WO2021129611A1

WO2021129611A1 - Monitoring scenario detection method and apparatus, and electronic device

Info

Publication number: WO2021129611A1
Application number: PCT/CN2020/138306
Authority: WO
Inventors: 浦世亮; 戴虎
Original assignee: 上海高德威智能交通系统有限公司
Priority date: 2019-12-24
Filing date: 2020-12-22
Publication date: 2021-07-01
Also published as: CN111767775B; CN111767775A

Abstract

A monitoring scenario detection method and apparatus, and an electronic device. The method comprises: performing image recognition on a monitoring image of a monitoring scenario to obtain scenario information of the monitoring scenario (S101), the scenario information being used to indicate the status of various traffic signals in the monitoring scenario; determining, according to the scenario information, whether a traffic signal that does not conform to a preset rule exists in the monitoring scenario (S102); and if there is a traffic signal that does not conform to the preset rule in the monitoring scenario, determining that the monitoring scenario is abnormal (S103). In the described method, related information of a monitoring scenario can be digitized by means of image recognition, thus an abnormality occurring in the monitoring scenario can be detected automatically, and a related person can promptly respond to the abnormality, thereby reducing the impact that the abnormality occurring in the monitoring scenario has on a monitoring system, and further improving the stability of the monitoring system.

Description

Monitoring scene detection method, device and electronic equipment

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on December 24, 2019, with an application number of 201911351212.3 and an invention titled "a monitoring scene detection method, device and electronic equipment", the entire content of which is incorporated by reference In this application.

Technical field

This application relates to the field of intelligent transportation technology, and in particular to a monitoring scene detection method, device, and electronic equipment.

Background technique

In some application scenarios, out of actual needs, the monitoring system needs to obtain traffic signals in the monitoring scenario. For example, in the process of taking images of violations by electronic police, it is necessary to determine whether the vehicle violates the rules based on traffic signals. In related technologies, manual configuration can be used to enable the monitoring system to obtain information related to traffic signals in the monitoring scene. For example, manually mark the location and type of traffic signals such as stop lines, guide lines, and zebra crossings in the monitoring image, and monitor The system determines whether the vehicle violates regulations based on the location and type of the marked traffic signal.

However, due to some reasons, such as human negligence, lack of maintenance, etc., the manually configured traffic signal may not match the actual application scenario, that is, the traffic signal obtained by the monitoring system does not match the actual traffic signal, so the monitoring system cannot work normally. The police, for example, may mistakenly photograph illegal and scrapped images that cannot be used as evidence of vehicle violations.

Summary of the invention

The purpose of the embodiments of this application is to provide a monitoring scene detection method, device, and electronic equipment to automatically detect abnormalities in the monitoring scene, so that relevant personnel can respond in time, and reduce the impact of abnormalities in the monitoring scene on the monitoring system The impact of this, thereby improving the stability of the monitoring system. The specific technical solutions are as follows:

In the first aspect of the present application, a monitoring scene detection method is provided, and the method includes:

Performing image recognition on the surveillance image of the surveillance scene to obtain scene information of the surveillance scene, where the scene information is used to indicate the status of each traffic signal in the surveillance scene;

According to the scene information, determine whether there is a traffic signal that does not conform to a preset rule in the monitoring scene;

If there is a traffic signal that does not conform to a preset rule in the monitoring scene, it is determined that the monitoring scene is abnormal.

In a possible implementation manner, the determining, according to the scene information, whether there is a traffic signal that does not conform to a preset rule in the monitoring scene includes:

According to the state of each traffic signal indicated by the scene information, determine whether there is a traffic signal with a completeness lower than a preset completeness threshold among the various traffic signals in the monitoring scene;

If there is a traffic signal whose integrity is lower than the preset integrity threshold, it is determined that there is a traffic signal that does not comply with the preset rule in the monitoring scene.

In a possible implementation manner, in the state of each traffic signal indicated by the scene information, it is determined whether there is a completeness degree lower than a preset completeness threshold in each of the traffic signals in the monitoring scene After the traffic signal, the method further includes:

If the scene information indicates that the completeness of at least one traffic marking is lower than the preset completeness threshold, send warning information indicating that the traffic marking is stained in the monitoring scene to the preset terminal.

If the scene information indicates that the integrity of at least one traffic sign is lower than the preset integrity threshold, sending alarm information indicating that the monitoring equipment set in the monitoring scene is not properly installed to the preset terminal.

Determining whether the state of each traffic signal represented by the scene information is consistent with the state of each traffic signal represented by the traffic signal parameters preset for the monitoring scene;

If the state of each traffic signal indicated by the scene information is inconsistent with the state of each traffic signal indicated by the traffic signal parameter preset for the monitoring scene, it is determined that there is a traffic signal that does not conform to the preset rule in the monitoring scene.

In a possible implementation manner, the determining whether the state of each traffic signal indicated by the scene information is consistent with the state of each traffic signal indicated by the traffic signal parameters preset for the monitoring scene includes:

Determining whether the state of the traffic signal represented by the scene information is missing relative to the state of the traffic signal represented by the traffic signal parameter;

The method also includes:

If the state of the traffic signal indicated by the scene information is missing relative to the state of the traffic signal indicated by the traffic signal parameter, send warning information indicating the absence of a traffic signal in the monitoring scene to a preset terminal, or send to the The preset terminal sends alarm information used to indicate that the traffic signal parameter setting is unreasonable

In a possible implementation manner, the determining whether each traffic signal represented by the scene information is consistent with each traffic signal represented by a traffic signal parameter preset for the monitoring scene includes:

Determine whether there is an offset between the position of each traffic signal indicated by the scene information and the position of each traffic signal indicated by the traffic signal parameter;

The method also includes:

If each traffic signal indicated by the scene information has an offset with respect to each traffic signal indicated by the traffic signal parameter, an alarm information used to indicate that the monitoring device installed in the monitoring scene is offset is sent to the preset terminal.

In a possible implementation manner, the method further includes:

Acquiring status information sent by a signal light detector set in the monitoring scene, where the status information is used to indicate the status of each signal light detected by the signal light detector;

The determining, according to the scene information, whether there is a traffic signal that does not conform to a preset rule in the monitoring scene includes:

Determining whether the state of the signal light indicated by the scene information is consistent with the state of the signal indicated by the state information;

If the state of the signal lamp indicated by the scene information is inconsistent with the state of the signal indicated by the state information, it is determined that there is a traffic signal that does not conform to a preset rule in the monitoring scene.

According to the scene information, determine whether the duration of the signal lights in the monitoring scene continuously being in the same state exceeds a preset duration threshold;

If the duration of the signal lights in the monitoring scene continuously being in the same state exceeds the preset duration threshold, it is determined that there is a traffic signal that does not meet the preset rule in the monitoring scene.

In a possible implementation manner, after the determining that the monitoring scene is abnormal, the method further includes:

It is forbidden to capture an event associated with a target traffic signal, and the target traffic signal is a traffic signal that does not comply with a preset rule in the monitoring scene.

In a possible implementation manner, after determining whether the state of each traffic signal represented by the scene information is consistent with the state of each traffic signal represented by the traffic signal parameters preset for the monitoring scene, The method also includes:

If the status of each traffic signal represented by the scene information is inconsistent with the status of each traffic signal represented by the traffic signal parameters preset for the monitoring scene, the monitoring equipment is monitored according to the scene information of the monitoring scene. Configure the parameters for correction.

In a possible implementation manner, the correcting the configuration parameters of the monitoring device according to the scene information of the monitoring scene includes:

According to the scene information of the monitoring scene, generating configuration parameters that match the scene information as correction configuration parameters;

The configuration parameter of the monitoring device is changed to the correction configuration parameter.

According to the location of each traffic signal indicated by the scene information, determine whether there is a traffic signal located in the area where a preset abnormal event occurs in the monitoring scene;

If there is a traffic signal located in the area where the preset abnormal event occurs, it is determined that there is a traffic signal that does not comply with the preset rule in the monitoring scene.

In a second aspect of the present application, a monitoring scene detection device is provided, the device including:

The image recognition module is configured to perform image recognition on the monitoring image of the monitoring scene to obtain scene information of the monitoring scene, where the scene information is used to indicate the status of each traffic signal in the monitoring scene;

The rule matching module is configured to determine, according to the scene information, whether there is a traffic signal that does not conform to a preset rule in the monitoring scene;

The abnormality monitoring module is configured to determine that the monitoring scene is abnormal if there is a traffic signal that does not conform to a preset rule in the monitoring scene.

In a possible implementation manner, the rule matching module is specifically configured to determine whether there is a low integrity in each traffic signal in the monitoring scene according to the state of each traffic signal indicated by the scene information Traffic signals at a preset integrity threshold;

In a possible implementation, the abnormality monitoring module is further configured to determine whether there are any traffic signals in the monitoring scene based on the status of each traffic signal indicated by the scene information After the traffic signal whose integrity is lower than the preset integrity threshold, if the scene information indicates that the integrity of at least one traffic marking is lower than the preset integrity threshold, send to the preset terminal indicating the monitoring scene Warning information of traffic marking defacement.

In a possible implementation manner, the abnormality monitoring module is further configured to determine whether there are any traffic signals in the monitoring scene based on the status of each traffic signal indicated by the scene information After a traffic signal whose integrity is lower than the preset integrity threshold, if the integrity of at least one traffic sign indicated by the scene information is lower than the preset integrity threshold, send to the preset terminal a message indicating that the traffic signal is set at the preset integrity threshold. The monitoring equipment in the monitoring scene sets up unreasonable alarm information.

In a possible implementation, the rule matching module is specifically configured to determine the status of each traffic signal represented by the scene information and the status of each traffic signal represented by the traffic signal parameters preset for the monitoring scene. Whether the status is consistent;

In a possible implementation manner, the rule matching module is specifically configured to determine whether the state of the traffic signal indicated by the scene information is missing relative to the state of the traffic signal indicated by the traffic signal parameter;

The abnormality detection module is further configured to send to a preset terminal a traffic signal indicating the traffic signal in the monitoring scene if the state of the traffic signal indicated by the scene information is missing relative to the state of the traffic signal indicated by the traffic signal parameter Missing warning information, or sending warning information indicating that the traffic signal parameter setting is unreasonable to the preset terminal.

In a possible implementation, the rule matching module is specifically configured to determine whether the position of each traffic signal indicated by the scene information is offset from the position of each traffic signal indicated by the traffic signal parameter;

The abnormality monitoring module is specifically configured to send to a preset terminal the monitoring set in the monitoring scene if each traffic signal indicated by the scene information has an offset relative to each traffic signal indicated by the traffic signal parameter. Alarm information that the device has shifted.

In a possible implementation manner, the device further includes a signal light state acquisition module, which is used to acquire the state information sent by the signal light detector set in the monitoring scene, and the state information is used to indicate that the signal light detector detects The status of each semaphore that arrives;

The rule matching module is specifically configured to determine whether the state of the signal light indicated by the scene information is consistent with the state of the signal indicated by the state information;

In a possible implementation manner, the rule matching module is specifically configured to determine, according to the scene information, whether the duration of the signal lights in the monitoring scene continuously being in the same state exceeds a preset duration threshold;

In a possible implementation, the device further includes a monitoring system management module, which is configured to prohibit capturing an event associated with a target traffic signal after the monitoring scene is determined to be abnormal, and the target traffic signal is the target traffic signal. Traffic signals that do not comply with preset rules in the monitoring scene.

In a possible implementation manner, the device further includes a parameter correction module configured to determine the state of each traffic signal represented by the scene information and the preset for the monitoring scene After the states of the various traffic signals indicated by the traffic signal parameters are consistent, if the states of the various traffic signals indicated by the scene information are inconsistent with the states of the various traffic signals indicated by the traffic signal parameters preset for the monitoring scene, Correct the configuration parameters of the monitoring device according to the scene information of the monitoring scene.

In a possible implementation manner, the parameter correction module is specifically configured to generate configuration parameters matching the scene information according to the scene information of the monitoring scene, as the correction configuration parameters;

In a possible implementation manner, the rule matching module is specifically configured to determine whether there are any traffic signals located in the area where a preset abnormal event occurs in the monitoring scene according to the position of each traffic signal indicated by the scene information. Traffic signal

In the third aspect of this application, an electronic device is provided, including:

Memory, used to store computer programs;

The processor is configured to implement the method steps in any one of the above-mentioned first aspects when executing the program stored in the memory.

In a fourth aspect of the present application, a computer-readable storage medium is provided, and a computer program is stored in the computer-readable storage medium. Method steps.

The monitoring scene detection method, device, and electronic equipment provided by the embodiments of the application can digitize the relevant information of the monitoring scene through image recognition, so as to automatically detect abnormalities in the monitoring scene, so that relevant personnel can respond in time. Reduce the impact of abnormalities in the monitoring scene on the monitoring system, thereby improving the stability of the monitoring system. Of course, implementing any product or method of the present application does not necessarily need to achieve all the advantages described above at the same time.

Description of the drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic flowchart of a monitoring scene detection method provided by an embodiment of the application;

FIG. 2 is a schematic flowchart of a method for detecting traffic signals in a monitoring scenario applied to an electronic police according to an embodiment of the application; FIG.

3 is a schematic diagram of another flow chart of a method for detecting traffic signals in a monitoring scenario applied to an electronic police according to an embodiment of the application;

FIG. 4 is a schematic flow diagram of another method for detecting traffic signals in a monitoring scenario applied to an electronic police according to an embodiment of the application; FIG.

FIG. 5 is a schematic flow diagram of another method for detecting traffic signals in a monitoring scenario applied to an electronic police according to an embodiment of the application; FIG.

FIG. 6 is a schematic flowchart of another monitoring scene detection method provided by an embodiment of the application;

FIG. 7 is a schematic flow diagram of another method for detecting traffic signals in a monitoring scenario applied to an electronic police according to an embodiment of the application; FIG.

FIG. 8a is a schematic structural diagram of a monitoring scene detection device provided by an embodiment of this application;

FIG. 8b is a schematic diagram of another structure of a monitoring scene detection device provided by an embodiment of the application;

FIG. 8c is a schematic diagram of another structure of a monitoring scene detection device provided by an embodiment of the application;

FIG. 9 is a schematic structural diagram of an electronic device provided by an embodiment of this application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

Referring to Fig. 1, Fig. 1 is a schematic diagram of a possible flow of a monitoring scene provided by an embodiment of the application. This method can be used for any electronic device with a monitoring scene detection function in the monitoring system. For example, it may be Applied to the camera as the front end, it can also be applied to the server as the back end. Methods can include:

S101: Perform image recognition on a surveillance image of a surveillance scene to obtain scene information of the surveillance scene.

The scene information is used to indicate the status of each traffic signal in the monitoring scene. The scene information can be obtained by image recognition of the surveillance images taken at a certain time, or it can be obtained by image recognition of the surveillance images taken at multiple different moments, for example, it can be obtained by recognizing the surveillance images taken at a certain time. Perform image recognition on multiple video frames in the surveillance video to obtain scene information.

The algorithm used for image recognition can be different according to different application scenarios. For example, it can be an end-to-end mapping from the surveillance image to the scene information by using a pre-trained neural network. In other possible embodiments, the image may also be recognized using a model obtained based on traditional machine learning, which is not limited in this embodiment.

The traffic signal may include one or more of traffic markings, traffic signs, and signal lights. Traffic markings can include lane lines, stop lines, ground guidance lines, zebra crossings, and so on. Traffic signals can include warning signs, prohibition signs, and instruction signs.

The state of the traffic signal may refer to one or more attributes of the traffic signal that can be obtained through image recognition. For example, the state of the traffic signal may include the location and/or category of the traffic signal. And the status of different types of traffic signals can be expressed in different ways. For example, for traffic markings or traffic signs, the position and category of the traffic markings or traffic signs can be used to indicate the traffic markings or traffic signs. The state, and the coordinates of the four vertices of the smallest bounding rectangle of the area where the traffic line or traffic sign is located in the surveillance image can be used to indicate the location of the traffic line or traffic sign, the traffic line or traffic sign The category may be expressed in the form of a label. For example, the label “1” may indicate a lane line, the label “2” may indicate a stop line, and the label “3” may indicate a ground guide line. For another example, for a signal light, the color of the signal light may be used to indicate the state of the signal light.

S102: According to the scene information, determine whether there is a traffic signal that does not conform to a preset rule in the monitoring scene.

The preset rules can be set by the user according to actual needs or experience. For example, in some application scenarios, there may be certain requirements for the clarity of the traffic signal in the image, and it can be to determine whether the clarity of each traffic signal meets the requirement. If the clarity of the traffic signal does not meet the requirement, it is determined that there is a traffic signal that does not meet the preset rules in the monitoring scene.

It is understandable that the reason why the traffic signal does not comply with the preset rules may be abnormality of the traffic signal itself, such as traffic markings and traffic signs being defaced, or the failure of the traffic signal light to prevent normal switching, or it may be set in the monitoring system. The monitoring equipment of the scene is abnormal, such as the position and orientation angle of the monitoring equipment installed in the monitoring scene is offset from the installation position, and the installation position of the monitoring equipment installed in the monitoring scene is unreasonable, resulting in the captured traffic signs, The traffic marking is incomplete.

S103: If there is a traffic signal that does not meet the preset rule in the monitoring scene, it is determined that the monitoring scene is abnormal.

If there are traffic signals that do not conform to the rules in the monitoring scene, it can be considered that the traffic signals that the monitoring system recognizes from the monitoring scene may not be accurate enough. Based on the inaccurate traffic signals, the monitoring system cannot work normally. Therefore, it can be considered that the monitoring scenario in this case is abnormal.

On the other hand, as in the foregoing analysis, if there are traffic signals that do not conform to the preset rules in the monitoring scene, it can be considered that the traffic signals and/or the monitoring equipment in the monitoring scene are abnormal, and therefore the monitoring scene can be considered abnormal.

For the convenience of description, the following will take the application scenario of the electronic police as an example to describe the monitoring scene detection method provided in the embodiment of the present application. For other application scenarios, the principle is the same, so it will not be repeated.

Refer to Figure 2. Figure 2 is a schematic flow chart of a traffic signal detection method applied to an electronic police monitoring scene provided by an embodiment of the application, and the method includes:

S201: Identify the surveillance image of the surveillance scene to obtain scene information of the surveillance scene.

This step is the same as S101, and you can refer to the foregoing related description about S101, which will not be repeated here.

S202: Determine, according to the status of each traffic signal indicated by the scene information, whether there is a traffic signal with a completeness lower than a preset completeness threshold in the monitoring scene.

The degree of completeness may indicate how complete the shape of the traffic signal represented by the scene information is compared to the theoretical shape of the traffic signal. Exemplarily, for example, the white solid line is theoretically a continuous and uninterrupted white line segment with a certain line width. According to the position of the white solid line indicated by the scene information, the monitoring image at that position is a continuous and uninterrupted white line segment. The white line segment with a certain line width can be considered to be relatively complete. If the monitoring image at this position is a white line segment with more non-white areas (such as areas with road color), it can be considered that the completeness of the white solid line is relatively low. For another example, the left turn indicator is theoretically a circular pattern with a white border and a blue background, and there is a left turn arrow in the middle of the pattern. According to the position of the left turn indicator indicated by the scene information, the monitor image at that position is With a white border and blue background and a circular pattern with a left turn arrow in the middle, it can be considered that the completeness of the left turn indicator is relatively high. If the surveillance image at this position is a semicircular pattern with a white border and a blue background, and there are some left-turn arrows in the middle, it can be considered that the completeness of the left-turn indicator is relatively low.

The integrity threshold can be set according to the actual needs or experience of the user. The lower the integrity threshold, the lower the probability that an abnormality in the monitoring scene is not detected. The higher the integrity threshold, the lower the possibility of erroneously determining a normal monitoring scene as abnormal. And for different traffic signals, different integrity thresholds can be set, which is not limited in this embodiment.

The result obtained by determining whether there is a traffic signal whose integrity is lower than the preset integrity threshold in the monitoring scene can be a binarized signal used to indicate whether there is a traffic signal whose integrity is below the preset integrity threshold in the monitoring scene Numerical value, for example, the output result of "Yes" means that there is a traffic signal whose integrity is lower than the preset integrity threshold in the monitored scene, and the output result of "No" means that there is no traffic signal whose integrity is below the preset integrity threshold in the monitored scene signal. The output result can also be a collection of all traffic signals whose completeness is lower than the preset completeness threshold in the monitoring scene. For example, the output result can be {signal light, lane line}, which means that the completeness of the signal light and lane line in the monitoring scene is lower than the preset completeness threshold. Set the integrity threshold. The integrity of traffic signals other than the signal lights and lane lines is not lower than the preset integrity threshold. If the set is not empty, it can be considered that there is integrity in the monitoring scene below the preset integrity threshold. If the set is an empty set, it can be considered that there are no traffic signals with completeness lower than the preset completeness threshold in the monitoring scene.

S203: If there is a traffic signal whose integrity is lower than a preset integrity threshold, it is determined that there is a traffic signal that does not meet the preset rule in the monitoring scene.

If the integrity of a traffic signal is lower than the integrity threshold, it can be considered that there is less information about the traffic signal in the surveillance image, that is, it is difficult to accurately identify the traffic signal in the surveillance image. Therefore, it is difficult to use the traffic signal as a credible criterion in the process of judging whether the vehicle is in violation of the regulations based on the monitoring image.

According to different application scenarios, the reasons that cause the integrity of the traffic signal indicated by the scene information to be lower than the preset integrity threshold may be different. For example, for traffic markings, the traffic markings may be defaced, and for traffic signs, the traffic signs may be defaced, or it may be caused by the unreasonable installation of monitoring equipment in the monitoring scene. For another example, it may be due to the unreasonable erection of the monitoring equipment, which results in the part of the traffic sign being in a blind spot of the monitoring equipment.

Referring to FIG. 3, FIG. 3 is a schematic diagram of another flow chart of a traffic signal detection method applied to a monitoring scene of an electronic police according to an embodiment of the application, and the method includes:

S301: Perform image recognition on the surveillance image of the surveillance scene to obtain scene information of the surveillance scene.

S302: Determine whether the state of each traffic signal indicated by the scene information is consistent with the state of each traffic signal indicated by the traffic signal parameters preset for the monitoring scene.

The traffic signal parameters can be manually pre-configured. Illustratively, manually select the area where the zebra crossing is located in the surveillance image to obtain the traffic signal parameters preset for the zebra crossing. For example, manually mark the location of the lane line in the surveillance image to obtain Traffic signal parameters preset for lane lines.

The state of the traffic signal indicated by the scene information is inconsistent with the state of the traffic signal indicated by the traffic signal parameter, which may mean that the state of the traffic signal indicated by the scene information is missing from the state of the traffic signal indicated by the traffic signal parameter, and/ Or, the position of the traffic signal indicated by the scene information is offset from the position of the same type of traffic signal indicated by the traffic signal parameter. For example, if the scene information represents the status of 3 lanes in the monitoring scene, and the traffic signal parameter represents the status of 4 lanes in the monitoring scene, it can be considered that the status of the traffic signal represented by the scene information is relative to that represented by the traffic signal parameter. The state of the traffic signal is missing (the state of a lane line is missing), so the state of the traffic signal represented by the scene information is inconsistent with the state of the traffic signal represented by the traffic signal parameters. For another example, suppose that the scene information indicates that there is a left turn indicator in the surveillance scene, and the sign is located at position A, and the traffic signal parameter indicates that there is a left turn indicator in the surveillance scene, and the sign is located at position B, and the positions A and B are two. For different locations, it can also be considered that the state of the traffic signal represented by the scene information is different from the state of the traffic signal represented by the traffic signal parameters.

S303: If the state of the traffic signal indicated by the scene information is inconsistent with the state of the traffic signal indicated by the traffic signal parameter, it is determined that there is a traffic signal that does not conform to a preset rule in the monitored scene.

It is understandable that, regardless of the unreasonable configuration of traffic signal parameters, if the state of the traffic signal indicated by the scene information is different from the state of the traffic signal indicated by the traffic signal parameter, it means that the monitoring scene is compared with the configuration of the traffic signal. The signal parameters have changed. If the monitoring system still works according to the configured traffic signal parameters, it may not work properly.

Regardless of the possible changes in the monitoring scene, if the state of the traffic signal indicated by the scene information is different from the state of the traffic signal indicated by the traffic signal parameter, it means that the pre-configured traffic signal parameters for the monitoring scene may be unreasonable , Working in accordance with unreasonable traffic signal parameters may cause the monitoring system to fail to work normally.

In summary, if the state of the traffic signal indicated by the scene information is different from the state of the traffic signal indicated by the traffic signal parameter, it can be considered that the traffic signal of the monitored scene does not conform to the preset rule.

As in the previous analysis, if the state of the traffic signal indicated by the scene information is inconsistent with the state of the traffic signal indicated by the traffic signal parameter, it may be because the traffic signal parameter configuration is unreasonable. In order to eliminate the abnormality of the monitoring scene in this situation as soon as possible, one In a possible embodiment, if the status of each traffic signal indicated by the scene information is inconsistent with the status of each traffic signal indicated by the traffic signal parameters preset for the monitoring scene, the configuration of the monitoring equipment can be configured according to the scene information of the monitoring scene The parameters are corrected.

Exemplarily, it may be based on the scene information of the monitoring scene to generate configuration parameters matching the scene information as the correction configuration parameters. And change the configuration parameters of the monitoring equipment to correction configuration parameters. For example, assuming that the scene information of the monitoring scene indicates that the solid white line is located at position A in the monitoring scene, and the configuration parameter indicates that the solid white line is located at position B, then a configuration parameter indicating that the solid white line is located at position A is generated as a correction configuration parameter , And use the correction configuration parameter to replace the current configuration parameter.

Referring to FIG. 4, FIG. 4 is a schematic flow diagram of another method for detecting traffic signals in a monitoring scenario applied to an electronic police according to an embodiment of the application, and the method includes:

S401: Perform image recognition on a surveillance image of a surveillance scene to obtain scene information of the surveillance scene.

This step is the same as S101, and you can refer to the previous description about S101.

S402: Acquire status information sent by a signal light detector set in a monitoring scene.

The status information is used to indicate the status of each signal light detected by the signal light. The signal light detector may be integrated on the camera, or it may be integrated on the signal light, or it may be independent of the camera and the signal light, which is not limited in this embodiment.

The signal light detector may be a device used to obtain the state of the signal light in the monitoring scene in the monitoring system, and the signal light detector may determine the state of the signal light through the electrical signal generated during the operation of the signal light.

S403: Determine whether the state of the signal lamp indicated by the scene information is consistent with the state of the signal lamp indicated by the state information.

Exemplarily, assuming that the scene information indicates that the signal light in the monitoring scene is in a red light state, and the status information indicates that the signal light of the monitoring scene is in a green light state, it can be considered that the state of the signal light indicated by the scene information and the state information are The states of the indicated semaphores are inconsistent.

For another example, assuming that the scene information indicates that the signal light in the monitoring scene is in a red light state, and the status information indicates that the signal light of the monitoring scene is in a red light state, it can be considered that the state of the signal light represented by the scene information and the state information are The states of the indicated semaphores are the same.

S404: If the state of the signal lamp indicated by the scene information is inconsistent with the state of the signal lamp indicated by the state information, it is determined that there is a traffic signal that does not conform to the preset rule in the monitoring scene.

If the status of the signal light indicated by the scene information is different from the status of the signal light detected by the signal light detector, it can be considered that the status information output by the signal light detector set in the monitoring scene is incorrect. Working according to incorrect status information may cause the monitoring system to fail to work normally. Therefore, if the state of the signal lamp indicated by the scene information is inconsistent with the state of the signal indicated by the state information, it can be considered that the signal lamp in the monitoring scene does not conform to the preset rule.

Referring to FIG. 5, FIG. 5 is a schematic flow diagram of another method for detecting traffic signals in a monitoring scenario applied to an electronic police according to an embodiment of the application, and the method includes:

S501: Perform image recognition on the surveillance image of the surveillance scene to obtain scene information of the surveillance scene.

S502: According to the scene information, determine whether the duration of the signal lamp in the monitoring scene information continuously being in the same state exceeds a preset duration threshold.

Among them, the length of time that the signal lamp is continuously in the same state refers to the length of time that the signal lamp elapses from entering a state to leaving the state. According to the scene information obtained by the surveillance image recognition of multiple time nodes, determine the state of the semaphore in the surveillance scene in these multiple time nodes, and assume that if the semaphore is at the same time on two adjacent time nodes in the time domain , The semaphore is still in the same state between these two time nodes. Furthermore, according to the state of the signal light at each time node, it is determined whether the duration of the signal light in the monitoring scene information continuously being in the same state exceeds the preset duration threshold.

Exemplarily, suppose that according to the scene information, the signal light is in the green light-on state at t=0s, the green light is on at t=10s, the green light is on at t=20s, and the green light is on at t=30s. When the red light is on, and the red light is on at t=40s, it can be considered that the signal light stays in the green light state for 30s, and the red light is on for 10s. If the preset duration threshold is 25s, the duration of the signal light continuously in the green light state exceeds the preset duration threshold.

S503: If the duration of the signal lamp in the monitoring scene information continuously being in the same state exceeds the preset duration threshold, it is determined that there is a traffic signal that does not meet the preset rule in the monitoring scene.

It is understandable that the signal lights alternately turn on green, yellow, and red lights according to a preset process. That is, in the time domain, the state of the signal lamp is theoretically alternately changed. Therefore, if the signal lamp is in the same state for a long time, it can be considered that the signal lamp is malfunctioning. When there is a malfunctioning signal lamp in the monitoring scene, the monitoring system may not work normally.

In some application scenarios, when it is determined that the monitoring scene is abnormal, a corresponding record can be generated for relevant personnel to consult, and then discover the abnormality of the monitoring scene. In other application scenarios, in order to make it easier for relevant personnel to discover abnormalities in the monitoring scenario in time, alarm information can be sent to the preset terminal. The preset terminal may be a mobile terminal device of the relevant person, or a personal computer of the relevant person. The method of sending the alarm information and the specific content included in the alarm information may be different according to different application scenarios. This embodiment does not limit this. For example, it may be sending a short message carrying the alarm information to the mobile phone of the relevant person, and For example, it may also be sending an email carrying alarm information to the mailbox of the relevant person.

In a possible embodiment, in order to facilitate the relevant persons to deal with the abnormality in the monitoring scene in a targeted manner, the alarm information may be used to indicate the type of the abnormality in the monitoring scene. For example, if it is determined that the integrity of at least one traffic marking is lower than the preset integrity threshold according to the state of the traffic signal indicated by the scene information, it may send to the preset terminal the information indicating the pollution of the traffic marking in the monitoring scene. Alarm information.

For another example, if it is determined that the integrity of at least one traffic sign is lower than the preset integrity threshold according to the state of the traffic signal indicated by the scene information, it can be sent to the preset terminal to indicate that the monitoring equipment installed in the monitoring scene is not set up. Reasonable warning information.

For another example, if the state of the traffic signal indicated by the scene information is missing relative to the state of the traffic signal indicated by the traffic signal parameter, the alarm information used to indicate the absence of the traffic signal in the monitoring scene can be sent to the preset terminal, or also The alarm information used to indicate that the traffic signal parameter setting is unreasonable can be sent to the preset terminal.

For another example, if the position of each traffic signal indicated by the scene information is offset from the position of each traffic signal indicated by the traffic signal parameter, it can be sent to the preset terminal to indicate that the monitoring device installed in the monitoring scene is offset. Alarm information.

Regarding the judgment method of the condition for sending the alarm information in the above example, refer to the related description in the embodiment shown in FIG. 2 to FIG. 4, which will not be repeated here.

In some application scenarios, managers may only be interested in part of the events that occur in the monitoring scene. For example, in the process of vehicle violation detection, they may only be interested in violation events. If a picture is captured when there is no event of interest to the user in the monitoring scene, the user cannot obtain the information of interest by reviewing the picture, and a certain labor cost will be incurred for reviewing the picture. Therefore, in order to reduce labor costs, in related technologies, the surveillance system can detect events that occur in the surveillance scene. When a preset event occurs in the surveillance scene, the surveillance scene will be captured to obtain event-related images. The relevant personnel can capture the images. As evidence of the occurrence of a preset event in the monitoring scene for subsequent related processing. Exemplarily, taking the surveillance system as an electronic police as an example, it can detect whether a violation event occurs in the surveillance scene. If a violation event occurs, capture the surveillance scene and obtain the violation images. The management personnel use these images as evidence of vehicle violations. Violating vehicles shall be punished.

The surveillance system consumes certain resources in the process of capturing images, such as bandwidth resources and storage resources. However, for some reasons, the images captured by the surveillance system may not be used as evidence of a preset event in the surveillance scene, which leads to relevant personnel It is not possible to perform follow-up related processing based on the captured image. That is, the resources occupied by the monitoring system are wasted. For example, taking the monitoring system as the electronic police as an example, if there is a construction road in the surveillance scene, and the compaction line of the vehicle due to construction detours, it may be captured by the electronic police, but the captured image cannot be regarded as the vehicle's violation. evidence. On the other hand, the violation images that managers can review per unit time are limited. If there are images that cannot be used as vehicle violation evidence in the violation images, it will result in fewer images that can be used as vehicle violation evidence reviewed by the managers per unit time, that is, It reduces the work efficiency of managers and increases the labor cost of supervision.

Based on this, in a possible embodiment, it may be as shown in FIG. 6, which is a schematic flowchart of another monitoring scene detection method provided by an embodiment of this application, including:

S601: Perform image recognition on the surveillance image of the surveillance scene to obtain scene information of the surveillance scene.

S602: According to the scene information, determine whether there is a traffic signal that does not conform to a preset rule in the monitoring scene.

This step is the same as S102, and you can refer to the foregoing related description of S102.

S603: If there is a traffic signal that does not meet the preset rule in the monitoring scene, it is determined that the monitoring scene is abnormal.

This step is the same as S103, and you can refer to the foregoing related description of S103.

S604: It is forbidden to capture an event associated with the target traffic signal.

Among them, the target traffic signal is a traffic signal that does not meet the preset rules in the monitoring scene. Prohibition of snapshots may refer to the prohibition of snapshots by equipment used to monitor the monitoring place in the surveillance system.

In a possible embodiment, if there is a traffic signal with a completeness lower than a preset completeness threshold in the monitoring scene, then the traffic signal with a completeness lower than the preset threshold is used as the target traffic signal.

In another possible embodiment, if the traffic marking is missing in the monitoring scene, the missing traffic marking may be determined as the target traffic signal.

In yet another possible embodiment, if the signal lamp in the monitoring scene is always on or often dark, the signal lamp may be determined as the target traffic signal.

In another possible embodiment, if the state of the signal light in the image captured by the monitoring device in the monitoring scene is inconsistent with the state information output by the signal light detection device, the signal light may be determined as the target traffic signal.

The fact that an event is associated with a traffic signal may mean that when detecting whether the event occurs in a monitoring scene, it needs to be detected according to the state of the traffic signal.

For example, when detecting whether a red light-breaking event occurs in a monitoring scene, it needs to be detected according to the state of the signal light, so the red-light-breaking event is related to the signal light. If the signal light is the target traffic signal, it is prohibited to capture the red light incident.

For another example, when detecting whether an illegal lane change event occurs in a monitoring scene, it needs to be based on the state of the traffic marking, so the illegal lane change event is related to the traffic marking. If the traffic marking is the target traffic signal, it is prohibited to capture the illegal lane change event.

The prohibition of snapping can be automatically released after a certain period of time, or it can be released after receiving the prohibition release instruction. In a possible embodiment, it is forbidden to capture an event, and it can also be cancelled after it is determined that all traffic signals associated with the event comply with a preset rule. For example, if the red-light-taking event is prohibited because the signal light is the target traffic signal, the red-light-driving event prohibition can be lifted after the signal light meets the preset rules again.

This embodiment can be selected according to the abnormal type of the monitoring scene, corresponding to the prohibition of capturing related events, so as to avoid the inaccuracy of event detection caused by abnormal monitoring of the scene, that is, improving the image captured by the relevant personnel. Possibility, effectively reducing the waste of labor costs.

The following will describe the association relationship between the forbidden capture event and the target traffic signal with a specific example:

For example, if the target traffic signal is a guide sign, such as a left turn sign, it can be forbidden to capture the event of driving without following the guide.

For another example, if the target traffic signal is a traffic marking, it may be prohibited to capture the line pressing and lane change events corresponding to the traffic marking. It is understandable that there may be multiple traffic markings in the monitoring scene. If some of the traffic markings do not comply with the rules, and the other part of the traffic markings comply with the preset rules, it is forbidden to capture the pressure corresponding to that part of the traffic markings. At the same time, continue to capture the line pressing and lane change events corresponding to the other part of the traffic marking. It is also forbidden to capture line pressing and lane change events corresponding to all traffic markings, which is not limited in this embodiment.

For another example, if the target traffic signal is a stop line, it is forbidden to capture the incident of running a red light and driving without following the guidance.

For another example, if the target traffic signal is a semaphore, it is forbidden to capture red light or green light incidents.

The foregoing association relationship is only the association relationship in one possible embodiment. In other possible embodiments, the association relationship can be changed, added or deleted according to user experience or needs, which is not limited in this embodiment.

It is understandable that, although the traffic signals may function to indicate and/or restrict the driving of the vehicle, in some application scenarios, the driving of the vehicle may not comply with these traffic signals and will not violate the regulations. For example, during road construction, one-way lanes may become two-way lanes. For example, at the scene of a traffic accident, when the traffic police evacuates the scene manually, the vehicle can follow the traffic police's instructions instead of observing the signal lights. Therefore, in these scenarios, the traffic signals may not function as expected to indicate and restrict the driving of the vehicle, and it can be considered that these traffic signals are abnormal.

Based on this, in a possible embodiment, as shown in FIG. 7, FIG. 7 is a schematic flowchart of another monitoring scene detection method provided by an embodiment of the application, including:

S701: Perform image recognition on a surveillance image of a surveillance scene to obtain scene information of the surveillance scene.

S702: Determine, according to the location of each traffic signal indicated by the scene information, whether there is a traffic signal located in the area where a preset abnormal event occurs in the monitoring scene.

The preset abnormal event may be different according to different application scenarios. For example, the preset abnormal event may include one or more of construction and traffic accidents, and may also include other events in other possible embodiments. This embodiment does not apply to this. Do restrictions. Exemplarily, if a lane is under construction, the lane is the area where the preset abnormal event occurs, and it can be determined whether there is a traffic signal in the lane in the monitoring scene.

S703: If there is a traffic signal located in the area where the preset abnormal event occurs, it is determined that there is a traffic signal that does not meet the preset rule in the monitoring scene.

In a possible embodiment, the traffic signal in the area where the preset abnormal event occurs can be used as the target traffic signal, and it is forbidden to capture the event associated with the target traffic signal. Still taking the example in the aforementioned S702 as an example, the lane line of the lane under construction may be determined as the target traffic signal, and it is forbidden to capture events associated with the lane line.

Referring to Fig. 8a, Fig. 8a is a schematic structural diagram of a monitoring scene detection device provided by an embodiment of the application, which may include:

The image recognition module 801 is used to perform image recognition on the monitoring image of the monitoring scene to obtain scene information of the monitoring scene, and the scene information is used to indicate the status of each traffic signal in the monitoring scene;

The rule matching module 802 is used to determine whether there is a traffic signal that does not meet the preset rules in the monitoring scene according to the scene information;

The abnormality monitoring module 803 is configured to determine that the monitoring scene is abnormal if there is a traffic signal that does not meet the preset rules in the monitoring scene.

In a possible implementation, the rule matching module 802 is specifically configured to determine whether there are any traffic signals in the monitoring scene whose integrity is lower than a preset integrity threshold according to the status of each traffic signal indicated by the scene information. Traffic signal

If there is a traffic signal whose integrity is lower than the preset integrity threshold, it is determined that there is a traffic signal that does not meet the preset rules in the monitoring scene.

In a possible implementation, the abnormality monitoring module 803 is also used to determine whether the integrity of each traffic signal in the monitoring scene is lower than the preset integrity threshold according to the status of each traffic signal indicated by the scene information After the traffic signal, if the scene information indicates that the integrity of at least one traffic marking is lower than the preset integrity threshold, the alarm information used to indicate the pollution of the traffic marking in the monitoring scene is sent to the preset terminal.

In a possible implementation, the abnormality monitoring module 803 is also used to determine whether the integrity of each traffic signal in the monitoring scene is lower than the preset integrity threshold according to the status of each traffic signal indicated by the scene information After the traffic signal, if the integrity of at least one traffic sign indicated by the scene information is lower than the preset integrity threshold, the alarm information indicating that the monitoring equipment set in the monitoring scene is not properly installed is sent to the preset terminal.

In a possible implementation, the rule matching module 802 is specifically configured to determine whether the state of each traffic signal represented by the scene information is consistent with the state of each traffic signal represented by the traffic signal parameters preset for the monitoring scene;

If the status of each traffic signal indicated by the scene information is inconsistent with the status of each traffic signal indicated by the traffic signal parameters preset for the monitoring scene, it is determined that there are traffic signals in the monitoring scene that do not conform to the preset rules.

In a possible implementation, the rule matching module 802 is specifically configured to determine whether the state of the traffic signal represented by the scene information is missing relative to the state of the traffic signal represented by the traffic signal parameters;

The anomaly detection module 803 is further configured to send to a preset terminal a signal indicating the absence of a traffic signal in the monitoring scene if the state of the traffic signal indicated by the scene information is missing relative to the state of the traffic signal indicated by the traffic signal parameter. Or send to the preset terminal warning information indicating that the traffic signal parameter setting is unreasonable.

In a possible implementation, the rule matching module 802 is specifically used to determine whether the position of each traffic signal indicated by the scene information is offset from the position of each traffic signal indicated by the traffic signal parameter;

The abnormality monitoring module 803 is specifically configured to send to the preset terminal information indicating that the monitoring equipment set in the monitoring scene is offset if the traffic signals indicated by the scene information are offset from the traffic signals indicated by the traffic signal parameters. Alarm information.

In a possible implementation, the device further includes a signal light state acquisition module, which is used to acquire the state information sent by the signal light detector set in the monitoring scene, and the state information is used to indicate the state of each signal light detected by the signal light detector;

The rule matching module 802 is specifically configured to determine whether the state of the signal light indicated by the scene information is consistent with the state of the signal indicated by the state information;

If the state of the signal light indicated by the scene information is inconsistent with the state of the signal indicated by the state information, it is determined that there is a traffic signal that does not conform to the preset rule in the monitoring scene.

In a possible implementation manner, the rule matching module 802 is specifically configured to determine, according to the scene information, whether the duration of the signal lights in the monitoring scene continuously being in the same state exceeds a preset duration threshold;

If the duration of the signal lights in the monitoring scene continuously being in the same state exceeds the preset duration threshold, it is determined that there are traffic signals in the monitoring scene that do not meet the preset rules.

In a possible implementation, as shown in FIG. 8b, the device further includes a monitoring system management module 804, which is used to prohibit capturing events associated with the target traffic signal after determining that the monitoring scene is abnormal, and the target traffic signal is the monitoring scene Traffic signals that do not comply with the preset rules.

In a possible implementation, as shown in FIG. 8c, the device further includes a parameter correction module 805, which is used to determine the state of each traffic signal represented by the scene information and the traffic signal parameters preset for the monitoring scene After the indicated states of the various traffic signals are consistent, if the states of the various traffic signals indicated by the scene information are inconsistent with the states of the various traffic signals indicated by the traffic signal parameters preset for the monitoring scene, according to the scene information of the monitoring scene, Correct the configuration parameters of the monitoring equipment.

In a possible implementation manner, the parameter correction module 805 is specifically configured to generate configuration parameters matching the scene information according to the scene information of the monitoring scene, as the correction configuration parameters;

Change the configuration parameters of the monitoring device to the calibration configuration parameters.

In a possible implementation manner, the rule matching module 802 is specifically configured to determine whether there is a traffic signal in the area where a preset abnormal event occurs in the monitoring scene according to the position of each traffic signal indicated by the scene information;

If there is a traffic signal in the area where the preset abnormal event occurs, it is determined that there is a traffic signal that does not meet the preset rules in the monitoring scene.

An embodiment of the present application also provides an electronic device, as shown in FIG. 9:

The memory 901 is used to store computer programs;

The processor 902 is configured to implement the following steps when executing the program stored in the memory 901:

Perform image recognition on the surveillance images of the surveillance scene to obtain scene information of the surveillance scene, which is used to indicate the status of each traffic signal in the surveillance scene;

According to the scene information, determine whether there is a traffic signal that does not meet the preset rules in the monitoring scene;

If there is a traffic signal that does not meet the preset rules in the monitoring scene, it is determined that the monitoring scene is abnormal.

In a possible implementation manner, determining whether there is a traffic signal that does not comply with preset rules in the monitoring scene according to the scene information includes:

According to the state of each traffic signal indicated by the scene information, determine whether there is a traffic signal with a completeness lower than a preset completeness threshold in each of the traffic signals in the monitoring scene;

In a possible implementation manner, after determining whether there is a traffic signal with a completeness lower than a preset completeness threshold in each traffic signal in the monitoring scene according to the state of each traffic signal indicated by the scene information, the method further includes :

If the scene information indicates that the completeness of at least one traffic marking is lower than the preset completeness threshold, the alarm information used to indicate the pollution of the traffic marking in the monitoring scene is sent to the preset terminal.

If the scene information indicates that the integrity of at least one traffic sign is lower than the preset integrity threshold, the alarm information indicating that the monitoring equipment set in the monitoring scene is not properly installed is sent to the preset terminal.

Determine whether the state of each traffic signal represented by the scene information is consistent with the state of each traffic signal represented by the traffic signal parameters preset for the monitoring scene;

If the state of each traffic signal indicated by the scene information is inconsistent with the state of each traffic signal indicated by the traffic signal parameters preset for the monitoring scene, it is determined that there are traffic signals in the monitoring scene that do not conform to the preset rules.

In a possible implementation manner, determining whether the state of each traffic signal represented by the scene information is consistent with the state of each traffic signal represented by the traffic signal parameters preset for the monitoring scene includes:

Specifically, it is used to determine whether the state of the traffic signal indicated by the scene information is missing relative to the state of the traffic signal indicated by the traffic signal parameter;

The method also includes:

If the state of the traffic signal indicated by the scene information is missing relative to the state of the traffic signal indicated by the traffic signal parameter, send warning information indicating the absence of a traffic signal in the monitoring scene to a preset terminal, or send to the The preset terminal sends alarm information used to indicate that the traffic signal parameter setting is unreasonable.

In a possible implementation manner, determining whether each traffic signal represented by the scene information is consistent with each traffic signal represented by the traffic signal parameters preset for the monitoring scene includes:

Methods also include:

If each traffic signal indicated by the scene information has an offset with respect to each traffic signal indicated by the traffic signal parameter, the alarm information used to indicate that the monitoring device set in the monitoring scene is offset is sent to the preset terminal.

In a possible implementation, the method further includes:

Acquire the status information sent by the signal light detector set in the monitoring scene, and the status information is used to indicate the status of each signal light detected by the signal light detector;

According to the scene information, determine whether there is a traffic signal that does not meet the preset rules in the monitoring scene, including:

Determine whether the state of the signal lamp indicated by the scene information is consistent with the state of the signal indicated by the state information;

According to the scene information, determine whether the duration of the signal lights in the monitoring scene continuously being in the same state exceeds the preset duration threshold;

In a possible implementation, after determining that the monitoring scenario is abnormal, the method further includes:

It is forbidden to capture events related to the target traffic signal. The target traffic signal is a traffic signal that does not meet the preset rules in the monitoring scene.

In a possible implementation, after determining whether the state of each traffic signal represented by the scene information is consistent with the state of each traffic signal represented by the traffic signal parameters preset for the monitoring scene, the method further includes:

If the status of each traffic signal indicated by the scene information is inconsistent with the status of each traffic signal indicated by the traffic signal parameters preset for the monitoring scene, the configuration parameters of the monitoring device are corrected according to the scene information of the monitoring scene.

In a possible implementation, correcting the configuration parameters of the monitoring device according to the scene information of the monitoring scene includes:

According to the scene information of the monitoring scene, generate configuration parameters matching the scene information as correction configuration parameters;

Change the configuration parameters of the monitoring device to calibration configuration parameters.

In a possible implementation manner, according to the scene information, it is determined whether there is a traffic signal that does not meet the preset rules in the monitoring scene, including:

According to the location of each traffic signal indicated by the scene information, determine whether there is a traffic signal in the area where the preset abnormal event occurs in the monitoring scene;

The memory mentioned in the above electronic device may include random access memory (Random Access Memory, RAM), and may also include non-volatile memory (Non-Volatile Memory, NVM), such as at least one disk storage. Optionally, the memory may also be at least one storage device located far away from the foregoing processor.

The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (Network Processor, NP), etc.; it may also be a digital signal processor (Digital Signal Processing, DSP), a dedicated integrated Circuit (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

In yet another embodiment provided in this application, a computer-readable storage medium is also provided. The computer-readable storage medium stores instructions that, when run on a computer, cause the computer to execute any of the above-mentioned embodiments. Monitoring scene detection method.

In another embodiment provided by the present application, there is also provided a computer program product containing instructions, which when run on a computer, causes the computer to execute any monitoring scene detection method in the foregoing embodiments.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, it can be implemented in the form of a computer program product in whole or in part. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, computer, server, or data center. Transmission to another website, computer, server or data center via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrated with one or more available media. The usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)).

It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply one of these entities or operations. There is any such actual relationship or order between. Moreover, the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes those that are not explicitly listed Other elements of, or also include elements inherent to this process, method, article or equipment. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other same elements in the process, method, article, or equipment that includes the element.

The various embodiments in this specification are described in a related manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, electronic equipment, computer-readable storage medium, and computer program product, since they are basically similar to the method embodiments, the description is relatively simple. For related parts, please refer to the part of the description of the method embodiments. .

The above descriptions are only preferred embodiments of this application, and are not intended to limit this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in the protection of this application. Within the range.

Claims

A monitoring scene detection method, characterized in that the method includes:

Performing image recognition on the surveillance image of the surveillance scene to obtain scene information of the surveillance scene, where the scene information is used to indicate the status of each traffic signal in the surveillance scene;

According to the scene information, determine whether there is a traffic signal that does not conform to a preset rule in the monitoring scene;

If there is a traffic signal that does not conform to a preset rule in the monitoring scene, it is determined that the monitoring scene is abnormal.
The method according to claim 1, wherein the determining whether there is a traffic signal that does not conform to a preset rule in the monitoring scene according to the scene information comprises:

According to the state of each traffic signal indicated by the scene information, determine whether there is a traffic signal with a completeness lower than a preset completeness threshold among the various traffic signals in the monitoring scene;

If there is a traffic signal whose integrity is lower than the preset integrity threshold, it is determined that there is a traffic signal that does not comply with the preset rule in the monitoring scene.
The method according to claim 2, characterized in that, in the state of each traffic signal indicated by the scene information, it is determined whether there is a completeness lower than expected in each of the traffic signals in the monitoring scene. After setting the traffic signal of the integrity threshold, the method further includes:

If the scene information indicates that the integrity of at least one traffic marking is lower than the preset integrity threshold, sending warning information indicating that the traffic marking is defaced in the monitoring scene is sent to the preset terminal.
The method according to claim 2, characterized in that, in the state of each traffic signal indicated by the scene information, it is determined whether there is a completeness lower than expected in each of the traffic signals in the monitoring scene. After setting the traffic signal of the integrity threshold, the method further includes:

If the scene information indicates that the integrity of at least one traffic sign is lower than the preset integrity threshold, sending alarm information indicating that the monitoring equipment set in the monitoring scene is not properly installed to the preset terminal.
The method according to claim 1, wherein the determining whether there is a traffic signal that does not conform to a preset rule in the monitoring scene according to the scene information comprises:

Determining whether the state of each traffic signal represented by the scene information is consistent with the state of each traffic signal represented by the traffic signal parameters preset for the monitoring scene;

If the state of each traffic signal indicated by the scene information is inconsistent with the state of each traffic signal indicated by the traffic signal parameter preset for the monitoring scene, it is determined that there is a traffic signal that does not conform to the preset rule in the monitoring scene.
The method according to claim 5, wherein the determining whether the state of each traffic signal represented by the scene information is consistent with the state of each traffic signal represented by the traffic signal parameters preset for the monitoring scene ,include:

Determining whether the state of the traffic signal represented by the scene information is missing relative to the state of the traffic signal represented by the traffic signal parameter;

The method also includes:

If the state of the traffic signal indicated by the scene information is missing relative to the state of the traffic signal indicated by the traffic signal parameter, send warning information indicating the absence of a traffic signal in the monitoring scene to a preset terminal, or send to the The preset terminal sends alarm information used to indicate that the traffic signal parameter setting is unreasonable.
The method according to claim 5, wherein the determining whether each traffic signal represented by the scene information is consistent with each traffic signal represented by a traffic signal parameter preset for the monitoring scene comprises:

Determine whether there is an offset between the position of each traffic signal indicated by the scene information and the position of each traffic signal indicated by the traffic signal parameter;

The method also includes:

If each traffic signal indicated by the scene information has an offset with respect to each traffic signal indicated by the traffic signal parameter, an alarm information used to indicate that the monitoring device installed in the monitoring scene is offset is sent to the preset terminal.
The method according to claim 1, wherein the method further comprises:

Acquiring status information sent by a signal light detector set in the monitoring scene, where the status information is used to indicate the status of each signal light detected by the signal light detector;

The determining, according to the scene information, whether there is a traffic signal that does not conform to a preset rule in the monitoring scene includes:

Determining whether the state of the signal light indicated by the scene information is consistent with the state of the signal indicated by the state information;

If the state of the signal lamp indicated by the scene information is inconsistent with the state of the signal indicated by the state information, it is determined that there is a traffic signal that does not conform to a preset rule in the monitoring scene.
The method according to claim 1, wherein the determining whether there is a traffic signal that does not conform to a preset rule in the monitoring scene according to the scene information comprises:

According to the scene information, determine whether the duration of the signal lights in the monitoring scene continuously being in the same state exceeds a preset duration threshold;

If the duration of the signal lights in the monitoring scene continuously being in the same state exceeds the preset duration threshold, it is determined that there is a traffic signal that does not meet the preset rule in the monitoring scene.
The method according to claim 1, wherein after the determining that the monitoring scene is abnormal, the method further comprises:

It is forbidden to capture an event associated with a target traffic signal, and the target traffic signal is a traffic signal that does not comply with a preset rule in the monitoring scene.
The method according to claim 5, characterized in that in the determining whether the state of each traffic signal indicated by the scene information is different from the state of each traffic signal indicated by the traffic signal parameters preset for the monitoring scene After the agreement, the method further includes:

If the status of each traffic signal represented by the scene information is inconsistent with the status of each traffic signal represented by the traffic signal parameters preset for the monitoring scene, the monitoring equipment is monitored according to the scene information of the monitoring scene. Configure the parameters for correction.
The method according to claim 11, wherein the correcting the configuration parameters of the monitoring device according to the scene information of the monitoring scene comprises:

According to the scene information of the monitoring scene, generating configuration parameters that match the scene information as correction configuration parameters;

The configuration parameter of the monitoring device is changed to the correction configuration parameter.
The method according to claim 1, wherein the determining whether there is a traffic signal that does not conform to a preset rule in the monitoring scene according to the scene information comprises:

According to the location of each traffic signal indicated by the scene information, determine whether there is a traffic signal located in the area where a preset abnormal event occurs in the monitoring scene;

If there is a traffic signal located in the area where the preset abnormal event occurs, it is determined that there is a traffic signal that does not comply with the preset rule in the monitoring scene.
A monitoring scene detection device, characterized in that the device includes:

The image recognition module is configured to perform image recognition on the monitoring image of the monitoring scene to obtain scene information of the monitoring scene, where the scene information is used to indicate the status of each traffic signal in the monitoring scene;

The rule matching module is configured to determine, according to the scene information, whether there is a traffic signal that does not conform to a preset rule in the monitoring scene;

The abnormality monitoring module is configured to determine that the monitoring scene is abnormal if there is a traffic signal that does not conform to a preset rule in the monitoring scene.
The device according to claim 14, wherein the rule matching module is specifically configured to determine whether each traffic signal in the monitoring scene is included in the state of each traffic signal indicated by the scene information. There are traffic signals whose integrity is lower than the preset integrity threshold;

If there is a traffic signal whose integrity is lower than the preset integrity threshold, it is determined that there is a traffic signal that does not comply with the preset rule in the monitoring scene.
The device according to claim 15, wherein the abnormality monitoring module is further configured to determine the state of each traffic signal in the monitoring scene according to the state of each traffic signal indicated by the scene information After whether there is a traffic signal whose integrity is lower than the preset integrity threshold in the signal, if the scene information indicates that the integrity of at least one traffic marking is below the preset integrity threshold, send to the preset terminal to indicate The warning information of traffic marking defacement in the monitoring scene.
The device according to claim 15, wherein the abnormal monitoring module is further configured to determine the respective traffic signals in the monitoring scene according to the state of each traffic signal indicated by the scene information. After the signal has a traffic signal whose integrity is lower than the preset integrity threshold, if the integrity of at least one traffic sign indicated by the scene information is lower than the preset integrity threshold, send to the preset terminal to indicate The monitoring equipment set in the monitoring scene sets up unreasonable alarm information.
The device according to claim 14, wherein the rule matching module is specifically configured to determine the status of each traffic signal represented by the scene information and the traffic signal parameter preset for the monitoring scene. Whether the status of each traffic signal is consistent;

If the state of each traffic signal indicated by the scene information is inconsistent with the state of each traffic signal indicated by the traffic signal parameter preset for the monitoring scene, it is determined that there is a traffic signal that does not conform to the preset rule in the monitoring scene.
The device according to claim 14, wherein the device further comprises a signal light state acquisition module, configured to acquire the state information sent by the signal light detector set in the monitoring scene, and the state information is used to indicate the The status of each signal light detected by the signal light detector;

The rule matching module is specifically configured to determine whether the state of the signal light indicated by the scene information is consistent with the state of the signal indicated by the state information;

If the state of the signal lamp indicated by the scene information is inconsistent with the state of the signal indicated by the state information, it is determined that there is a traffic signal that does not conform to a preset rule in the monitoring scene.
The device according to claim 14, wherein the rule matching module is specifically configured to determine, according to the scene information, whether the duration of the signal lights in the monitoring scene continuously being in the same state exceeds a preset duration threshold;

If the duration of the signal lights in the monitoring scene continuously being in the same state exceeds the preset duration threshold, it is determined that there is a traffic signal that does not meet the preset rule in the monitoring scene.
The device according to claim 14, wherein the device further comprises a monitoring system management module, which is configured to prohibit capturing an event associated with a target traffic signal after the determination of the monitoring scene is abnormal, and the target The traffic signal is a traffic signal that does not meet the preset rules in the monitoring scene.
The device according to claim 18, wherein the device further comprises a parameter correction module, and the parameter correction module is used to determine the status of each traffic signal indicated by the scene information and the monitoring After the state of each traffic signal indicated by the preset traffic signal parameters of the scene is consistent, if the state of each traffic signal indicated by the scene information is different from the state of each traffic signal indicated by the traffic signal parameter preset for the monitoring scene The status of the monitoring device is inconsistent, and the configuration parameters of the monitoring device are corrected according to the scene information of the monitoring scene.
The device according to claim 22, wherein the parameter correction module is specifically configured to generate configuration parameters matching the scene information according to the scene information of the monitoring scene as the correction configuration parameters;

The configuration parameter of the monitoring device is changed to the correction configuration parameter.
The device according to claim 14, wherein the rule matching module is specifically configured to determine whether a preset abnormal event occurs in the monitoring scene according to the position of each traffic signal indicated by the scene information Traffic signals in the area;

If there is a traffic signal located in the area where the preset abnormal event occurs, it is determined that there is a traffic signal that does not comply with the preset rule in the monitoring scene.
An electronic device, characterized in that it comprises:

Memory, used to store computer programs;

The processor is configured to implement the method steps described in any one of claims 1-13 when executing the program stored in the memory.
A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method steps according to any one of claims 1-13 are realized.