and not to shake in the tracking and snapshot process.
It should be noted that the steps illustrated in the above-described flow diagrams or in the flow diagrams of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that, although a logical order is illustrated in the flow diagrams, in some cases, the steps illustrated or described may be performed in an order different than here.
In this embodiment, a target capturing and tracking apparatus for a vehicle-mounted camera is further provided, where the apparatus is used to implement the foregoing embodiments and preferred embodiments, and the description of the apparatus is omitted, and the apparatus includes:
the identification module is used for controlling the panoramic camera to identify a target to be captured;
the position adjusting module is used for acquiring the position of the target to be snapshotted after the panoramic camera determines the target to be snapshotted, and adjusting the position of the detail camera according to the position of the target to be snapshotted;
the detection module is used for detecting the real-time relative motion state between the target to be snapshotted and the detail camera;
and the tracking snapshot module is used for selecting different tracking control strategies to control the detail cameras to perform tracking snapshot on the target to be snapshot based on the real-time relative motion state.
The above modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the modules may be located in the same processor; or the modules can be respectively positioned in different processors in any combination.
There is also provided in this embodiment an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
It should be noted that, for specific examples in this embodiment, reference may be made to the examples described in the foregoing embodiments and optional implementations, and details are not described again in this embodiment.
In addition, in combination with the target capturing and tracking method for the vehicle-mounted camera provided in the above embodiment, a storage medium may also be provided to implement in this embodiment. The storage medium having stored thereon a computer program; the computer program, when executed by a processor, implements any of the above embodiments of a target capture and tracking method for a vehicle camera.
It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to be limiting. All other embodiments, which can be derived by a person skilled in the art from the examples provided herein without any inventive step, shall fall within the scope of protection of the present application.
It is obvious that the drawings are only examples or embodiments of the present application, and it is obvious to those skilled in the art that the present application can be applied to other similar cases according to the drawings without creative efforts. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
The term "embodiment" is used herein to mean that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly or implicitly understood by one of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the patent protection. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (15)
1. A target capture and tracking method for a vehicle-mounted camera, the vehicle-mounted camera including a panoramic camera and a detail camera, the method comprising,
controlling the panoramic camera to identify a target to be snapshotted;
after the panoramic camera determines the target to be snapped, acquiring the position of the target to be snapped, and adjusting the position of the detail camera according to the position of the target to be snapped;
detecting a real-time relative motion state between the target to be snapshotted and the detail camera;
and selecting different tracking control strategies to control the detail camera to perform tracking snapshot on the target to be snapshot based on the real-time relative motion state.
2. The method according to claim 1, wherein the detecting a real-time relative motion state between the object to be captured and the detail camera comprises,
and determining the real-time relative motion state between the target to be captured and the detail camera according to the change of pixel points of the target to be captured in two adjacent image frames acquired by the detail camera.
3. The method according to claim 2, wherein the determining the real-time relative motion state between the object to be captured and the detail camera according to the change of pixel points of the object to be captured in two adjacent image frames collected by the detail camera comprises,
when the change of pixel points of a target to be captured in two adjacent image frames acquired by the detail camera is larger than a preset first threshold value, determining that the real-time relative motion state is relative motion;
and when the change of pixel points of the target to be captured in two adjacent image frames acquired by the detail camera is smaller than or equal to the first threshold value, determining that the real-time relative motion state is relatively static.
4. The method according to claim 3, wherein when the real-time relative motion state is relative motion, selecting different tracking control strategies to control the detail camera to perform tracking snapshot on the target to be snapshot based on the real-time relative motion state comprises,
calculating the position coordinate value of the target to be captured in the image frame of the detail camera, calculating the position deviation value of the target to be captured at the ith moment according to the position coordinate value of the target to be captured in the image frame of the detail camera acquired at the ith moment and the ith-1 moment, obtaining the tracking speed of the detail camera according to the position deviation value, and adjusting the movement speed of the detail camera according to the tracking speed.
5. The method of claim 4, wherein the deriving the tracking speed of the detail camera from the location deviation value comprises,
the tracking speed of the detail camera includes a horizontal tracking speed VxAnd a vertical tracking velocity VySaid horizontal tracking velocity VxAnd a vertical tracking velocity VyRespectively calculating according to the following formulas;
Vx＝Kp*eix+Ki*∑eix+Kd*(eix-e(i-1)x)
Vy＝Kp*eiy+Ki*∑eiy+Kd*(eiy-e(i-1)y)
wherein e isixA horizontal position deviation value e of the target to be snapshotted at the ith momentiyA vertical position deviation value e of the target to be snapshotted at the ith moment(i-1)xThe horizontal position deviation value e of the target to be snapshotted at the i-1 th moment(i-1)yThe vertical position deviation value of the target to be snapshotted at the i-1 th moment, i is an integer larger than 1, Kp、Ki、KdThe parameters are adjusted for speed.
6. The method according to claim 3, wherein the vehicle-mounted camera further comprises a gyroscope, when the real-time relative motion state is relatively static, the selecting different tracking control strategies to control the detail camera to perform tracking snapshot on the target to be snapshot based on the real-time relative motion state comprises,
acquiring the motion speed of the detail camera and the angular speed of the gyroscope at the ith moment, calculating the target speed of the detail camera according to the motion speed of the detail camera and the angular speed of the gyroscope, and adjusting the motion speed of the detail camera according to the target speed.
7. The method according to claim 1, wherein after the adjusting the position of the detail camera according to the position of the object to be captured, the method further comprises,
detecting whether a curve or an obstacle exists in a moving path of a vehicle mounted with the vehicle-mounted camera;
if the vehicle motion path exists, the motion path of the vehicle is predicted, and motion compensation is performed on the detail camera according to the prediction result.
8. The method according to claim 7, wherein when an obstacle exists in a moving path of the vehicle, the predicting the moving path of the vehicle and the motion compensating the detail camera according to the prediction result comprise identifying the obstacle in the moving path of the vehicle, detecting a distance between the vehicle and the obstacle, and calculating a time when the vehicle reaches the obstacle according to a moving speed of the vehicle; and calculating the compensation acceleration and the compensation speed of the detail camera according to the time of the vehicle reaching the obstacle and the position deviation value of the target to be captured, and adjusting the motion parameters of the detail camera according to the compensation acceleration and the compensation speed.
9. The method according to claim 7, wherein calculating the compensated acceleration and compensated speed of the detail camera based on the time when the vehicle reaches the obstacle and the positional deviation value of the target to be captured includes,
calculating a compensated acceleration and a compensated speed of the detail camera according to the following formulas;
jerk＝Amax/t
ak＝ak-1+jerk*T
vk＝vk-1+ak*T
k＝t/T
Vk-1＝Kp*ek-1+Ki*∑ek-1+Kd*(ek-1-e(k-2))
wherein Amax is the maximum acceleration allowed by the detail camera, t is the time for the vehicle to reach the obstacle, jerk is an intermediate variable, akFor compensating acceleration, v, of the detail camerakFor the compensation speed of the detail camera, T is the discrete sampling period, Kp、Ki、KdFor adjusting the parameters, ekAnd k is the position deviation value of the target to be snapshotted at the kth moment, and k is an integer larger than 2.
10. The method of claim 1, further comprising, after the panoramic camera determines the target to be snapped,
identifying a target contour of the target to be captured in the image acquired by the panoramic camera to obtain a first position coordinate of the target contour in the image acquired by the panoramic camera;
obtaining a second position coordinate of the target contour in an image collected by the detail camera according to a preset corresponding relation of the position coordinates of the panoramic camera and the detail camera;
obtaining a target position coordinate according to the second position coordinate and a first included angle, wherein the first included angle is an included angle between the light supplement lamp and the detail camera;
and controlling the detail camera to move to the target position coordinate.
11. The method of claim 1, further comprising,
when the detail camera is detected to shake, calculating the moving distance of an anti-shake device of the detail camera according to the following formula;
wherein f is the focal length of the detail camera, D is the moving distance of the anti-shake device, alpha is the shake angle of the detail camera, and SR is the image stabilization sensitivity;
and controlling the anti-shake device to move reversely according to the moving distance of the anti-shake device.
12. A target capture and tracking apparatus for a vehicle-mounted camera, the apparatus comprising:
the identification module is used for controlling the panoramic camera to identify a target to be captured;
the position adjusting module is used for acquiring the position of the target to be snapshotted after the panoramic camera determines the target to be snapshotted, and adjusting the position of the detail camera according to the position of the target to be snapshotted;
the detection module is used for detecting the real-time relative motion state between the target to be snapshotted and the detail camera;
and the tracking snapshot module is used for selecting different tracking control strategies to control the detail camera to perform tracking snapshot on the target to be snapshot based on the real-time relative motion state.
13. A target capture and tracking system for a vehicle-mounted camera, the system comprising,
the target capturing and tracking system comprises a mounting seat, a holder supported on the mounting seat, a panoramic camera and a detail camera which are arranged on the holder, and a control unit arranged in the holder, wherein the control unit is used for executing the target capturing and tracking method for the vehicle-mounted camera according to any one of claims 1 to 11.
14. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to perform the target capturing and tracking method for a vehicle-mounted camera according to any one of claims 1 to 11.
15. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for object snapping and tracking for on-board cameras of any of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111191031.6A CN114071013B (en) | 2021-10-13 | 2021-10-13 | Target snapshot and tracking method and device for vehicle-mounted camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111191031.6A CN114071013B (en) | 2021-10-13 | 2021-10-13 | Target snapshot and tracking method and device for vehicle-mounted camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114071013A true CN114071013A (en) | 2022-02-18 |
| CN114071013B CN114071013B (en) | 2023-06-20 |
Family
ID=80234659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111191031.6A Active CN114071013B (en) | 2021-10-13 | 2021-10-13 | Target snapshot and tracking method and device for vehicle-mounted camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114071013B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006004188A (en) * | 2004-06-17 | 2006-01-05 | Daihatsu Motor Co Ltd | Obstacle recognition method and obstacle recognition device |
| US20090281756A1 (en) * | 2008-05-08 | 2009-11-12 | L-3 Communications Corporation | Accelerometer and Method for Error Compensation |
| CN101598559A (en) * | 2008-06-05 | 2009-12-09 | 广东电子工业研究院有限公司 | The location compensation method of Vehicular continuous navigation device and the optimized Algorithm of locator data |
| CN106705992A (en) * | 2015-11-12 | 2017-05-24 | 北京自动化控制设备研究所 | Biaxial optical fiber inertial navigation system rapid self-calibration self-alignment method |
| CN206650789U (en) * | 2017-04-24 | 2017-11-17 | 福州大学至诚学院 | A kind of automatic energy saving system based on video monitor |
| CN107878453A (en) * | 2017-11-07 | 2018-04-06 | 长春工业大学 | A kind of automobile emergency collision avoidance integral type control method for hiding dynamic barrier |
| CN108881703A (en) * | 2017-05-09 | 2018-11-23 | 杭州海康威视数字技术股份有限公司 | Stabilization control method and device |
| CN110293967A (en) * | 2019-05-21 | 2019-10-01 | 重庆长安汽车股份有限公司 | A kind of automobile low speed active safety executes control method and control system |
| CN111372037A (en) * | 2018-12-25 | 2020-07-03 | 杭州海康威视数字技术股份有限公司 | Target snapshot system and method |
| US20200228720A1 (en) * | 2017-06-16 | 2020-07-16 | Hangzhou Hikvision Digital Technology Co., Ltd. | Target Object Capturing Method and Device, and Video Monitoring Device |
| CN112644488A (en) * | 2020-12-30 | 2021-04-13 | 清华大学苏州汽车研究院（吴江） | Adaptive cruise system |
| CN112683269A (en) * | 2020-12-07 | 2021-04-20 | 电子科技大学 | MARG attitude calculation method with motion acceleration compensation |
-
2021
- 2021-10-13 CN CN202111191031.6A patent/CN114071013B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006004188A (en) * | 2004-06-17 | 2006-01-05 | Daihatsu Motor Co Ltd | Obstacle recognition method and obstacle recognition device |
| US20090281756A1 (en) * | 2008-05-08 | 2009-11-12 | L-3 Communications Corporation | Accelerometer and Method for Error Compensation |
| CN101598559A (en) * | 2008-06-05 | 2009-12-09 | 广东电子工业研究院有限公司 | The location compensation method of Vehicular continuous navigation device and the optimized Algorithm of locator data |
| CN106705992A (en) * | 2015-11-12 | 2017-05-24 | 北京自动化控制设备研究所 | Biaxial optical fiber inertial navigation system rapid self-calibration self-alignment method |
| CN206650789U (en) * | 2017-04-24 | 2017-11-17 | 福州大学至诚学院 | A kind of automatic energy saving system based on video monitor |
| CN108881703A (en) * | 2017-05-09 | 2018-11-23 | 杭州海康威视数字技术股份有限公司 | Stabilization control method and device |
| US20200228720A1 (en) * | 2017-06-16 | 2020-07-16 | Hangzhou Hikvision Digital Technology Co., Ltd. | Target Object Capturing Method and Device, and Video Monitoring Device |
| CN107878453A (en) * | 2017-11-07 | 2018-04-06 | 长春工业大学 | A kind of automobile emergency collision avoidance integral type control method for hiding dynamic barrier |
| CN111372037A (en) * | 2018-12-25 | 2020-07-03 | 杭州海康威视数字技术股份有限公司 | Target snapshot system and method |
| CN110293967A (en) * | 2019-05-21 | 2019-10-01 | 重庆长安汽车股份有限公司 | A kind of automobile low speed active safety executes control method and control system |
| CN112683269A (en) * | 2020-12-07 | 2021-04-20 | 电子科技大学 | MARG attitude calculation method with motion acceleration compensation |
| CN112644488A (en) * | 2020-12-30 | 2021-04-13 | 清华大学苏州汽车研究院（吴江） | Adaptive cruise system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114071013B (en) | 2023-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111526285B (en) | Image anti-shake method, electronic equipment and computer-readable storage medium | |
| CN106027887B (en) | For the method, apparatus and electronic equipment of the rifle ball linkage control of rotating mirror holder | |
| JP6032034B2 (en) | Object detection device | |
| WO2020029596A1 (en) | Lens control method and device and terminal | |
| WO2020117285A1 (en) | A multicamera system for autonamous driving vehicles | |
| JP2017072986A (en) | Autonomous flying device, control method and program of autonomous flying device | |
| CN114281100B (en) | Unmanned aerial vehicle inspection system and method without hovering | |
| CN107615744A (en) | A kind of image taking determination method for parameter and camera device | |
| CN108933896A (en) | The method and system of the steady picture of panoramic video based on Inertial Measurement Unit | |
| US7936385B2 (en) | Image pickup apparatus and imaging method for automatic monitoring of an image | |
| EP3275173B1 (en) | Image capture system with motion compensation | |
| TW201929210A (en) | Semiconductor device, imaging system, and program | |
| CN110609576B (en) | Cloud deck control method, device and system, control equipment and storage medium | |
| JP2956056B2 (en) | Tracking control method and apparatus, and shake correction method and apparatus | |
| JP3615867B2 (en) | Automatic camera system | |
| CN114071013A (en) | Target capturing and tracking method and device for vehicle-mounted camera | |
| JP7003972B2 (en) | Distance estimation device, distance estimation method and computer program for distance estimation | |
| CN111684784B (en) | Image processing method and device | |
| US20230341079A1 (en) | Control method based on image capturing apparatus, control method and apparatus for gimbal | |
| CN113645397A (en) | Tracking method, device and system for moving target object | |
| JP2001116527A (en) | Method and device for detecting solid body | |
| JPH09322052A (en) | Automatic photographing camera system | |
| JP2021129268A (en) | Imaging apparatus and method for controlling the same | |
| CN113170057B (en) | Imaging unit control device | |
| JP2017038243A (en) | Imaging apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |