CN113052047A

CN113052047A - Traffic incident detection method, road side equipment, cloud control platform and system

Info

Publication number: CN113052047A
Application number: CN202110290137.5A
Authority: CN
Inventors: 董子超; 董洪义; 时一峰
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Apollo Intelligent Connectivity Beijing Technology Co Ltd
Priority date: 2021-03-18
Filing date: 2021-03-18
Publication date: 2021-06-29
Anticipated expiration: 2041-03-18
Also published as: CN113052047B

Abstract

The application discloses a traffic incident detection method, road side equipment, a cloud control platform and a system, and relates to artificial intelligence, automatic driving, intelligent traffic, vehicle and road cooperative sensing and computer vision in computer technology and image processing. The method comprises the following steps: the method comprises the steps of obtaining an image to be detected corresponding to a preset road section, obtaining target pixel information corresponding to each pixel position in the image to be detected, determining a target static object in the image to be detected according to the target pixel information of each pixel position and pre-stored initial pixel information of each pixel position, determining the residence time of the target static object, and determining that a traffic incident exists in the preset road section if the residence time is larger than a preset time threshold value.

Description

Traffic incident detection method, road side equipment, cloud control platform and system

Technical Field

The application relates to computer technology and artificial intelligence, automatic driving, intelligent transportation, vehicle and road cooperative sensing and computer vision in image processing, in particular to a detection method of a traffic incident, road side equipment, a cloud control platform and a system.

Background

In a traffic scenario, traffic events are sometimes occurring. For example, a motor vehicle impacts a pedestrian, a non-motor vehicle collides with a motor vehicle, and so on. To improve the safety of vehicles, pedestrians and the like, traffic events may be detected.

The traditional detection method of the traffic incident is as follows: the method comprises the steps of collecting multi-frame images of a road section in a preset time period, judging the stay time of each vehicle in the multi-frame images according to the multi-frame images, and determining whether a traffic event occurs or not by combining with information of other vehicles, pedestrians and the like around each vehicle.

However, determining whether a traffic event occurs by combining information of other vehicles, pedestrians, and the like may result in more targets to be analyzed, thereby causing problems of higher analysis complexity and lower reliability of false detection.

Disclosure of Invention

The application provides a traffic incident detection method, road side equipment, a cloud control platform and a system for reducing analysis complexity and improving detection reliability.

According to a first aspect of the present application, there is provided a method of detecting a traffic event, comprising:

acquiring an image to be detected corresponding to a preset road section, and acquiring target pixel information corresponding to each pixel position in the image to be detected;

determining a target static object in the image to be detected according to target pixel information of each pixel position and pre-stored initial pixel information of each pixel position, wherein the initial pixel information is obtained by analyzing a plurality of sample images of the preset road section, and the sample images are images of the preset road section in normal traffic;

and determining the stay time of the target static object, and determining that a traffic event exists in the preset road section if the stay time is greater than a preset time threshold.

According to a second aspect of the present application, there is provided a traffic event detection apparatus comprising:

the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring an image to be detected corresponding to a preset road section and acquiring target pixel information corresponding to each pixel position in the image to be detected;

the first determining unit is used for determining a target static object in the image to be detected according to target pixel information of each pixel position and pre-stored initial pixel information of each pixel position, wherein the initial pixel information is obtained by analyzing a plurality of sample images of the preset road section, and the sample images are images of the preset road section in normal traffic;

a second determination unit for determining a dwell time of the target stationary object;

and the third determining unit is used for determining that a traffic event exists in the preset road section if the stay time is greater than a preset time threshold.

According to a third aspect of the present application, there is provided an electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect.

According to a fourth aspect of the present application, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of the first aspect.

According to a fifth aspect of the present application, there is provided a computer program product comprising: a computer program, stored in a readable storage medium, from which at least one processor of an electronic device can read the computer program, execution of the computer program by the at least one processor causing the electronic device to perform the method of the first aspect.

According to a sixth aspect of the present application, there is provided a roadside apparatus including the electronic apparatus according to the third aspect.

According to a seventh aspect of the present application, a cloud control platform is provided, which includes the electronic device according to the third aspect.

According to an eighth aspect of the present application, there is provided a traffic event detection system comprising: a camera, the apparatus of the second aspect, wherein,

the camera is used for collecting an image to be detected corresponding to a preset road section and sending the image to be detected to the device.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:

fig. 1 is a scene diagram of a method for detecting a traffic event, in which an embodiment of the present application may be implemented;

FIG. 2 is a schematic diagram according to a first embodiment of the present application;

FIG. 3 is a schematic diagram according to a second embodiment of the present application;

FIG. 4 is a schematic illustration according to a third embodiment of the present application;

FIG. 5 is a schematic illustration according to a fourth embodiment of the present application;

fig. 6 is a block diagram of an electronic device for implementing a method for detecting a traffic event according to an embodiment of the present application.

Detailed Description

The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a scene diagram of a method for detecting a traffic event according to an embodiment of the present disclosure, as shown in fig. 1, a vehicle 101 travels a road segment 102, at least one side of the road segment 102 may be provided with one or more road side devices 103, and at least one side of the road segment 102 may be further provided with one or more cameras 104.

The camera 104 may perform image acquisition, as shown in fig. 1, the camera 104 may acquire an image of the road segment 102, where the image may include the vehicle 101 traveling on the road segment 102.

The camera 104 may be disposed on the same side as the roadside apparatus 103, or may be disposed on the opposite side of the roadside apparatus 103. And the camera 104 may be connected to the roadside apparatus 103, and may transmit the image collected by it to the roadside apparatus 103.

The roadside device 103 may analyze the image transmitted by the camera 104 to determine whether a traffic event occurred for the road segment 102.

It should be noted that fig. 1 is only used for exemplary illustration, and an application scenario to which the detection method of the traffic incident according to the embodiment may be applied is not to be construed as a limitation to the application scenario of the detection method of the traffic incident according to the embodiment.

For example, the application scenario shown in fig. 1 may further include more vehicles 101, more cameras 104, more roadside devices 103, and the like.

Similarly, the application scenario shown in fig. 1 may further include fewer vehicles 101, fewer roadside devices 103, and the like.

For another example, the application scenario shown in fig. 1 may further include a server connected to the roadside device 103, where the server may be a server, or may also be a cloud server (such as a cloud control platform), and the cloud server may be preferred in consideration of computing resources of the cloud server. And if the application scene comprises the server, the server can analyze the image.

As another example, the application scenario shown in fig. 1 may further include a pedestrian walking on the road segment 102, a bicycle traveling on the road segment 102, and the like.

It should be noted that, in the related art, the detection method of the traffic incident is as follows: the camera 104 collects an image and transmits the collected image to the roadside apparatus 103.

The roadside apparatus 103 determines the time during which each vehicle traveling on the road segment 102 stays during a period of time (e.g., 2 minutes, etc.) based on the images during the period of time, and determines whether a traffic event occurs on the road segment 102 by combining information of surrounding vehicles, pedestrians, etc. of each vehicle.

For example, if the stay time of the vehicle a is 1 minute and the stay time of the other vehicle is between 50 seconds and 55 seconds, the roadside apparatus 103 determines that the traffic event occurs on the road segment 102.

However, with the solution adopted in the above related art, the roadside apparatus 103 needs to analyze a plurality of targets, for example, the staying time of each vehicle and pedestrian in each image needs to be recorded and analyzed, so that the analysis complexity may be large, the consumption of analysis resources may be high, and the accuracy and reliability of the detection result may be low due to the complicated analysis.

In order to avoid at least one of the above technical problems, the inventors of the embodiments of the present application have made creative efforts to obtain the inventive concept of the embodiments of the present application: and determining a static object at the time of detection according to the pixel information of each pixel position at the time of detection and the pixel information of each pixel position at the time of normal traffic, and determining whether a traffic event exists based on the stay time of the static object.

Based on the inventive concept, the application provides a traffic incident detection method, roadside equipment, a cloud control platform and a system, which are applied to computer technology and artificial intelligence, automatic driving, intelligent traffic, vehicle and road cooperative sensing and computer vision in image processing, so as to achieve the technical effects of improving detection efficiency and detection reliability.

Fig. 2 is a schematic diagram of a first embodiment of the present application, and as shown in fig. 2, the method for detecting a traffic event of the present embodiment includes:

s201: and acquiring an image to be detected corresponding to a preset road section, and acquiring target pixel information corresponding to each pixel position in the image to be detected.

For example, the execution subject of this embodiment may be a detection device of a traffic event (hereinafter, referred to as a detection device for short), the detection device may be a server (including a local server and a cloud server, where the server may be a cloud control platform, a vehicle-road cooperative management platform, a central subsystem, an edge computing platform, a cloud computing platform, and the like), may also be a road side device, may also be a terminal device, may also be a processor, may also be a chip, and the like, and this embodiment is not limited. In a system architecture of intelligent transportation vehicle-road cooperation, the road side equipment comprises road side sensing equipment with a computing function and road side computing equipment connected with the road side sensing equipment, the road side sensing equipment (such as a road side camera) is connected to the road side computing equipment (such as a Road Side Computing Unit (RSCU)), the road side computing equipment is connected to a server, and the server can communicate with an automatic driving vehicle or an auxiliary driving vehicle in various modes; or the roadside sensing device comprises a calculation function, and the roadside sensing device is directly connected to the server. The above connections may be wired or wireless.

It should be understood that the preset road section may be any road section, may be a road section including a traffic light, may also be a road section without a traffic light, may be a road section including an intersection, may also be a road section including a t-junction, may also be a road section without an intersection, and the length and width of the road section are not limited in this embodiment.

It should be noted that the image to be detected includes a plurality of pixel positions, and a pixel position may be understood as a position in the image coordinate system corresponding to a physical point in the world coordinate system, and each pixel position corresponds to the target pixel information. For example, the target pixel information may be a pixel value.

S202: and determining a target static object in the image to be detected according to the target pixel information of each pixel position and pre-stored initial pixel information of each pixel position.

The initial pixel information is obtained by analyzing a plurality of sample images of the preset road section, and the sample images are images of the preset road section in normal traffic.

For example, the detection device may obtain a plurality of preset sample images when traffic is normal (i.e., when there is no traffic event, and the traffic event may be understood as an event that vehicles or pedestrians cannot normally pass due to occurrence of the traffic event, such as an event of traffic jam caused by vehicle collision, an event of no passing caused by temporary rush repair of road facilities, and the like), and analyze each sample image, so as to obtain the pixel information (i.e., the initial pixel information) of the first pixel position.

It should be noted that, for a preset link, different images include the same pixel position, but since vehicles, pedestrians, and the like of the preset link have fluidity, the same pixel position may have the same or different pixel information in different images.

In this embodiment, there are introduced: the detection device determines the characteristic of the target static object of the image to be detected by combining the acquired target pixel information corresponding to the detection based on the initial pixel information obtained by analyzing the image in normal traffic, and by the characteristic, the analyzed target (namely, the object in motion state is reduced, so that the object in motion state does not need to be considered and analyzed) can be relatively reduced (relative to the related technology as an example), thereby realizing the technical effects of saving analysis resources, reducing errors caused by analysis by reducing analysis, and further improving the accuracy and reliability of detection.

S203: and determining the stay time of the target static object, and determining that a traffic event exists in a preset road section if the stay time is greater than a preset time threshold.

The time threshold may be set by the detection device based on experience, history, and experiment, and the embodiment is not limited.

This step can be understood as: the detection device can determine the stay time of the target static object, judge the stay time and the time threshold value, and if the stay time is greater than the time threshold value, the detection device can determine that a traffic event exists in the preset road section.

In other embodiments, the detection device may determine that the traffic event does not exist on the predetermined route segment if the detection device determines that the stay time is less than the time threshold.

Based on the above analysis, an embodiment of the present application provides a method for detecting a traffic event, including: acquiring an image to be detected corresponding to a preset road section, acquiring target pixel information corresponding to each pixel position in the image to be detected, determining a target static object in the image to be detected according to the target pixel information of each pixel position and pre-stored initial pixel information of each pixel position, wherein the initial pixel information is obtained by analyzing a plurality of sample images of the preset road section, the sample images are images of the preset road section under normal traffic, determining the stay time of the target static object, and determining that a traffic event exists in the preset road section if the stay time is greater than a preset time threshold value. Therefore, when the initial pixel information corresponds to normal traffic, the pixel information corresponding to each pixel position respectively can be used for efficiently and accurately determining the target static object from the image to be detected based on the initial pixel information and the target pixel information so as to determine whether a traffic event exists according to the residence time and the time threshold of the target static object, the object in a motion state does not need to be analyzed, the defects of more analysis objects, higher analysis cost and higher resource consumption caused by related technologies are avoided, resources are saved, analysis interference caused by more analysis objects can be reduced due to the reduction of the analysis objects, and the technical effects of improving the accuracy and the reliability of detection are achieved.

Fig. 3 is a schematic diagram of a second embodiment of the present application, and as shown in fig. 3, the method for detecting a traffic event of the present embodiment includes:

s301: a plurality of sample images of a preset road section are acquired.

The sample image is an image corresponding to normal traffic.

For example, if the detection party of the traffic event of the present embodiment is applied to the application scenario shown in fig. 1, the step may be understood as: the roadside apparatus may receive a plurality of sample images transmitted by the camera.

For example, the camera may capture each image (which may also be a video) of a preset road segment, and transmit each captured image to the roadside device.

Accordingly, the roadside device may select a plurality of images when the traffic state of the preset road segment is normal as the sample images. The plurality of sample images may be continuous images or discontinuous images, and the embodiment is not limited.

S302: a pixel value is obtained for each sample image at each pixel location.

For example, the roadside apparatus may analyze each sample image to obtain a pixel value corresponding to each pixel position of each sample image.

S303: and aiming at any pixel position, determining initial pixel information of any pixel position according to the pixel value of each sample image at any pixel position.

Wherein the initial pixel information includes a pixel mean and a pixel variance.

For example, the background identification model may be constructed in a background modeling manner, and the background identification model may be a gaussian model, where the gaussian model has certain gaussian distribution information, and the gaussian distribution information includes a pixel mean and a pixel variance corresponding to each pixel.

For example, the roadside apparatus may perform an initialization process on the matrix parameters of the gaussian model. The initialization process may be understood as randomly setting matrix parameters of the gaussian model.

The roadside device may train the gaussian model based on a plurality of sample images (which may be T-frame images in a video), so that the trained gaussian model has a certain gaussian distribution, and the gaussian distribution information includes a pixel mean value and a pixel variance corresponding to each pixel.

Specifically, the training process may be understood as determining the mean of each pixel position, so as to obtain the mean of the pixel position (i.e. the pixel mean), and in turn determining the variance of the pixel position (i.e. the pixel variance). It should be noted that the principle of calculating the pixel mean and the pixel variance can be referred to the calculation principle in the related art, and is not described herein again.

It should be noted that, in this embodiment, the pixel value of the pixel position of each sample image when the traffic is normal is determined, and then the pixel mean value and the pixel variance corresponding to each pixel position are obtained based on the analysis of each pixel value, so that the object in the motion state (such as a vehicle and a pedestrian) is filtered based on the pixel mean value and the pixel variance subsequently to obtain the target stationary object, thereby determining the traffic event, and the accuracy and the reliability of the filtering can be improved, thereby achieving the technical effect of determining the accuracy and the reliability of the traffic event.

S304: and acquiring an image to be detected corresponding to a preset road section, and acquiring target pixel information corresponding to each pixel position in the image to be detected.

Exemplarily, the description about S304 may refer to the description about S201, and is not repeated here.

S305: and determining difference information between the target pixel information and the initial pixel information of each pixel position, and determining the target static object according to the difference information.

Based on the above analysis, the initial pixel information is determined according to normal traffic, and in a normal traffic scene, vehicles, pedestrians and the like are generally in motion, i.e., vehicles and pedestrians, are generally objects in a non-stationary state, in the present embodiment, for each pixel position, target pixel information of the pixel position is compared with initial pixel information, difference information between the two (i.e., the target pixel information and the initial pixel information) is determined, the object in the non-static state (namely, the object in the moving state) and the object in the static state (namely, the target static object) can be determined relatively accurately and efficiently, therefore, analysis of objects in a non-static state is avoided, analysis difficulty is reduced, requirements for analysis resources are reduced, resources are saved, analysis efficiency is improved, and accuracy of analysis results is improved (namely accuracy of detection of traffic incidents is improved).

In some embodiments, the target pixel information includes a target pixel value, and S305 may include the steps of:

step 1: and calculating the difference value between the target pixel value corresponding to each pixel position and the pixel mean value.

Wherein the difference information comprises a difference value.

Step 2: and acquiring pixel positions with difference values larger than the preset pixel threshold value corresponding to each pixel position from each pixel position.

In some embodiments, the pixel threshold is determined based on a pixel variance.

And step 3: and determining the pixel position with the difference value larger than the preset pixel threshold value as a target static object corresponding to the object in the image to be detected.

As can be seen from the above analysis, the initial pixel information includes a pixel mean and a pixel variance, and the initial pixel information is determined based on an image in normal traffic, so that, for any pixel position, if the difference value is smaller, it indicates that the deviation of the target pixel value is smaller, the target pixel value may conform to a gaussian distribution, and the object at the any pixel position may be an object in a moving state, and if the difference value is larger, it indicates that the deviation of the target pixel value is larger, and the target pixel value may not conform to the gaussian distribution, and the object at the any pixel position may be an object in a stationary state, and thus, the object may be determined as a target stationary object.

Specifically, for any pixel position, the roadside device may calculate a difference value between the target pixel value and the pixel mean value, and if the difference value is less than three times the pixel variance, it indicates that the target pixel value has a smaller deviation, and the object at any pixel position is an object in a motion state; on the contrary, if the difference is smaller than the triple pixel variance, it indicates that the target pixel value deviation is large, and the object at any pixel position is an object in a static state (i.e., a target static object).

It should be noted that, in this embodiment, by determining the difference between the target pixel value and the pixel mean value at each pixel position and determining the magnitude relationship between the difference and the pixel threshold (which may be understood as the correlation between the difference and the pixel variance) so as to determine the target stationary object based on the magnitude relationship, the target stationary object can be determined conveniently and quickly.

In some embodiments, the initial pixel information of the corresponding pixel location may be reconstructed based on the pixel values having the difference values greater than the pixel threshold, and as in connection with the above example, the gaussian distribution of the corresponding pixel location may be reconstructed to obtain new pixel mean and pixel variance.

In some embodiments, a difference value smaller than a preset pixel threshold corresponding to each pixel position may be selected from the difference values, and the initial pixel information of each corresponding pixel position may be updated based on the selected difference value.

For example, based on the target pixel mean corresponding to the selected difference, the corresponding pixel mean and pixel variance are updated. With reference to the above example, the embodiment may be understood that the gaussian model may be updated based on the target pixel mean corresponding to the selected difference value to obtain new gaussian analysis information, that is, to obtain a new pixel mean and a new pixel variance.

In the embodiment, the accuracy and reliability of the pixel information can be improved by updating the initial pixel information, so that the technical effects of the reliability and accuracy of the traffic incident detection are improved.

S306: and filtering the target static object according to a preset region of interest.

The interesting area is an area of a non-stop position on a preset road section.

For example, the region of interest may be a region of non-interest, which is divided from a preset road segment based on a requirement, and may be a region serving as a stop position, such as an emergency stop zone, and a region other than the region of non-interest may be a region of interest.

This step can be understood as: the target stationary object may include a vehicle, a pedestrian, and the like in the region of non-interest, and the roadside device may filter the target stationary object in the region of non-interest to obtain the target stationary object in the region of interest.

It should be noted that, in this embodiment, the target stationary object is filtered according to the region of interest, and the target stationary object in the non-region of interest does not need to be analyzed, so that the number of the analyzed objects is reduced, the analysis cost is reduced, the analysis resources are saved, the noise data in the analysis process is avoided, and the accuracy and reliability of the determination of the subsequent traffic event are improved.

S307: and identifying the category of the target static object which is retained after the filtering processing to obtain an identification result.

The recognition result may be a vehicle, a pedestrian, or another obstacle.

In general, a traffic event occurs between a vehicle and a vehicle, and between a vehicle and a pedestrian, and therefore, in the present embodiment, after filtering the target stationary object, the category of the target stationary object that remains after the filtering process is identified, so that when the identification result is a vehicle, a pedestrian, the subsequent operation is performed, thereby improving the reliability of the detection of the traffic event.

S308: if the recognition result is a vehicle and/or a pedestrian, the staying time of the target static object remained after the filtering processing is determined.

In some embodiments, determining the dwell time of the target stationary object retained by the filtering process may include the steps of:

step 1: and determining the attribute information of the target static object retained by the filtering process, and acquiring the attribute information of the pre-stored initial static object.

The road side equipment can obtain a static object (namely an initial static object) by detecting the first frame image, and stores the attribute information of the initial static object.

The attribute information may include a size attribute, a color attribute, a shape attribute, a time attribute, and the like.

Step 2: and if the target static object retained by the filtering process and the initial static object are determined to be the same static object according to the attribute information of the target static object retained by the filtering process and the attribute information of the initial static object, acquiring the static time of the initial static object.

For example, the roadside apparatus may determine whether attribute information corresponding to each of two objects (an initial stationary object, a target stationary object that is retained after the filtering process) is the same, and if the attribute information is the same, it indicates that the two objects are the same object, and may determine the stationary time based on the time attribute of the initial stationary object.

For example, taking the size attribute as an example, the roadside device may determine the size attributes of the two objects respectively, determine whether the size attributes of the two objects are the same, and if the size attributes of the two objects are the same, consider the two objects to be the same object.

Specifically, the roadside apparatus may determine the time of each frame image, and if an initial still object is included in a certain frame image, may determine the stop time of the initial still object as the time of the frame image.

And step 3: and determining the staying time of the target static object remained after the filtering treatment according to the static time.

In connection with the above example, the time of the current frame image may be determined, and the time difference between the time of the current frame image and the still time may be determined as the dwell time.

It should be noted that, in the present embodiment, by determining the staying time of the target still object retained through the filtering process based on the attribute information of the target still object retained through the filtering process and the attribute information of the initial still object, the technical effect of determining the reliability and accuracy of the staying time can be improved.

S309: and if the stay time is greater than the preset time threshold, determining that the traffic incident exists on the preset road section.

For example, regarding the description of S309, reference may be made to the partial description in S203, and details are not described here.

S310: and generating and outputting a prompt message and/or a driving strategy adjustment message.

The prompting message is used for indicating that a traffic event occurs on a preset road section, and the driving strategy adjusting message is used for indicating that the vehicle adjusts the driving strategy based on the driving strategy adjusting message.

With reference to the above example and the application scenario shown in fig. 1, when the roadside device determines that a traffic event exists, in an example, the roadside device may generate a prompt message, and transmit the prompt message to a vehicle having a connection relationship with the roadside device, so as to notify the vehicle of the occurrence of the traffic event on a preset road segment, so that the vehicle may make a corresponding driving strategy adjustment, such as adjusting a route, based on the prompt message, so as to avoid driving on the preset road segment; in another example, the roadside device may generate a driving strategy adjustment message and may transmit the driving strategy adjustment message to a vehicle having a connection relationship with the roadside device, so that the vehicle adjusts a driving strategy, such as re-planning a route, based on the driving strategy adjustment message.

It should be noted that the technical effects of safety and reliability of vehicle driving can be improved by generating and outputting the prompt message and/or the driving strategy adjustment information.

Fig. 4 is a schematic diagram of a traffic event detection device 400 according to a third embodiment of the present application, as shown in fig. 4, and the traffic event detection device 400 includes:

the first obtaining unit 401 is configured to obtain an image to be detected corresponding to a preset road segment, and obtain target pixel information corresponding to each pixel position in the image to be detected.

The first determining unit 402 is configured to determine a target stationary object in an image to be detected according to target pixel information of each pixel position and pre-stored initial pixel information of each pixel position, where the initial pixel information is obtained by analyzing a plurality of sample images of a preset road section, and the sample images are images of the preset road section in normal traffic.

A second determination unit 403 for determining the dwell time of the target stationary object.

A third determining unit 404, configured to determine that a traffic event exists on the preset road segment if the staying time is greater than the preset time threshold.

Fig. 5 is a schematic diagram of a fourth embodiment of the present application, and as shown in fig. 5, the traffic event detection apparatus 500 of the present embodiment includes:

the second obtaining unit 501 is configured to obtain a plurality of sample images of a preset road segment, where the sample images are images corresponding to normal traffic.

A third obtaining unit 502 is configured to obtain a pixel value of each sample image at each pixel position.

A fourth determining unit 503, configured to determine, for any pixel position, initial pixel information of any pixel position according to a pixel value of each sample image at the any pixel position.

The first obtaining unit 504 is configured to obtain an image to be detected corresponding to a preset road segment, and obtain target pixel information corresponding to each pixel position in the image to be detected.

The first determining unit 505 is configured to determine a target stationary object in an image to be detected according to target pixel information of each pixel position and pre-stored initial pixel information of each pixel position, where the initial pixel information is obtained by analyzing a plurality of sample images of a preset road section, and the sample images are images of the preset road section in normal traffic.

As can be appreciated in conjunction with fig. 5, in some embodiments, the target pixel information includes a target pixel value and the initial pixel information includes a pixel mean value; the first determination unit 505 includes:

a calculating subunit 5051 is configured to calculate a difference between the target pixel value corresponding to each pixel position and the pixel mean, where the difference information includes the difference.

A first obtaining sub-unit 5052 is configured to obtain, from the pixel positions, pixel positions having a difference larger than a preset pixel threshold value corresponding to each pixel position.

A first determining sub-unit 5053 is configured to determine that the pixel position where the difference is greater than the pixel threshold corresponds to the object in the image to be detected, as a target still object.

An updating sub-unit 5054 is configured to select, from the difference values, a difference value smaller than the respective corresponding pixel threshold of each pixel position, and update the initial pixel information of the respective corresponding pixel position based on the selected difference value.

The filtering unit 506 is configured to perform filtering processing on the target stationary object according to a preset region of interest, where the region of interest is a region of a non-stop position on the preset road segment.

The identification unit 507 is configured to identify a category of the target stationary object to obtain an identification result, and if the identification result is a vehicle and/or a pedestrian, determine a staying time of the target stationary object.

A second determining unit 508 for determining the dwell time of the target stationary object.

As can be seen in conjunction with fig. 5, in some embodiments, the second determining unit 508 includes:

a second determining sub-unit 5081 for determining attribute information of the target stationary object.

A second obtaining sub-unit 5082, configured to obtain pre-stored attribute information of the initial still object.

A third obtaining sub-unit 5083, configured to obtain the still time of the initial still object if it is determined that the target still object and the initial still object are the same still object according to the attribute information of the target still object and the attribute information of the initial still object.

A third determining subunit 5084, configured to determine a dwell time of the target stationary object according to the stationary time.

A third determining unit 509, configured to determine that a traffic event exists in the preset road segment if the staying time is greater than the preset time threshold.

A generating unit 510, configured to generate a prompt message and/or a driving strategy adjustment message, where the prompt message is used to indicate that the traffic event occurs on the preset road segment, and the driving strategy adjustment message is used to indicate that a vehicle adjusts a driving strategy based on the driving strategy adjustment message.

An output unit 511, configured to output a prompt message and/or a driving strategy adjustment message.

According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.

There is also provided, in accordance with an embodiment of the present application, a computer program product, including: a computer program, stored in a readable storage medium, from which at least one processor of the electronic device can read the computer program, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any of the embodiments described above.

FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 601 performs the respective methods and processes described above, such as the detection method of a traffic event. For example, in some embodiments, the method of detecting traffic events may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the above-described method of detecting traffic events may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured by any other suitable means (e.g., by means of firmware) to perform the detection method of the traffic event.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.

According to another aspect of the embodiments of the present application, there is also provided a roadside apparatus including the electronic apparatus as described in the embodiments above.

According to another aspect of the embodiment of the present application, an embodiment of the present application further provides a cloud control platform, including the electronic device described in the above embodiment.

According to another aspect of the embodiments of the present application, there is also provided a system for detecting a traffic event, including: the camera is used for collecting an image to be detected corresponding to a preset road section and sending the image to be detected to the device.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.

The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of detecting a traffic event, comprising:

2. The method according to claim 1, wherein determining the target still object in the image to be detected according to the target pixel information of each pixel position and the pre-stored initial pixel information of each pixel position comprises:

and determining difference information between the target pixel information and the initial pixel information of each pixel position, and determining the target static object according to the difference information.

3. The method of claim 2, wherein the target pixel information comprises a target pixel value, the initial pixel information comprises a pixel mean; determining difference information between target pixel information and initial pixel information of each pixel position, and determining the target static object according to the difference information, comprising:

calculating a difference value between a target pixel value corresponding to each pixel position and a pixel mean value, wherein the difference information comprises the difference value;

acquiring pixel positions with difference values larger than the preset pixel threshold value corresponding to each pixel position from each pixel position;

and determining the pixel position with the difference value larger than the pixel threshold value to correspond to the object in the image to be detected as the target static object.

4. The method of claim 3, wherein initial pixel information further comprises a pixel variance, the pixel threshold determined based on the pixel variance.

5. The method according to any one of claims 1 to 4, wherein before acquiring the image to be detected corresponding to the preset road segment, further comprising:

acquiring a plurality of sample images of the preset road section, wherein the sample images are images corresponding to normal traffic;

acquiring a pixel value of each sample image at each pixel position;

and aiming at any pixel position, determining initial pixel information of the any pixel position according to the pixel value of each sample image at the any pixel position.

6. The method of any of claims 1 to 4, wherein prior to determining the dwell time of the target stationary object, further comprising:

and filtering the target static object according to a preset region of interest, wherein the region of interest is a region of a non-stop position on the preset road section.

7. The method of any of claims 1 to 4, further comprising:

and identifying the type of the target static object to obtain an identification result, and if the identification result is a vehicle and/or a pedestrian, determining the stay time of the target static object.

8. The method of claim 3, wherein after calculating the difference between the target pixel value and the pixel mean value for each pixel position, further comprising:

and selecting a difference value smaller than the pixel threshold value corresponding to each pixel position from the difference values, and updating the initial pixel information of each corresponding pixel position based on the selected difference value.

9. The method of any of claims 1 to 4, wherein determining a dwell time of the target stationary object comprises:

determining the attribute information of the target static object, and acquiring the attribute information of a pre-stored initial static object;

if the target static object and the initial static object are determined to be the same static object according to the attribute information of the target static object and the attribute information of the initial static object, acquiring the static time of the initial static object;

and determining the dwell time of the target static object according to the static time.

10. The method of any of claims 1-4, further comprising, after determining that a traffic event exists for the preset road segment:

and generating and outputting a prompt message and/or a driving strategy adjusting message, wherein the prompt message is used for indicating the preset road section to have the traffic event, and the driving strategy adjusting message is used for indicating a vehicle to adjust the driving strategy based on the driving strategy adjusting message.

11. A traffic event detection device, comprising:

12. The apparatus according to claim 11, wherein the first determining unit is configured to determine difference information between target pixel information and initial pixel information for each pixel position, and determine the target stationary object according to the respective difference information.

13. The apparatus of claim 12, wherein the target pixel information comprises a target pixel value, the initial pixel information comprises a pixel mean; determining difference information between target pixel information and initial pixel information for each pixel position, the first determining unit including:

the calculating subunit is used for calculating a difference value between a target pixel value corresponding to each pixel position and a pixel mean value, wherein the difference information comprises the difference value;

the first obtaining subunit is used for obtaining pixel positions with difference values larger than the preset pixel threshold value corresponding to each pixel position from each pixel position;

and the first determining subunit is used for determining the pixel position with the difference value larger than the pixel threshold value as the target static object corresponding to the object in the image to be detected.

14. The apparatus of claim 13, wherein initial pixel information further comprises a pixel variance, the pixel threshold determined based on the pixel variance.

15. The apparatus of any of claims 11 to 14, further comprising:

the second acquisition unit is used for acquiring a plurality of sample images of the preset road section, wherein the sample images are images corresponding to normal traffic;

a third obtaining unit, configured to obtain a pixel value at each pixel position of each sample image;

and a fourth determining unit, configured to determine, for any pixel position, initial pixel information of the any pixel position according to a pixel value of each of the sample images at the any pixel position.

16. The apparatus of any of claims 11 to 14, further comprising:

and the filtering unit is used for filtering the target static object according to a preset region of interest, wherein the region of interest is a region of a non-stop position on the preset road section.

17. The apparatus of any of claims 11 to 14, further comprising:

and the identification unit is used for identifying the type of the target static object to obtain an identification result, and if the identification result is a vehicle and/or a pedestrian, determining the staying time of the target static object.

18. The apparatus of claim 13, wherein the first determining unit further comprises:

and the updating subunit is used for selecting the difference value smaller than the pixel threshold value corresponding to each pixel position from the difference values and updating the initial pixel information of the corresponding pixel position based on the selected difference value.

19. The apparatus according to any one of claims 11 to 14, wherein the second determining unit includes:

a second determining subunit, configured to determine attribute information of the target stationary object;

the second acquisition subunit is used for acquiring the attribute information of the pre-stored initial static object;

a third obtaining subunit, configured to obtain a stationary time of the initial stationary object if it is determined that the target stationary object and the initial stationary object are the same stationary object according to the attribute information of the target stationary object and the attribute information of the initial stationary object;

and the third determining subunit is used for determining the dwell time of the target static object according to the static time.

20. The apparatus of any of claims 11 to 14, further comprising, after determining that a traffic event exists for the preset road segment:

21. An electronic device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-10.

22. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-10.

23. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-10.

24. A roadside apparatus comprising the electronic apparatus of claim 21.

25. A cloud controlled platform comprising the electronic device of claim 21.

26. A system for detecting a traffic event, comprising: a camera, the apparatus of any one of claims 11 to 20,