CN109996377B

CN109996377B - Street lamp control method and device and electronic equipment

Info

Publication number: CN109996377B
Application number: CN201711487738.5A
Authority: CN
Inventors: 苏军
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2017-12-29
Filing date: 2017-12-29
Publication date: 2021-08-13
Anticipated expiration: 2037-12-29
Also published as: CN109996377A

Abstract

The embodiment of the invention provides a street lamp control method, a street lamp control device and electronic equipment, wherein the method comprises the following steps: acquiring a monitoring scene image; identifying a target in the monitoring scene image, and obtaining the attribute of the identified target, wherein the attribute of the target comprises: the position of the target in the monitored scene; determining a target street lamp for illuminating the identified target according to the position of the target in the monitored scene; determining the brightness of each target street lamp according to the attributes of the targets and the position of each target street lamp in the monitoring scene; and controlling each target street lamp to illuminate at the determined brightness. According to the technical scheme provided by the embodiment of the invention, the brightness of each target street lamp is determined according to the position of the target in the monitoring scene and the position of each target street lamp in the monitoring scene, and then each target street lamp is controlled to illuminate at the determined brightness, so that the target street lamp can illuminate for the target, and meanwhile, the waste of electric energy can be effectively avoided.

Description

Street lamp control method and device and electronic equipment

Technical Field

The invention relates to the technical field of street lamp control, in particular to a street lamp control method, a street lamp control device and electronic equipment.

Background

The intelligent street lamp is called as an intelligent street lamp, or an intelligent street lamp and intelligent illumination. Compared with the traditional street lamp, the street lamp has the advantages of realizing centralized management and control of the street lamp, operation and maintenance informatization, illumination intellectualization and the like.

The intelligent street lamp control system mainly controls the brightness of the street lamp through the following steps: collecting an image; comparing the acquired image with a pre-stored background model, and identifying a target in the foreground area of the image, wherein the identified target can be a person, a vehicle, an animal and the like; and acquiring the position of the identified target, and then sending a control signal to the target street lamp, wherein the target street lamp is a street lamp with the distance between the position and the position of the target within a preset distance range, so that each target street lamp is in a normal working state, namely the target street lamp works according to rated power, thereby illuminating the target.

According to the above description, the intelligent street lamp control system enables the target street lamps to be in the normal working state as long as the target is detected in the image. However, in practical applications, the way of controlling the street lamps of the intelligent street lamp control system causes waste of electric energy. For example, after the intelligent street lamp control system collects the images, 2 target street lamps are identified in the images, the target street lamps are close to one target street lamp and far from the other target street lamp, obviously, the target street lamp close to the target street lamp is needed to illuminate the target street lamp, and if the two target street lamps are controlled to be in a normal working state, the waste of electric energy can be caused.

Disclosure of Invention

The embodiment of the invention aims to provide a street lamp control method, a street lamp control device and electronic equipment, so that the waste of electric energy can be effectively avoided while the target street lamp can be ensured to illuminate for a target. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present invention provides a street lamp control method, where the method includes:

acquiring a monitoring scene image; identifying a target in the monitoring scene image, and obtaining the attribute of the identified target, wherein the attribute of the target comprises: the position of the target in the monitored scene;

determining a target street lamp for illuminating the identified target according to the position of the target in the monitored scene;

determining the brightness of each target street lamp according to the attributes of the targets and the position of each target street lamp in the monitoring scene;

and controlling each target street lamp to illuminate at the determined brightness.

Optionally, the method further includes:

and when the monitoring scene image is identified to have no target, controlling the brightness of each street lamp in the monitoring scene to be preset brightness.

Optionally, the determining the brightness of each target street lamp according to the attribute of the target and the position of each target street lamp in the monitoring scene includes:

calculating the brightness adjusting factor of each target street lamp according to the following formula:

wherein P represents a brightness adjustment factor, i is an identification number of an identified target, min is a minimum function, x_iAnd y_iThe position coordinates of the target with the identification number i in the monitoring scene are obtained; x and Y are position coordinates of a target street lamp;

and determining the brightness of each target street lamp according to the preset corresponding relation between the brightness adjustment factor and the brightness adjustment factor of each target street lamp.

Optionally, the attributes of the target further include: the category of the target and the speed of the target;

the determining the brightness of each target street lamp according to the attributes of the targets and the position of each target street lamp in the monitoring scene comprises the following steps:

and determining the brightness of each target street lamp according to the position of the target in the monitoring scene, the position of each target street lamp in the monitoring scene and one or more other attributes of the target except the position of the target in the monitoring scene.

Optionally, the determining the brightness of each target street lamp according to the position of the target in the monitoring scene, the position of each target street lamp in the monitoring scene, and one or more other attributes of the target except the position of the target in the monitoring scene includes:

wherein, P represents brightness adjusting factor, i is an identification number of a recognized target, attr (i) is a weighting coefficient corresponding to the attribute of the target with the identification number of i, and r_iCoefficient adjustment factors corresponding to the target with the identification number i, and the min function is a minimum function, x_iAnd y_iThe position coordinates of the target with the identification number i in the monitoring scene are obtained; x and Y areA position coordinate of a target street lamp;

Optionally, the obtaining attributes of the identified target includes:

extracting features of the identified target based on a first deep learning network;

according to the characteristics of the identified target, the attributes of the identified target are determined based on the second deep learning network.

Optionally, before the obtaining the attribute of the identified target, the method further includes:

selecting a target with a confidence coefficient greater than or equal to a preset confidence coefficient from the identified targets;

correspondingly, the obtaining of the attribute of the identified target includes:

obtaining attributes of the selected target, wherein the attributes of the selected target include: the position of the target in the monitored scene;

the determining a target street lamp for illuminating the identified target according to the position of the target in the monitored scene includes:

and determining a target street lamp for illuminating the selected target according to the position of the target in the monitored scene.

Optionally, the acquiring the monitoring scene image includes:

and acquiring a monitoring scene image by using a low-illumination camera.

In a second aspect, an embodiment of the present invention further provides a street lamp control device, where the street lamp control device includes:

the image acquisition module is used for acquiring a monitoring scene image;

a target identification module, configured to identify a target in the monitored scene image, and obtain an attribute of the identified target, where the attribute of the target includes: the position of the target in the monitored scene;

the street lamp determining module is used for determining a target street lamp for illuminating the identified target according to the position of the target in the monitoring scene;

the brightness determining module is used for determining the brightness of each target street lamp according to the attributes of the targets and the position of each target street lamp in the monitoring scene;

and the brightness control module is used for controlling each target street lamp to illuminate at the determined brightness.

Optionally, the brightness determining module is specifically configured to:

and if the target does not exist in the monitored scene image, determining the brightness of each street lamp in the monitored scene as the preset brightness.

Optionally, the brightness determining module is specifically configured to:

the brightness determination module includes:

the first brightness determining unit is used for determining the brightness of each target street lamp according to the position of the target in the monitoring scene, the position of each target street lamp in the monitoring scene and one or more other attributes of the target except the position of the target in the monitoring scene.

Optionally, the first brightness determining unit is specifically configured to:

wherein, P represents brightness adjusting factor, i is an identification number of a recognized target, attr (i) is a weighting coefficient corresponding to the attribute of the target with the identification number of i, and r_iCoefficient adjustment factors corresponding to the target with the identification number i, and the min function is a minimum function, x_iAnd y_iThe position coordinates of the target with the identification number i in the monitoring scene are obtained; x and Y are position coordinates of a target street lamp;

Optionally, the target identification module is specifically configured to:

and determining the identified target attribute based on the second deep learning network according to the characteristics of the identified target.

Optionally, the apparatus further comprises:

the target selection module is used for selecting targets with confidence degrees larger than or equal to a preset confidence degree from the targets identified by the target identification module;

correspondingly, the target identification module is specifically configured to:

obtaining the attribute of the target selected by the target selection module, wherein the attribute of the selected target comprises: the position of the target in the monitored scene;

the street lamp determination module is specifically configured to:

and determining a target street lamp for illuminating the selected target according to the position of the target in the monitoring scene.

Optionally, the image obtaining module is specifically configured to:

and acquiring a monitoring scene image by using a low-illumination camera.

In a third aspect, an embodiment of the present invention further provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete mutual communication through the communication bus;

a memory for storing a computer program;

and the processor is used for realizing the street lamp control method of the first aspect when executing the program stored in the memory.

In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the street lamp control method according to the first aspect is implemented.

Therefore, in the technical scheme provided by the embodiment of the invention, when the target appears in the monitoring scene, the target street lamp capable of illuminating the target is determined according to the position of the target in the monitoring scene; and determining the brightness of each target street lamp according to the position of the target in the monitoring scene and the position of each target street lamp in the monitoring scene, and further controlling each target street lamp to illuminate at the determined brightness. Instead of only detecting that a target appears in the monitored scene image, each target street lamp with the distance to the target within the preset distance range works according to the rated power. Therefore, through the technical scheme provided by the embodiment of the invention, the target street lamp can illuminate the target, and meanwhile, the waste of electric energy can be effectively avoided.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a street lamp control method according to an embodiment of the present invention;

fig. 2 is a flowchart of another street lamp control method according to an embodiment of the present invention;

fig. 3 is a flowchart of another street lamp control method according to an embodiment of the present invention;

fig. 4 is a flowchart of another street lamp control method according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of a street lamp control device according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of a street lamp control device according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of a street lamp control device according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In order to solve the technical problems described in the background art, embodiments of the present invention provide a street lamp control method, device, electronic device, and storage medium, so as to achieve the purpose of saving energy while ensuring that a good lighting effect is provided for a target.

In a first aspect, a street lamp control method provided by an embodiment of the present invention is described below.

The street lamp control method provided by the embodiment of the invention can be applied to night monitoring scenes. The execution main body of the street lamp control method can be a background control server; the street lamp control method can also be a camera with the function of executing the street lamp control method, for example, the street lamp control method provided by the embodiment of the invention can be directly executed after the camera collects the monitoring scene image, thereby reducing the load of the background control server. Of course, it is reasonable that the execution main body of the street lamp control method may also be any other electronic device capable of executing the street lamp control method provided by the embodiment of the present invention. The embodiment of the invention does not specifically limit the execution main body of the street lamp control method.

As shown in fig. 1, a street lamp control method provided in the embodiment of the present invention includes the following steps:

s101, acquiring a monitoring scene image;

at night, in order to improve the energy-saving efficiency of the street lamp, if no target appears near the street lamp, the street lamp is in a sleep state; when a target appears near the street lamp, the street lamp is switched from the sleep state to the working state. Therefore, in order to improve the energy saving efficiency of the street lamp and ensure that the street lamp can illuminate for the target in time when the target appears near the street lamp, the image of the monitored scene needs to be acquired so as to identify whether the target exists in the image of the monitored scene in the subsequent steps. The above object can be understood as: it is reasonable to have a person or object present in the monitored scene, wherein the object may be a bicycle, a car, an animal, etc.

The manner of obtaining the monitored scene image may be: a camera is installed in a monitored scene, and the camera can shoot images of the monitored scene in real time or at preset time intervals. It can be understood that the position of the camera in the monitored scene and the number of cameras in the monitored scene may be determined according to actual conditions, and the position of the camera in the monitored scene and the number of cameras in the monitored scene are not specifically limited in the embodiment of the present invention.

It should be noted that, a common camera can only shoot a clear monitoring scene image when the light intensity of the monitoring scene reaches a certain light intensity; that is to say, if the ordinary camera is required to capture a clear monitoring scene image, the street lamp cannot be in a deep sleep state, otherwise, the monitoring scene image captured by the ordinary camera is not clear, and it is inconvenient to identify whether a target exists in the monitoring scene image in subsequent steps. Therefore, if a common camera is used for collecting images of a monitored scene, the electric energy is wasted because the street lamp cannot be in a deep sleep state.

Therefore, in order to avoid the waste of electric energy caused by the fact that the street lamp cannot be in the deep sleep state, in the embodiment of the invention, the monitoring scene image can be collected by using the low-illumination camera, wherein the low-illumination camera can still shoot a clear monitoring scene image when the street lamp is in the deep sleep state.

S102, identifying a target in the monitored scene image, and obtaining the attribute of the identified target, wherein the attribute of the target comprises: the position of the target in the monitored scene;

after the monitored scene image is acquired, in order to determine whether a target appears in the monitored scene, whether the target exists in the monitored scene image needs to be identified.

For example, the collected monitoring scene image may be compared with a pre-stored background image of the monitoring scene to obtain a foreground region of the monitoring scene image, and then the target of the image foreground region may be identified. Or, the trained target recognition model may be used to recognize the target in the monitored scene image, and the training process of the target recognition model may be: collecting a large number of sample images, calibrating the target in the collected sample images, inputting the calibrated sample images into the deep learning network, and repeatedly training the deep learning network to finally obtain the target recognition model. The embodiment of the invention does not specifically limit how to identify the target in the monitored scene image.

It is understood that the number of the targets in the monitored scene image may be one or more. For example, if there is only one person in the monitored scene, the number of objects in the monitored scene image is one; if there are multiple people in the monitored scene, the number of the targets in the monitored scene image is multiple.

After the target in the monitored scene image is identified, the attribute of the identified target needs to be obtained, wherein the attribute of the target may be the position of the target in the monitored scene, the category of the target, the speed of the target, and the like.

The method for obtaining the attribute of the target in the monitoring scene image may be as follows: features of the targets in the monitored scene image are extracted based on the first deep learning network, and attributes of the targets in the monitored scene image are determined by the second deep learning network according to the extracted features. The first deep learning network may be referred to as a feature recognition model, and a training process of the feature recognition model may be: collecting a large number of target samples, calibrating the characteristics of a target in the collected target samples, inputting the calibrated target samples into a deep learning network, and repeatedly training the deep learning network to finally obtain a characteristic recognition model; the second deep learning network may be referred to as an attribute recognition model, and the training process of the attribute recognition model may be: collecting a large number of target samples, calibrating the attributes of the targets in the collected target samples, inputting the calibrated target samples into the deep learning network, and repeatedly training the deep learning network to finally obtain an attribute recognition model.

In this embodiment, the attribute identification model is used to identify the position of the target in the monitored scene, where the position may be an absolute position of the target in the monitored scene or a relative position of the target in the monitored scene with respect to the street lamp, which is reasonable.

S103, determining a target street lamp for illuminating the identified target according to the position of the target in the monitoring scene;

in this step, after the position of the target in the monitored scene image is obtained, a street lamp whose distance to the target is within a preset distance may be selected according to the position of the target in the monitored scene, since the street lamp whose distance to the target is within the preset distance range is a street lamp capable of illuminating the target; in addition, because there may be a plurality of street lamps within a preset distance from the target, some street lamps are capable of effectively illuminating the target, and some street lamps are incapable of effectively illuminating the target, in this case, the street lamps capable of effectively illuminating the target may be determined as the target street lamps. It is understood that the number of the target street lamps may be one or more.

For example, after the electronic device acquires an image, recognizing that a target exists in the image, and acquiring the position of the target; and the distance to the target is within the preset distance range, but the street lamp is closer to one street lamp of the two street lamps and is farther from the other street lamp. Obviously, the target needs to be illuminated by the street lamp closer to the target, that is, the street lamp closer to the target is a street lamp capable of effectively illuminating the target, and therefore, the street lamp closer to the target can be determined as the target street lamp.

It can be understood by those skilled in the art that the preset distance range in the above description can be set according to actual situations, and the embodiment of the present invention does not specifically limit the size of the preset distance.

S104, determining the brightness of each target street lamp according to the attributes of the targets and the position of each target street lamp in the monitoring scene;

in this embodiment, the attribute of the target is the position of the target in the monitoring scene, after the position of the target in the monitoring scene is determined, the distance from the target street lamp to the target can be calculated according to the position of the target in the monitoring scene and the position of each target street lamp in the monitoring scene, and the brightness of the target street lamp is determined according to the distance from the target street lamp to the target.

In one embodiment, determining the brightness of each target street lamp according to the obtained position of the target in the monitored scene and the position of each target street lamp in the monitored scene may include the following two steps:

the first step is: calculating the brightness adjusting factor of each target street lamp according to the following formula:

wherein, P represents a brightness adjustment factor, i is an identification number of an identified target, each target in the monitored scene image corresponds to an identification number, and the identification number may be 1, 2, 3, etc.; a, b, c.. etc. are also possible; the min function is a function of taking the minimum value, x_iAnd y_iPosition coordinates of the target marked as i in the monitored scene; x and Y are position coordinates of a target street lamp;

from the above formula, the brightness adjustment factor of a target street lamp is calculated according to the sum of the reciprocal of the distance from each target in the monitored scene to the target street lamp, and the farther the distance from a target street lamp to each target in the monitored scene image is, the smaller the brightness adjustment factor is. Specifically, if the distance between one target street lamp and each target in the monitoring scene image is far, the calculated brightness adjusting factor of the target street lamp is small; if the distance between one target street lamp and each target in the monitoring scene image is short, the calculated brightness adjusting factor of the target street lamp is large; and if one target street lamp is far away from some targets in the monitoring scene image and is close to other targets in the monitoring scene image, the calculated brightness adjusting factor of the target street lamp is centered.

In the above formula, the position coordinates of the target and the position coordinates of the target street lamp are both two-dimensional coordinates, and for the accuracy of distance calculation, the two-dimensional coordinates may be converted into world coordinates, which is also reasonable.

The second step is: and determining the brightness of each target street lamp according to the preset corresponding relation between the brightness adjustment factor and the brightness adjustment factor of each target street lamp.

As can be seen from the above description, the farther a target street lamp is from each target in the monitored scene image, the smaller the brightness adjustment factor of the target street lamp is calculated, and the target in the monitored scene image needs to be illuminated by the target street lamp closer to the target. Therefore, it can be known that the corresponding relationship between the preset brightness adjustment factor and the brightness may be: the larger the brightness adjusting factor is, the higher the brightness of the target street lamp is; the smaller the brightness adjustment factor, the smaller the brightness of the target street lamp. The corresponding relation between the brightness factor and the brightness is obtained through a large number of experiments by the inventor, and the method has high accuracy.

After the brightness adjusting factor of each target street lamp is calculated through the first step, the brightness of each target street lamp can be obtained according to the corresponding relation between the preset brightness adjusting factor and the brightness.

And S105, controlling each target street lamp to illuminate at the determined brightness.

After the brightness of each target street lamp is obtained, the electronic device sends a corresponding control signal to each target street lamp, so that the brightness of each target street lamp is the brightness obtained through the calculation of S104, and each target street lamp illuminates according to the determined brightness.

In the technical scheme provided by the embodiment of the invention, when the electronic equipment identifies that a target appears in a monitoring scene, firstly, a target street lamp capable of illuminating the target is determined according to the position of the target in the monitoring scene; and determining the brightness of each target street lamp according to the position of the target in the monitoring scene and the position of each target street lamp in the monitoring scene, and further controlling each target street lamp to illuminate at the determined brightness. Instead of the electronic equipment, as long as the electronic equipment detects that the target exists in the monitored scene image, each target street lamp with the distance to the target within the preset distance range works according to the rated power. Therefore, through the technical scheme provided by the embodiment of the invention, the target street lamp can illuminate the target, and meanwhile, the waste of electric energy can be effectively avoided.

In order to further reduce the waste of electric energy, an embodiment of the present invention further provides another street lamp control method, as shown in fig. 2, the street lamp control method includes the following steps:

s201, acquiring a monitoring scene image;

s202, identifying a target in the monitored scene image, and obtaining the attribute of the identified target, wherein the attribute of the target comprises: the position of the target in the monitored scene;

s203, determining a target street lamp for illuminating the identified target according to the position of the target in the monitoring scene;

s204, determining the brightness of each target street lamp according to the attributes of the targets and the position of each target street lamp in the monitoring scene;

s205, controlling each target street lamp to illuminate at the determined brightness;

and S206, when the monitoring scene image is identified to have no target, controlling the brightness of each street lamp in the monitoring scene to be preset brightness.

In this embodiment, steps S201 to S205 are the same as steps S101 to S105 in the embodiment shown in fig. 1, and steps S101 to S105 have been described in detail in the embodiment shown in fig. 1, and therefore, steps S201 to S205 are not described again in this embodiment of the present invention. Step S206 will be explained in detail below.

And when the target does not exist in the monitoring scene image, the target is illustrated to leave the monitoring scene. After the target leaves the monitoring scene, if the street lamp in the monitoring scene still illuminates at the brightness determined when the target exists in the monitoring scene, the waste of electric energy is caused.

In order to save electric energy, when no target is identified in the monitoring scene, the brightness of each street lamp in the monitoring scene is controlled to be preset brightness. It can be understood that, when the camera for capturing the monitoring scene image is a normal camera, the preset brightness may be a brightness that enables the normal camera to capture a clear monitoring scene image; when the camera for shooting the monitoring scene image is a low-illumination camera, the low-illumination camera still can shoot a clear monitoring scene image when the street lamp is in a deep sleep state, and the preset brightness can be 0 at the moment, namely the target street lamp is in the deep sleep state. The embodiment of the present invention does not specifically limit the magnitude of the preset luminance.

It is understood that step S206 may be performed after step S205, and may also be performed after step S201. Specifically, after the monitored scene image is collected, if it is identified that no target exists in the monitored scene image, it is indicated that no target exists in the monitored scene at the current moment, and in order to achieve the purpose of energy saving, the brightness of each street lamp in the monitored scene is controlled to be the preset brightness.

It should be noted that the execution subject may identify whether the target exists in the monitoring scene in real time, or may identify whether the target exists in the monitoring scene according to a preset time interval. It is clear that identifying whether a target exists in the monitored scene image in real time can better achieve energy savings.

In the technical scheme provided by the embodiment of the invention, when the electronic equipment identifies that a target appears in a monitoring scene, firstly, a target street lamp capable of illuminating the target is determined according to the position of the target in the monitoring scene; determining the brightness of each target street lamp according to the position of the target in the monitoring scene and the position of each target street lamp in the monitoring scene, and further controlling each target street lamp to illuminate at the determined brightness; and when the fact that the target does not exist in the monitored scene image is recognized, controlling the brightness of the target street lamp to be preset brightness. Therefore, through the technical scheme provided by the embodiment of the invention, the target street lamp can illuminate the target, and meanwhile, the waste of electric energy can be effectively avoided.

In order to further reduce the waste of electric energy, an embodiment of the present invention further provides another street lamp control method, as shown in fig. 3, the street lamp control method includes the following steps:

s301, acquiring a monitoring scene image;

s302, identifying a target in the monitored scene image, and obtaining the attribute of the identified target, wherein the attribute of the target comprises: the position of the target in the monitoring scene, the type of the target and the speed of the target;

s303, determining a target street lamp for illuminating the identified target according to the position of the target in the monitoring scene;

s304, determining the brightness of each target street lamp according to the position of the target in the monitoring scene, the position of each target street lamp in the monitoring scene and one or more other attributes of the target except the position of the target in the monitoring scene;

and S305, controlling each target street lamp to illuminate at the determined brightness.

In this embodiment, steps S301, S303, and S305 are sequentially the same as steps S101, S103, and S105 in the embodiment shown in fig. 1, and steps S101, S103, and S105 have been described in detail in the embodiment shown in fig. 1, so steps S301, S303, and S305 are not described again in this embodiment of the present invention. The steps S302 and S304 will be explained in detail below.

S302, identifying a target in the monitored scene image, and obtaining the attribute of the identified target, wherein the attribute of the target comprises: the position of the target in the monitored scene, the category of the target, and the velocity of the target.

After the monitored scene image is obtained, in order to be able to determine whether a target appears in the monitored scene, the target in the monitored scene image needs to be identified. There are various ways to identify the target, and since the way to identify the target has been elaborated in the embodiment shown in fig. 1, it is not described herein again.

After identifying the target in the monitored scene image, the attributes of the identified target need to be obtained, and in this embodiment, the attributes of the target may include: the position of the target in the monitored scene, the category of the target, and the velocity of the target. Specifically, the categories of the targets may be: people, vehicles, animals, etc., not to mention here, the speed of an object is the speed at which the object moves in the monitored scene, wherein the speed of the object is a vector, both magnitude and direction.

In this embodiment, the position of the target in the monitored scene, the category of the target, and the velocity of the target may be identified by the attribute identification model. The number of attribute identification models may be 1, 2, or 3. Specifically, when the number of the attribute identification models is 1, the attribute identification model may include three sub-attribute identification models, where a first sub-attribute identification model is used to identify a position of the target in the monitored scene, a second sub-attribute identification model is used to identify a category of the target, and a third sub-attribute identification model is used to identify a speed of the target; when the number of the attribute identification models is 2, one attribute identification model comprises two sub-attribute identification models, namely, the attribute identification model is used for identifying two attributes of the three attributes of the position of the target in the monitoring scene, the category of the target and the speed of the target, and the other attribute identification model is used for identifying the other attribute of the three attributes; when the number of the attribute recognition models is 3, the position of the object, the category of the object, and the speed of the object are recognized by the three attribute recognition models, respectively.

It should be noted that the attribute identification model for identifying the position of the target may identify an absolute position of the target in the monitoring scene, or may identify a position of the target in the monitoring scene relative to the street lamp; the attribute identification model for identifying the category of the object may determine the category of the object by identifying which category the object is in the highest probability, for example, if the attribute identification model identifies that the object is a person, the category of the object is determined to be a person; the attribute identification model for identifying the speed of the target may identify a range of the speed, for example, a speed threshold may be preset, and if the identified speed is smaller than the speed threshold, the speed of the target is determined to be slower, and if the identified speed is greater than the speed threshold, the speed of the target is determined to be faster.

Of course, the speed of the target may be calculated by any other calculation method capable of calculating the speed. For example, the camera captures a plurality of monitoring scene images, so that the positions of the target in the plurality of monitoring scene images can be known, and the capturing time of the plurality of monitoring scene images is also determined, so that the speed of the target can be estimated.

S304, determining the brightness of each target street lamp according to the position of the target in the monitoring scene, the position of each target street lamp in the monitoring scene and one or more other attributes of the target except the position of the target in the monitoring scene.

In one embodiment, the brightness of each target street lamp may be determined according to the position of the target in the monitoring scene, the position of each target street lamp in the monitoring scene, and the category of the target, and may also be determined according to the position of the target in the monitoring scene, the position of each target street lamp in the monitoring scene, and the speed of the target, and may also be determined according to the position of the target in the monitoring scene, the position of each target street lamp in the monitoring scene, the category of the target, and the speed of the target, and the process of determining the brightness of each target street lamp may include the following two steps:

wherein, P represents brightness adjusting factor, i is an identification number of a recognized target, attr (i) is a weighting coefficient corresponding to the attribute of the target with the identification number of i, and r_iCoefficient adjustment factors corresponding to the target with the identification number i, and the min function is a minimum function, x_iAnd y_iThe position coordinates of the target with the identification number i in the monitoring scene are obtained; x and Y are the position coordinates of a target street light.

For each target street lamp, the position of the target street lamp in the monitoring scene is determined, and therefore, the brightness factor of the target street lamp is related to the position of the target in the monitoring scene, the category of the target and the speed of the target.

In the embodiment shown in fig. 1, the relationship between the position of the target in the monitored scene and the magnitude of the brightness adjustment factor of the target street lamp has been elaborated, and details are not repeated here.

The relationship between the magnitude of the brightness factor of the target street lamp and the speed and category of the target will be described in detail below.

First, the relationship between the magnitude of the brightness factor of the target street lamp and the speed of the target is elaborated,

for a plurality of targets with different speeds, the brightness adjustment factor of the target street lamp may be different even if the plurality of targets are the same distance from the target street lamp. Specifically, the faster the speed of the target is, the shorter the time of the target staying near the target street lamp is, and the lower the degree of dependence of the target on the target street lamp is; the slower the speed of the target, the longer the time spent in the vicinity of the target street lamp, the higher the degree of dependence of the target on the target street lamp.

For example, taking the target as a bicycle or an automobile as an example, in practical applications, there are two scenarios, the first scenario is: the distance between the bicycle and the target street lamp is 5 meters, and the speed of the bicycle is 5 meters per second; the second scenario is: the distance between the automobile and the target street lamp is also 5 meters, and the speed of the automobile is 10 meters per second. It can be seen from this that: the speed of the bicycle is slower, so that the bicycle stays near the target street lamp for a longer time, and the degree of dependence on the target street lamp is higher; and the speed of the automobile is higher, so that the automobile stays near the target street lamp for a short time, and the dependence degree on the target street lamp is lower. At the moment, the brightness adjusting factor of the target street lamp is larger when the target is a bicycle by adjusting the weighting factor corresponding to the attribute of the target and the coefficient adjusting factor corresponding to the target; when the target is an automobile, the brightness adjusting factor of the target street lamp is small.

It is emphasized that velocity is a vector, which has not only magnitude, but also direction. The brightness adjustment factor of the target street lamp is not only related to the speed of the target, but also related to the speed direction of the target, that is, the brightness adjustment factor of the target street lamp is related to the moving direction of the target.

For example, in practical applications, there are two scenarios, the first scenario is: the distance between the bicycle and the target street lamp is 5 meters, the speed of the bicycle is 5 meters per second, and the speed direction of the bicycle is towards the target street lamp; another scenario is: the distance of bicycle apart from target street lamp is 5 meters, and the speed size of bicycle is 5 meters per second, and the speed direction of bicycle is for keeping away from target street lamp. Therefore, in the two scenarios, the target is the same, the distance between the target and the target street lamp is the same, and the speed of the target is the same, but the two scenarios are different in that: the speed direction of the targets is different.

In the first scenario, the bicycle runs towards the target street lamp, and in the next time, the distance between the bicycle and the target street lamp is closer and closer, so that the degree of dependence on the target street lamp is higher; in the second scenario, the target runs against the target street lamp, and in the next time, the distance between the bicycle and the target street lamp is longer and longer, so that the degree of dependence on the target street lamp is lower. Therefore, the brightness adjusting factor of the target street lamp in the first scene is larger, and the brightness adjusting factor of the target street lamp in the second scene is smaller by adjusting the weighting coefficient corresponding to the attribute of the target and the coefficient adjusting factor corresponding to the target.

Secondly, the relationship between the brightness factor of the target street lamp and the category of the target is elaborated,

for a plurality of targets of different categories, the brightness adjustment factor of the target street lamp may be different even if the distance between the plurality of targets and the target street lamp is the same and the speed of the target is the same.

For example, in practical applications, there are two scenarios, the first scenario is: the target is a person, the distance between the person and the target street lamp is 5 meters, and the speed is 5 meters per second; the second scenario is: the target is an automobile, the distance between the automobile and the target street lamp is also 5 meters, and the speed is also 5 meters per second. Because the person does not have a light source, the degree of dependence on the target street lamp is high; and the automobile is provided with a light source, so that the dependence on the target street lamp is low. Therefore, the brightness adjusting factor of the target street lamp is larger when the target is a person by adjusting the weighting coefficient corresponding to the attribute of the target and the coefficient adjusting factor corresponding to the target; when the target is an automobile, the brightness adjusting factor of the target street lamp is small.

In summary, the brightness adjustment factor of the target street lamp is related to three target attributes, namely, the type of the target, the speed of the target, and the position of the target in the monitored scene, so that in practical application, the brightness adjustment factor of the target street lamp can be adjusted by adjusting the weighting factor corresponding to the attribute of the target and the coefficient adjustment factor corresponding to the target. Since the relationship between the three target attributes and the brightness adjustment factor of the target street lamp is elaborated in detail in the above description, it is not described herein again.

After the brightness adjustment factor of each target street lamp is calculated, the brightness of each target street lamp can be determined according to the corresponding relationship between the preset brightness adjustment factor and the brightness. The corresponding relation between the brightness factor and the brightness is obtained through a large number of experiments by the inventor, and the method has high accuracy.

According to the technical scheme provided by the embodiment of the invention, when the electronic equipment identifies that a target appears in a monitoring scene, a target street lamp capable of illuminating the target is determined according to the position of the target in the monitoring scene; and determining the brightness of each target street lamp according to the position of the target in the monitoring scene, the position of each target street lamp in the monitoring scene, the type of the target and the speed of the target, and further controlling each target street lamp to illuminate at the determined brightness. Therefore, the technical scheme provided by the embodiment of the invention can ensure that the target street lamp can better illuminate the target and avoid the waste of electric energy.

In order to improve the accuracy of the electronic device in identifying the target in the monitored scene image, as shown in fig. 4, an embodiment of the present invention further provides a street lamp control method, including the following steps:

s401, acquiring a monitoring scene image;

s402, identifying a target in the monitoring scene image;

s403, selecting targets with confidence degrees larger than or equal to a preset confidence degree from the identified targets;

s404, obtaining the attributes of the selected target, wherein the attributes of the target include: the position of the target in the monitored scene;

s405, determining a target street lamp for illuminating the selected target according to the position of the target in the monitoring scene;

s406, determining the brightness of each target street lamp according to the position of the target in the monitoring scene and the position of each target street lamp in the monitoring scene;

and S407, controlling each target street lamp to illuminate at the determined brightness.

In this embodiment, steps S401, S402, S406, and S407 have already been described in detail in the embodiment shown in fig. 1, and are not repeated herein, and steps S403 to S405 will be described in detail below.

because the confidence degrees of some targets are low in the targets identified from the monitored scene image, in order to improve the identification accuracy of the electronic equipment and reduce the load of the electronic equipment, the targets with the confidence degrees larger than or equal to the preset confidence degrees are selected from the identified targets. The embodiment of the invention does not specifically limit the size of the preset confidence.

after the target with the confidence degree greater than or equal to the preset confidence degree in the monitored scene image is selected, the attribute of the selected target needs to be obtained, in this embodiment, the attribute of the target includes the position of the target, so that in the subsequent step, the target street lamps for illuminating the target and the brightness of each target street lamp can be determined according to the position of the target, wherein the manner of obtaining the attribute of the selected target is described in detail in the embodiment shown in fig. 1, and is not described herein again.

S405, determining a target street lamp for illuminating the selected target according to the position of the target in the monitoring scene.

In this step, after selecting a target with a confidence degree greater than or equal to a preset confidence degree in the monitored scene image, a street lamp with a distance to the target within a preset distance may be selected according to the position of each selected target, that is, a street lamp with a distance to the target within a preset distance range may be a street lamp capable of illuminating the target; in this case, the target street lamp may be determined to be a street lamp that can effectively illuminate the target, and the target street lamp may be a street lamp that can effectively illuminate the target. It is understood that the number of the target street lamps may be one or more.

According to the technical scheme provided by the embodiment of the invention, when the electronic equipment identifies that the target appears in the monitored scene, the electronic equipment selects the target with the confidence coefficient larger than or equal to the preset confidence coefficient from the identified targets, and determines the target street lamp capable of illuminating the target according to the position of the target in the monitored scene; and determining the brightness of each target street lamp according to the position of the target in the monitoring scene and the position of each target street lamp in the monitoring scene, and further controlling each target street lamp to illuminate at the determined brightness. Therefore, by the technical scheme provided by the embodiment of the invention, the waste of electric energy can be avoided under the condition that the target street lamp is ensured to be the target illumination; and the accuracy of electronic equipment identification can be improved, and the load of the electronic equipment can be reduced.

In a second aspect, an embodiment of the present invention further provides a street lamp control device, as shown in fig. 5, the device includes:

an image obtaining module 510, configured to obtain a monitoring scene image;

an object identifying module 520, configured to identify an object in the monitored scene image, and obtain an attribute of the identified object, where the attribute of the object includes: the position of the target in the monitored scene;

a street lamp determining module 530, configured to determine a target street lamp for illuminating the identified target according to a position of the target in the monitored scene;

the brightness determining module 540 is configured to determine the brightness of each target street lamp according to the attribute of the target and the position of each target street lamp in the monitoring scene;

a brightness control module 550 for controlling each target street lamp to illuminate at the determined brightness;

the image obtaining module 510 is specifically configured to: and acquiring a monitoring scene image by using a low-illumination camera.

The brightness determining module 540 is specifically configured to:

The brightness determining module 540 is further configured to determine, if it is identified that no target exists in the monitored scene image, the brightness of each target street lamp in the monitored scene is a preset brightness.

In order to further avoid the waste of the electric energy, an embodiment of the present invention further provides another street lamp control device, as shown in fig. 6, the device includes:

an image obtaining module 610, configured to obtain a monitoring scene image;

an object identifying module 620, configured to identify an object in the monitored scene image, and obtain an attribute of the identified object, where the attribute of the object further includes: the category of the target and the speed of the target;

a street lamp determining module 630, configured to determine a target street lamp for illuminating the identified target according to a position of the target in the monitored scene;

the brightness determining module 640 is configured to determine the brightness of each target street lamp according to the position of the target in the monitoring scene and the position of each target street lamp in the monitoring scene;

and a brightness control module 650 for controlling each target street lamp to illuminate at the determined brightness.

Wherein the brightness determining module 640 comprises:

the first brightness determining unit 641 is configured to determine the brightness of each target street lamp according to the position of the target in the monitored scene, the position of each target street lamp in the monitored scene, and one or more other attributes of the target except the position of the target in the monitored scene.

The first brightness determination unit 641 is specifically configured to:

wherein, P represents brightness adjusting factor, i is an identification number of a recognized target, attr (i) is a weighting coefficient corresponding to the attribute of the target with the identification number of i, and r_iThe coefficient adjustment factor for the target identified by the number i,the min function is a function of taking the minimum value, x_iAnd y_iThe position coordinates of the target with the identification number i in the monitoring scene are obtained; x and Y are position coordinates of a target street lamp;

An embodiment of the present invention further provides a street lamp control device, as shown in fig. 7, the device includes:

an image obtaining module 710, configured to obtain a monitoring scene image;

the target identifying module 720 is configured to obtain the attribute of the target selected by the target selecting module, where the attribute of the selected target includes: the position of the target in the monitored scene;

a target selecting module 730, configured to select a target with a confidence greater than or equal to a preset confidence from the targets identified by the target identifying module;

a street lamp determining module 740, configured to determine a target street lamp for illuminating the identified target according to a position of the target in the monitored scene;

the brightness determining module 750 is configured to determine the brightness of each target street lamp according to the position of the target in the monitoring scene and the position of each target street lamp in the monitoring scene;

and a brightness control module 760 for controlling each target street lamp to illuminate at the determined brightness.

An embodiment of the present invention further provides an electronic device, as shown in fig. 8, which includes a processor 801, a communication interface 802, a memory 803, and a communication bus 804, where the processor 801, the communication interface 802, and the memory 803 complete mutual communication through the communication bus 804,

a memory 803 for storing a computer program;

the processor 801 is configured to execute the street lamp control method according to any one of the above-mentioned first method embodiments when executing the program stored in the memory 803.

The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.

The communication interface is used for communication between the electronic equipment and other equipment.

The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.

In another embodiment of the present invention, a computer-readable storage medium is further provided, where instructions are stored in the computer-readable storage medium, and when the instructions are executed on a computer, the computer is caused to execute the street lamp control method according to any one of the method embodiments of the first aspect.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the device, the electronic apparatus, and the storage medium embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiments.

The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims

1. A street lamp control method, characterized in that the method comprises:

calculating the distance from the target street lamp to the target according to the attribute of the target and the position of each target street lamp in the monitoring scene, and determining the brightness of the target street lamp according to the distance from the target street lamp to the target;

controlling each target street lamp to illuminate with the determined brightness;

wherein, the calculating the distance from the target street lamp to the target according to the attribute of the target and the position of each target street lamp in the monitoring scene, and determining the brightness of the target street lamp according to the distance from the target street lamp to the target comprises:

calculating to obtain a brightness adjusting factor of each target street lamp according to the sum of reciprocals of the distances from the targets to each target street lamp in the monitoring scene:

2. The method of claim 1, further comprising:

3. The method of claim 1, wherein calculating the brightness adjustment factor of each target street lamp according to the sum of reciprocal of the distance from the target to each target street lamp in the monitored scene comprises:

wherein P represents a brightness adjustment factor, i is an identification number of an identified target, min is a minimum function, x_iAnd y_iThe position coordinates of the target with the identification number i in the monitoring scene are obtained; x and Y are the position coordinates of a target street light.

4. The method of claim 1, wherein the attributes of the target further comprise: the category of the target and the speed of the target;

the calculating the distance from the target street lamp to the target according to the attribute of the target and the position of each target street lamp in the monitoring scene, and determining the brightness of the target street lamp according to the distance from the target street lamp to the target comprises the following steps:

5. The method of claim 4, wherein determining the brightness of each target street lamp according to the position of the target in the monitored scene, the position of each target street lamp in the monitored scene, and one or more other attributes of the target except the position of the target in the monitored scene comprises:

wherein, P represents brightness adjusting factor, i is an identification number of a recognized target, attr (i) is a weighting coefficient corresponding to the attribute of the target with the identification number of i, and r_iCorresponding to an object of identification number iCoefficient adjustment factor, min function being a function taking the minimum value, x_iAnd y_iThe position coordinates of the target with the identification number i in the monitoring scene are obtained; x and Y are position coordinates of a target street lamp;

6. The method of any one of claims 1 to 5, wherein the obtaining attributes of the identified target comprises:

7. The method of claim 1, wherein prior to said obtaining attributes of the identified target, the method further comprises:

8. The method of any of claims 1 to 5, wherein said acquiring an image of a monitored scene comprises:

and acquiring a monitoring scene image by using a low-illumination camera.

9. A street light control device, characterized in that the device comprises:

the image acquisition module is used for acquiring a monitoring scene image;

the brightness determining module is used for calculating the distance from the target street lamp to the target according to the attribute of the target and the position of each target street lamp in the monitoring scene, and determining the brightness of the target street lamp according to the distance from the target street lamp to the target;

the brightness control module is used for controlling each target street lamp to illuminate at the determined brightness;

the brightness determination module is specifically configured to:

calculating to obtain a brightness adjusting factor of each target street lamp according to the sum of reciprocals of the distances from the targets to each target street lamp in the monitoring scene; and determining the brightness of each target street lamp according to the preset corresponding relation between the brightness adjustment factor and the brightness adjustment factor of each target street lamp.

10. The apparatus of claim 9, wherein the brightness determination module is specifically configured to:

11. The apparatus of claim 9, wherein the brightness determination module is specifically configured to:

12. The apparatus of claim 10, wherein the attributes of the target further comprise: the category of the target and the speed of the target;

the brightness determination module includes:

13. The apparatus according to claim 12, wherein the first brightness determination unit is specifically configured to:

14. The apparatus according to any one of claims 9 to 13, wherein the object identification module is specifically configured to:

15. The apparatus of claim 9, further comprising:

the street lamp determination module is specifically configured to:

16. The apparatus according to any one of claims 9 to 13, wherein the image acquisition module is specifically configured to:

and acquiring a monitoring scene image by using a low-illumination camera.

17. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;

a memory for storing a computer program;

a processor for implementing the method steps of any of claims 1 to 8 when executing a program stored in the memory.