Target traffic event identification method, device, equipment and medium

Abstract

This disclosure provides a method, apparatus, device, and medium for identifying target traffic events, relating to the field of artificial intelligence technology, and particularly to the fields of intelligent transportation and autonomous driving. The implementation scheme includes: acquiring a first image captured by a first camera device; identifying a first target event in the first image; determining at least one second image region among multiple first image regions based on a first identification region; in response to at least one third image region having an event confidence level within the at least one second image region, determining the confidence level of the first target event based on the event confidence level of each third image region within the at least one third image region; and in response to the confidence level being greater than or equal to a confidence level threshold, identifying the first target event as the identification result.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to the fields of intelligent transportation and autonomous driving, specifically to a method, apparatus, electronic device, computer-readable storage medium, and computer program product for identifying target traffic events. Background Technology

[0002] Artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies mainly include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0003] With the rapid development of society, the field of intelligent transportation is advancing rapidly. Major cities are using various cameras to monitor traffic and determine whether vehicles are engaging in illegal activities. This involves using algorithms and other analytical methods to extract information such as vehicles, people, and lanes from massive amounts of surveillance video, generating various violation reports, and then pushing them to relevant traffic departments for processing.

[0004] The methods described in this section are not necessarily methods that had been previously conceived or adopted. Unless otherwise specified, no method described in this section should be assumed to be prior art simply because it is included in this section. Similarly, unless otherwise specified, the issues mentioned in this section should not be considered to be accepted in any prior art. Summary of the Invention

[0005] This disclosure provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for identifying target traffic incidents.

[0006] According to one aspect of this disclosure, a method for identifying a target traffic event is provided, comprising: acquiring a first image captured by a first camera device, the image captured by the first camera device including a plurality of first screen regions; identifying a first target event in the first image, the first target event being located in a first identification region in the first image; determining at least one second screen region among the plurality of first screen regions based on the first identification region, wherein each second screen region in the at least one second screen region satisfies the first preset condition; in response to the at least one second screen region including at least one third screen region having an event confidence level, determining the confidence level of the first target event based on the event confidence level of each third screen region in the at least one third screen region; and in response to the confidence level being greater than or equal to a confidence level threshold, determining the first target event as an identification result.

[0007] According to another aspect of this disclosure, a target traffic event recognition device is provided, comprising: a first acquisition unit configured to acquire a first image captured by a first camera device, the image captured by the first camera device including a plurality of first screen regions; a first recognition unit configured to recognize a first target event in the first image, the first target event being located in a first recognition region in the first image; a first determination unit configured to determine at least one second screen region among the plurality of first screen regions based on the first recognition region, wherein each second screen region in the at least one second screen region satisfies a first preset condition; a second determination unit configured to determine a confidence level of the first target event based on the event confidence level of each third screen region in the at least one second screen region in response to the at least one second screen region including at least one third screen region having an event confidence level; and a third determination unit configured to determine the first target event as a recognition result in response to the confidence level being greater than or equal to a confidence level threshold.

[0008] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the aforementioned target traffic event identification method.

[0009] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to perform the aforementioned target traffic event identification method.

[0010] According to another aspect of this disclosure, a computer program product is provided, including a computer program, wherein the computer program, when executed by a processor, implements the aforementioned target traffic event identification method.

[0011] According to another aspect of this disclosure, an edge computing device is provided, including the aforementioned electronic device.

[0012] According to one or more embodiments of this disclosure, the accuracy of the result feedback for target traffic event identification can be improved.

[0013] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0014] The accompanying drawings exemplify embodiments and form part of the specification, serving together with the textual description to explain exemplary implementations of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0015] Figure 1 A schematic diagram of an exemplary system in which the various methods described herein may be implemented according to embodiments of the present disclosure is shown;

[0016] Figure 2 A flowchart of a target traffic incident identification method according to an embodiment of the present disclosure is shown;

[0017] Figure 3 A flowchart of a first operation according to an embodiment of the present disclosure is shown;

[0018] Figure 4 A flowchart of a target traffic incident identification method according to an exemplary embodiment of the present disclosure is shown;

[0019] Figure 5 A structural block diagram of a target traffic incident identification device according to an embodiment of the present disclosure is shown;

[0020] Figure 6 A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0021] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0022] In this disclosure, unless otherwise stated, the use of terms such as "first," "second," etc., to describe various elements is not intended to limit the positional, temporal, or importance relationships of these elements; such terms are merely used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of that element, while in other cases, based on the context, they may refer to different instances.

[0023] The terminology used in the description of the various examples described in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context explicitly indicates otherwise, an element may be one or more unless the number of elements is specifically limited. Furthermore, the term "and / or" as used in this disclosure covers any one of the listed items and all possible combinations thereof.

[0024] In related technologies, in scenarios where target traffic events are identified based on two-dimensional video streams, the relevant identification algorithms suffer from a large number of misidentifications in actual use. Furthermore, in traffic scenarios, the identification of target traffic events is characterized by low commonality and strong individual differences. Optimizing the algorithm itself has little effect, can only improve the overall accuracy to a limited extent, and requires a large amount of computing resources and labor costs.

[0025] The embodiments of this disclosure provide a method for identifying target traffic events. First, the image of a first camera device is divided into multiple first image regions. After obtaining the target event identification result based on the image captured by the first camera device, at least one second image region that meets a first preset condition (e.g., the overlap between the identification region and the image region is greater than a preset threshold) is determined from the multiple first image regions based on the identification region of the identification result. The confidence level of the identification result is comprehensively determined based on the event confidence information of different regions included in at least one second image region. The confidence level of the first target event is judged based on the confidence level, thereby filtering out first target events with low confidence levels and only feeding back the first target events with confidence levels greater than or equal to the confidence level threshold as identification results to the user, thereby improving the accuracy of the target traffic event identification result feedback.

[0026] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0027] Figure 1 A schematic diagram of an exemplary system 100 in which the various methods and apparatus described herein can be implemented according to embodiments of this disclosure is shown. Reference Figure 1 The system 100 includes a motor vehicle 110, a server 120, and one or more communication networks 130 that couple the motor vehicle 110 to the server 120.

[0028] In embodiments of this disclosure, the motor vehicle 110 may include a computing device according to embodiments of this disclosure and / or be configured to perform a method according to embodiments of this disclosure.

[0029] Server 120 may run one or more services or software applications that enable methods for identifying target traffic events. In some embodiments, server 120 may also provide other services or software applications, which may include non-virtual environments and virtual environments. Figure 1 In the configuration shown, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or combinations thereof that can be executed by one or more processors. A user of motor vehicle 110 may sequentially interact with server 120 using one or more client applications to utilize the services provided by these components. It should be understood that various different system configurations are possible and may differ from system 100. Therefore, Figure 1 This is an example of a system used to implement the various methods described herein, and is not intended to be limiting.

[0030] Server 120 may include one or more general-purpose computers, special-purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running a virtual operating system, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that can be virtualized to maintain virtual storage devices for servers). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0031] The computing unit in server 120 can run one or more operating systems, including any of the aforementioned operating systems and any commercially available server operating system. Server 120 can also run any of a variety of additional server applications and / or middleware applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0032] In some implementations, server 120 may include one or more applications to analyze and merge data feeds and / or event updates received from vehicle 110. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of vehicle 110.

[0033] Network 130 can be any type of network well known to those skilled in the art, and can support data communication using any of a variety of available protocols (including, but not limited to, TCP / IP, SNA, IPX, etc.). By way of example only, one or more networks 110 can be satellite communication networks, local area networks (LANs), Ethernet-based networks, token ring networks, wide area networks (WANs), the Internet, virtual networks, virtual private networks (VPNs), intranets, extranets, blockchain networks, public switched telephone networks (PSTNs), infrared networks, wireless networks (including, for example, Bluetooth, WiFi), and / or any combination of these with other networks.

[0034] System 100 may also include one or more databases 150. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 150 may be used to store information such as audio files and video files. The data repository 150 may reside in various locations. For example, a data repository used by server 120 may be local to server 120, or it may be located away from server 120 and may communicate with server 120 via a network-based or dedicated connection. The data repository 150 may be of different types. In some embodiments, the data repository used by server 120 may be a database, such as a relational database. One or more of these databases may store, update, and retrieve data from and from the database in response to commands.

[0035] In some embodiments, one or more of the databases 150 may also be used by an application to store application data. The databases used by the application may be of different types, such as key-value stores, object stores, or regular stores supported by a file system.

[0036] Motor vehicle 110 may include sensors 111 for sensing the surrounding environment. Sensors 111 may include one or more of the following sensors: a visual camera, an infrared camera, an ultrasonic sensor, a millimeter-wave radar, and a lidar (LiDAR). Different sensors can provide different detection accuracy and range. Cameras may be mounted in front of, behind, or at other locations on the vehicle. Visual cameras can capture the situation inside and outside the vehicle in real time and present it to the driver and / or passengers. In addition, by analyzing the images captured by the visual cameras, information such as traffic light indications, intersection conditions, and the operating status of other vehicles can be obtained. Infrared cameras can capture objects in night vision conditions. Ultrasonic sensors may be mounted around the vehicle to measure the distance of objects outside the vehicle using the strong directionality of ultrasound. Millimeter-wave radar may be mounted in front of, behind, or at other locations on the vehicle to measure the distance of objects outside the vehicle using the characteristics of electromagnetic waves. LiDAR may be mounted in front of, behind, or at other locations on the vehicle to detect the edges and shape information of objects, thereby performing object recognition and tracking. Due to the Doppler effect, the radar device can also measure the speed changes of the vehicle and moving objects.

[0037] The motor vehicle 110 may also include a communication device 112. The communication device 112 may include a satellite positioning module capable of receiving satellite positioning signals (e.g., BeiDou, GPS, GLONASS, and GALILEO) from satellite 141 and generating coordinates based on these signals. The communication device 112 may also include a module for communicating with a mobile communication base station 142. The mobile communication network can implement any suitable communication technology, such as current or emerging wireless communication technologies (e.g., 5G technology) like GSM / GPRS, CDMA, and LTE. The communication device 112 may also have a vehicle-to-everything (V2X) module, configured to enable vehicle-to-the-world communication, for example, vehicle-to-vehicle (V2V) communication with other vehicles 143 and vehicle-to-infrastructure (V2I) communication with infrastructure 144. Furthermore, the communication device 112 may also have a module configured to communicate with a user terminal 145 (including but not limited to smartphones, tablets, or wearable devices such as watches) via, for example, a wireless local area network conforming to the IEEE 802.11 standard or Bluetooth. Using the communication device 112, the motor vehicle 110 can also access the server 120 via the network 130.

[0038] The motor vehicle 110 may also include a control unit 113. The control unit 113 may include a processor, such as a central processing unit (CPU) or a graphics processing unit (GPU), or other dedicated processors, that communicates with various types of computer-readable storage devices or media. The control unit 113 may include an autonomous driving system for automatically controlling various actuators in the vehicle. The autonomous driving system is configured to control the powertrain, steering system, and braking system of the motor vehicle 110 (not shown) via multiple actuators in response to inputs from multiple sensors 111 or other input devices to control acceleration, steering, and braking respectively, without human intervention or with limited human intervention. Some processing functions of the control unit 113 can be implemented via cloud computing. For example, some processing can be performed using an onboard processor while other processing can be performed using cloud computing resources. The control unit 113 may be configured to perform methods according to this disclosure. Furthermore, the control unit 113 may be implemented as an example of a computing device on the motor vehicle side (client) according to this disclosure.

[0039] Figure 1 The system 100 can be configured and operated in various ways to enable the application of the various methods and apparatus described in this disclosure.

[0040] According to some embodiments, such as Figure 2 As shown, a method for identifying target traffic events is provided, including:

[0041] Step S201: Acquire a first image captured by the first camera device, wherein the image captured by the first camera device includes multiple first screen areas;

[0042] Step S202: Identify a first target event in the first image, wherein the first target event is located in a first identification area in the first image;

[0043] Step S203: Based on the first recognition area, determine at least one second screen area among multiple first screen areas, wherein each second screen area in the at least one second screen area satisfies a first preset condition;

[0044] Step S204: In response to at least one second screen area including at least one third screen area with event confidence, determine the confidence level of the first target event based on the event confidence level of each third screen area in the at least one third screen area; and

[0045] Step S205: In response to a confidence level greater than or equal to a confidence threshold, the first target event is determined as the recognition result.

[0046] According to embodiments of this disclosure, the image of the first camera device is first divided into multiple first image regions. When a first target event is identified based on the image captured by the first camera device, at least one second image region that meets a first preset condition (e.g., the overlap between the identification region and the image region is greater than a preset threshold) is determined in the multiple first image regions through the first identification region of the first target event. Based on the event confidence information of different regions included in at least one second image region, the confidence of the identification result is comprehensively determined. The confidence of the first target event is judged based on the confidence, thereby filtering out first target events with low confidence and only feeding back the first target events with confidence greater than or equal to the confidence threshold as identification results to the user, thus improving the accuracy of the result feedback of target traffic event identification.

[0047] In some embodiments, the first camera device described above may be a camera device deployed with a target traffic event recognition algorithm. Target traffic event recognition may include, for example, traffic accident recognition, debris recognition, and traffic violation recognition.

[0048] The image captured by each camera device is essentially fixed. In some embodiments, the image from each camera device can be divided into multiple first image regions.

[0049] In some embodiments, the plurality of first screen areas may be a plurality of rectangular areas of equal size.

[0050] In some embodiments, the area of ​​each first frame region can be determined based on the size of the area occupied by the vehicle in the image that the camera device can capture.

[0051] In some embodiments, the area of ​​each first frame region can be 1.4 to 1.6 times the area occupied by the vehicle in the image that the camera device can capture.

[0052] In some embodiments, the area of ​​each first frame region can be 1.5 times the area occupied by the vehicle in the image that the camera device can capture.

[0053] In some embodiments, one or more of the multiple first screen areas may have a corresponding event confidence level for each first screen area.

[0054] In some embodiments, after a first image is captured based on a first camera device and a first target event is identified based on the first image, at least one second screen area associated with the first target event can be determined in multiple first screen areas based on the area where the event occurs in the first image (i.e., the first identification area, for example, a detection box).

[0055] Each second screen region satisfies a first preset condition. In some embodiments, the first preset condition may be that the overlap between the first recognition region and the second screen region in the second screen region is greater than an overlap threshold.

[0056] In some embodiments, the overlap threshold may be, for example, 60%.

[0057] In some embodiments, when determining at least one second screen region, the overlap between the first recognition region and each first screen region may be determined first, and the multiple first screen regions may be sorted based on the overlap. In this case, the first preset condition may be that the overlap of the second screen region ranks in the top N (N is a positive integer). For example, at least one screen region is the three screen regions with the highest overlap with the second recognition region among the multiple first screen regions.

[0058] In some embodiments, after determining the at least one second screen area, it can be determined whether each second screen area has event confidence information. In response to the fact that at least one second screen area includes at least one third screen area with event confidence information, the confidence of the first target event can be determined based on the event confidence of each of the at least one third screen areas.

[0059] In some embodiments, the confidence level of the first target event may be, for example, the minimum value among the confidence levels of at least one event in the at least one third screen area.

[0060] In some embodiments, the confidence level of the first target event may be, for example, the average confidence level of at least one event in the at least one third screen area.

[0061] In some embodiments, when the confidence level of the first target event is greater than or equal to the confidence level threshold, it can be considered that the identification of the event is accurate, and the first target event can be fed back to the user as the identification result.

[0062] In some embodiments, when each of the at least one second screen area lacks event confidence information, the first target event can be directly fed back to the user as the recognition result. Simultaneously, verification information of the recognition result fed back by the user is obtained, and the event confidence of the corresponding screen area is determined and updated based on historical recognition data, historical result verification data, and one or more of the recognition result and verification information.

[0063] In some embodiments, the event confidence is determined by performing a first operation, which includes: when a fourth screen region among a plurality of first screen regions does not have an event confidence, in response to recognizing a second target event based on a second image, and the overlap between the second recognition region corresponding to the second target event and the fourth screen region is greater than a first overlap threshold, determining an initial confidence of the fourth screen region as the event confidence of the fourth screen region, wherein the second image is acquired based on a first camera device, the second recognition region is located in the second image, and the initial confidence is determined based on historical recognition data and historical result verification data of the first camera device.

[0064] In some embodiments, when a fourth screen area among a plurality of first screen areas does not have event confidence information, when the fourth screen area is first associated with a target event (such as a second target event) (that is, the overlap between the second identification area corresponding to the second target event and the fourth screen area is greater than a first overlap threshold, wherein the first overlap threshold is, for example, 60%), the initial confidence of the fourth screen area can be determined first based on the historical identification data and historical result verification data of the device, and temporarily used as the event confidence of the area.

[0065] Therefore, by initializing the event confidence of the image area that lacks confidence information based on the historical recognition data and historical result verification data of the camera device prior to the deployment of the method disclosed herein, the event confidence of the image area can be efficiently determined even when there is not enough recognition result data for the image area, thereby improving the accuracy of the result feedback of target traffic event recognition based on the confidence level.

[0066] In some embodiments, historical identification data may include at least one target event identification result of the first camera device before the deployment of the method disclosed herein, and historical result verification data may include at least one result verification information of the first camera device for at least one target event identification result before the deployment of the method disclosed herein, wherein each result verification information indicates whether the target event identification result is correctly identified.

[0067] Determining the initial confidence level of the fourth image area based on the historical recognition data and historical result verification data of the first camera device may include determining the historical recognition accuracy based on the historical recognition data and historical result verification data, and determining the historical recognition accuracy as the initial confidence level.

[0068] In some embodiments, the first operation may further include: when a fifth screen region among a plurality of first screen regions has an event confidence level, in response to the recognition of a third target event based on a third image, and the overlap between the third recognition region corresponding to the third target event and the fifth screen region being greater than a second overlap threshold, updating the event confidence level corresponding to the fifth screen region based on the third target event and the result verification information of the third target event, wherein the third image is acquired based on the first camera device, the third recognition region is located in the third image, and the result verification information indicates whether the recognition of the third target event is correct.

[0069] In some embodiments, when a certain fifth screen region among a plurality of first screen regions has event confidence information (which may be the initial confidence or the event confidence obtained in the previous update), in response to the existence of a third target event in the fifth screen region, the overlap between the third identification region corresponding to the third target event and the fifth screen region is first calculated. When the overlap between the third identification region corresponding to the third target event and the fifth screen region is greater than a second overlap threshold, an update operation for the event confidence of the fifth screen region is triggered.

[0070] The second overlap threshold can be different from or the same as the first overlap threshold.

[0071] Since the recognition accuracy of different camera devices changes over time, by updating the confidence of the image area with confidence information, the confidence can be continuously updated, thereby improving the accuracy and timeliness of the confidence and improving the accuracy of the feedback results of target traffic event recognition.

[0072] In some embodiments, updating the event confidence level corresponding to the fifth screen area based on the third target event and the result verification information of the third target event includes: updating the historical recognition accuracy and the first recognition accuracy within a preset time range corresponding to the fifth screen area based on the third target event and the result verification information; and updating the event confidence level corresponding to the fifth screen area based on the updated historical recognition accuracy and the updated first recognition accuracy.

[0073] In some embodiments, the preset time range can be the most recent week of the current update.

[0074] Therefore, by simultaneously updating the overall historical accuracy and the recognition accuracy within a preset time range (such as within the past week), and thus updating the event confidence level in the area, the timeliness of the confidence level can be further improved, thereby enhancing the accuracy of the result feedback for target traffic event recognition.

[0075] In some embodiments, updating the event confidence level corresponding to the fifth screen area based on the updated historical recognition accuracy and the updated first recognition accuracy includes: updating the event confidence level corresponding to the fifth screen area based on the updated historical recognition accuracy, the updated first recognition accuracy, and a first parameter, wherein the first parameter is used to adjust the degree of influence of the updated first recognition accuracy on the event confidence level corresponding to the fifth screen area.

[0076] Therefore, by setting the first parameter, the weights of historical recognition accuracy and first recognition accuracy are adjusted, thereby adjusting the impact of scenario timeliness on confidence, thus achieving a more applicable and accurate confidence level for different scenarios.

[0077] In some embodiments, the event confidence score can be updated based on the following event confidence score calculation formula:

[0078]

[0079] Wherein, D represents the event confidence level of the fifth screen area, p1 represents the historical recognition accuracy of the fifth screen area, which can be determined based on the event recognition results and corresponding result verification information recorded by the first camera device in the fifth screen area after the method of this disclosure is deployed. p2 represents the first recognition accuracy of the fifth screen area within a preset time range (such as within the past week), which can be determined based on the event recognition results and corresponding result verification information within the fifth screen area within the preset time range. x represents an adjustable first parameter used to adjust the influence of historical recognition accuracy and first recognition accuracy on the event confidence level.

[0080] In some embodiments, x can be 1.2, which indicates that the confidence level of the event is more affected by the accuracy of the first identification and has stronger timeliness.

[0081] In some embodiments, the target traffic event identification method may further include: responding to a first camera device meeting a second preset condition, obtaining a second camera device based on first image feature matching of an image captured by the first camera device, to establish an association between the first camera device and the second camera device, wherein the second preset condition includes at least one sixth image region among a plurality of first image regions corresponding to the first camera device, the update number of the event confidence corresponding to each sixth image region in the at least one sixth image region is greater than a first preset number, the similarity between the second image features and the first image features of the image captured by the second camera device is greater than a preset similarity threshold, and the update number of the event confidence of each image region of the second camera device is less than or equal to the second preset number; and determining the event confidence of a seventh image region of the second camera device corresponding to the sixth image region based on the event confidence corresponding to each sixth image region in the at least one sixth image region corresponding to the first camera device.

[0082] In some embodiments, each camera device that has been deployed with the target event recognition algorithm can be recorded in a relational graph database. In the graph database, data points are established based on each camera device. The ID of each camera device is used as the data point label of that camera device, and the image features of that camera device and the event confidence of each image area are used as point attributes.

[0083] In some embodiments, the image features of each camera device can be the feature vector of a frame of image obtained by an image feature algorithm.

[0084] In some embodiments, when any online camera device meets the second preset condition (the first camera device includes at least one sixth screen area in the multiple first screen areas, and the update number of the event confidence corresponding to each sixth screen area in the at least one sixth screen area is greater than the first preset number, wherein the first preset number can be, for example, 10 times), the camera device can match and traverse the first screen features in its graph database attributes to obtain a list of all camera devices that do not meet the above conditions (that is, the update number of the event confidence of each screen area of ​​the camera device is less than or equal to the second preset number) and whose screen feature similarity is greater than a preset similarity threshold (for example, 80%). All camera devices in the list are identified as associated devices of the current camera device. At the same time, a relationship edge can be established for the data point of the camera device and each associated device data point in the graph database, and the event confidence corresponding to each sixth screen area in the camera device is shared as a lineage confidence with the associated devices.

[0085] In some embodiments, the second preset condition may also include multiple sixth screen areas among the multiple first screen areas, and the number of times the event confidence corresponding to each sixth screen area in the multiple sixth screen areas is updated is greater than the first preset number, wherein the first preset number may be, for example, 10 times.

[0086] Therefore, when the first camera device meets the second preset condition, it can match other strongly correlated but not yet accurately determined confidence levels based on the image characteristics of the first camera device, thereby achieving efficient sharing of confidence levels and improving the accuracy of confidence levels of correlated devices.

[0087] In some embodiments, the target traffic event identification method may further include: when the second camera device and the first camera device are associated, in response to the second camera device meeting a third preset condition, canceling the association relationship, wherein the third preset condition includes the second camera device having a target event identification count greater than a third preset count; and for each of the at least one eighth screen area, re-determining the event confidence level of the eighth screen area based on the identification result of each target event identification corresponding to the eighth screen area and the corresponding result verification information.

[0088] In some embodiments, when the aforementioned associated device meets a third preset condition (that is, the number of target events identified in at least one eighth screen area of ​​the camera device is greater than a third preset number, wherein the third preset number can be 10 times), the association relationship can be cancelled, and the event confidence of each eighth screen area of ​​the device can be re-determined based on the aforementioned event confidence calculation formula.

[0089] Therefore, once the associated device meets the third preset condition, the association can be terminated, and its own data can be used to update the confidence level, thereby improving the accuracy and timeliness of the confidence level of each device.

[0090] In some embodiments, the target traffic event can be a trajectory-determination type traffic event. Trajectory-determination type traffic events may include, for example, reversing events, wrong-way driving events, etc. In this case, such as... Figure 3 As shown, the first operation may also include:

[0091] Step S301: Before determining the event confidence level of the ninth screen area among multiple first screen areas, determine the vehicle type involved in the target traffic event;

[0092] Step S302: In response to the fact that the ninth screen area does not have an event confidence level corresponding to the vehicle model, based on the historical recognition data and historical result verification data corresponding to the vehicle model of the first camera device, determine the initial confidence level of the ninth screen area corresponding to the vehicle model, as the event confidence level of the ninth screen area corresponding to the vehicle model; and

[0093] Step S303: In response to the fact that the ninth screen area has an event confidence level corresponding to the vehicle model, update the event confidence level corresponding to the vehicle model in the ninth screen area based on the target traffic event and the corresponding result verification information.

[0094] In some embodiments, the event confidence scores for different vehicle models in each frame area can be maintained in the graph database for each camera device, and the event confidence scores for each vehicle model can be updated separately based on the data of the corresponding vehicle model.

[0095] In some embodiments, for trajectory-based traffic events (such as reversing events and driving in the wrong direction events), since the accuracy of identifying this type of event varies greatly among different vehicle models, confidence scores can be calculated and updated separately for different vehicle models (large, medium, small, etc.) to further improve the accuracy of the identification results.

[0096] Figure 4 A flowchart of a target traffic incident identification method according to an exemplary embodiment of the present disclosure is shown.

[0097] In some exemplary embodiments, such as Figure 4 As shown, the target traffic event identification method may include:

[0098] Step S401: For the current camera device, in response to the recognition of a new target event, determine whether to initiate event confidence judgment;

[0099] Step S402: In response to the current camera device meeting the preset conditions (the current camera device includes at least one screen area whose event confidence has been updated more than N times (N is a positive integer, for example, it can be 10), or the current camera device is associated with a corresponding camera device and shares the event confidence of that camera device), start the event confidence judgment and obtain the confidence of the current target event;

[0100] Step S403: Based on the confidence level of the current target event, feedback of corresponding result information, including: responding to the current target event having a confidence level greater than or equal to a preset confidence level, feeding the target event back to the user as an identification result; responding to the current target event having a confidence level less than a preset confidence level, filtering the target event so as not to feed it back to the user, or feeding the target event back to the user along with a low confidence level prompt.

[0101] Step S404: In response to the fact that the current camera device does not meet the above preset conditions, the event confidence judgment is not initiated, the target event is directly fed back to the user, and the user's feedback information (result verification information) is obtained.

[0102] Step S405: Based on the target event and its result verification information, update the event confidence of the corresponding screen area of ​​the current camera device.

[0103] In some embodiments, such as Figure 5 As shown, a target traffic incident identification device 500 is provided, comprising:

[0104] The first acquisition unit 510 is configured to acquire a first image captured by a first camera device, the image captured by the first camera device including multiple first screen areas;

[0105] The first recognition unit 520 is configured to recognize a first target event in a first image, wherein the first target event is located in a first recognition area of ​​the first image;

[0106] The first determining unit 530 is configured to determine at least one second screen region among a plurality of first screen regions based on a first identification region, wherein each second screen region in the at least one second screen region satisfies a first preset condition.

[0107] The second determining unit 540 is configured to, in response to at least one second screen region including at least one third screen region having an event confidence level, determine the confidence level of the first target event based on the event confidence level of each third screen region in the at least one third screen region; and

[0108] The third determining unit 550 is configured to determine the first target event as the recognition result in response to a confidence level greater than or equal to a confidence level threshold.

[0109] According to embodiments of this disclosure, the image of the first camera device is first divided into multiple first image regions. When a first target event is identified based on the image captured by the first camera device, at least one second image region that meets a first preset condition (e.g., the overlap between the identification region and the image region is greater than a preset threshold) is determined in the multiple first image regions through the first identification region of the first target event. The confidence level of the identification result is comprehensively determined based on the event confidence information of different regions included in at least one second image region. The confidence level of the first target event is judged based on the confidence level, thereby filtering out first target events with low confidence levels and only feeding back first target events with confidence levels greater than or equal to the confidence threshold as identification results to the user, thereby improving the accuracy of the result feedback of target traffic event identification.

[0110] In some embodiments, the target traffic event recognition device may further include: a fourth determining unit configured to determine event confidence by performing a first operation. The fourth determining unit includes: a first determining subunit configured to, in the case that a fourth screen region among a plurality of first screen regions does not have event confidence, in response to recognizing a second target event based on a second image, and the overlap between the second recognition region corresponding to the second target event and the fourth screen region is greater than a first overlap threshold, determine an initial confidence of the fourth screen region as the event confidence of the fourth screen region. The second image is acquired based on a first camera device, the second recognition region is located in the second image, and the initial confidence is determined based on historical recognition data and historical result verification data of the first camera device.

[0111] In some embodiments, the fourth determining unit may further include: a first updating subunit, configured to, when a fifth screen region among a plurality of first screen regions has an event confidence level, respond to the recognition of a third target event based on a third image, and the overlap between the third recognition region corresponding to the third target event and the fifth screen region is greater than a second overlap threshold, update the event confidence level corresponding to the fifth screen region based on the third target event and the result verification information of the third target event, wherein the third image is acquired based on the first camera device, the third recognition region is located in the third image, and the result verification information indicates whether the recognition of the third target event is correct.

[0112] In some embodiments, the first updating subunit may be further configured to: update the historical recognition accuracy and the first recognition accuracy within a preset time range corresponding to the fifth screen area based on the third target event and the result verification information; and update the event confidence level corresponding to the fifth screen area based on the updated historical recognition accuracy and the updated first recognition accuracy.

[0113] In some embodiments, updating the event confidence level corresponding to the fifth screen area based on the updated historical recognition accuracy and the updated first recognition accuracy includes: updating the event confidence level corresponding to the fifth screen area based on the updated historical recognition accuracy, the updated first recognition accuracy, and a first parameter, wherein the first parameter is used to adjust the degree of influence of the updated first recognition accuracy on the event confidence level corresponding to the fifth screen area.

[0114] In some embodiments, the target traffic event recognition device may further include: a matching unit configured to, in response to a first camera device meeting a second preset condition, obtain a second camera device based on first image features of an image captured by the first camera device, thereby establishing an association between the first camera device and the second camera device, wherein the second preset condition includes at least one sixth image region among a plurality of first image regions corresponding to the first camera device, the update number of the event confidence corresponding to each sixth image region in the at least one sixth image region is greater than a first preset number, the similarity between the second image features and the first image features of the image captured by the second camera device is greater than a preset similarity threshold, and the update number of the event confidence of each image region of the second camera device is less than or equal to the second preset number; and a fifth determining unit configured to, based on the event confidence corresponding to each sixth image region in the at least one sixth image region corresponding to the first camera device, determine the event confidence of a seventh image region of the second camera device corresponding to the sixth image region.

[0115] In some embodiments, the target traffic event recognition device may further include: a cancellation unit configured to cancel the association relationship when the second camera device and the first camera device are associated, in response to the second camera device meeting a third preset condition, wherein the third preset condition includes the number of target event recognitions in at least one eighth screen area of ​​the second camera device being greater than a third preset number; and a sixth determination unit configured to, for each eighth screen area of ​​at least one eighth screen area, re-determine the event confidence level of the eighth screen area based on the recognition result of each target event recognition corresponding to the eighth screen area and the corresponding result verification information.

[0116] In some embodiments, the target traffic event is a trajectory-determining traffic event, and the fourth determining unit may further include: a second determining subunit configured to determine the vehicle type involved in the target traffic event before determining the event confidence level of the ninth screen area among a plurality of first screen areas; a third determining subunit configured to, in response to the ninth screen area not having an event confidence level corresponding to the vehicle type, determine the initial confidence level of the ninth screen area corresponding to the vehicle type based on the historical recognition data and historical result verification data corresponding to the vehicle type of the first camera device, as the event confidence level of the ninth screen area corresponding to the vehicle type; and a second updating subunit configured to, in response to the ninth screen area having an event confidence level corresponding to the vehicle type, update the event confidence level of the ninth screen area corresponding to the vehicle type based on the target traffic event and the corresponding result verification information.

[0117] According to embodiments of this disclosure, an electronic device, a readable storage medium, and a computer program product are also provided.

[0118] According to another aspect of this disclosure, an edge computing device is also provided. Optionally, in addition to electronic devices, the edge computing device may also include communication components, etc. The electronic devices and communication components can be integrated or separately configured. The electronic devices can acquire data from roadside sensing devices (such as roadside cameras), such as images and videos, thereby performing image and video processing and data calculations, and then transmitting the processing and calculation results to the cloud control platform via the communication components.

[0119] Optionally, the edge computing device can also be a Road Side Computing Unit (RSCU). Alternatively, the electronic device itself can also have the functions of acquiring and communicating sensing data, such as an AI camera. The electronic device can directly perform image and video processing and data calculation based on the acquired sensing data, and then transmit the processing and calculation results to the cloud control platform.

[0120] Optionally, the cloud control platform performs processing in the cloud, including image and video processing and data calculation. The cloud control platform can also be called a vehicle-road cooperative management platform, V2X platform, cloud computing platform, central system, cloud server, etc.

[0121] refer to Figure 6 The present invention describes a structural block diagram of an electronic device 600 that can serve as a server or client of the present disclosure, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0122] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on 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. The RAM 603 may also store various programs and data required for the operation of the electronic device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0123] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606, output unit 607, storage unit 608, and communication unit 609. Input unit 606 can be any type of device capable of inputting information to electronic device 600. Input unit 606 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of electronic device, and can include, but is not limited to, a mouse, keyboard, touchscreen, trackpad, trackball, joystick, microphone, and / or remote control. Output unit 607 can be any type of device capable of presenting information, and can include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 608 can include, but is not limited to, a hard disk and an optical disk. Communication unit 609 allows electronic device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and can include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth devices, 602.11 devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0124] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with 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 special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the target traffic event recognition method of this disclosure. For example, in some embodiments, the target traffic event recognition method of this disclosure can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 600 via ROM 602 and / or 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 target traffic event recognition method described above can be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the target traffic event identification method of this disclosure by any other suitable means (e.g., by means of firmware).

[0125] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0126] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0127] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0128] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the 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 can be received in any form (including sound input, voice input, or tactile input).

[0129] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0130] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0131] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0132] While embodiments or examples of this disclosure have been described with reference to the accompanying drawings, it should be understood that the methods, systems, and devices described above are merely exemplary embodiments or examples, and the scope of the invention is not limited by these embodiments or examples, but only by the granted claims and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. Furthermore, the steps may be performed in a different order than that described in this disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, as the technology evolves, many elements described herein can be replaced by equivalents that appear after this disclosure.

Claims

1. A method for identifying target traffic events, comprising: Acquire a first image captured by a first camera device, wherein the image captured by the first camera device includes multiple first screen areas; Identify a first target event in the first image, wherein the first target event is located in a first identification region of the first image; Based on the first recognition region, at least one second image region is determined among multiple first image regions in the first image, wherein the overlap between each second image region and the first recognition region satisfies a first preset condition. In response to the at least one second screen area including at least one third screen area with event confidence, the confidence level of the first target event is determined based on the event confidence level of each third screen area in the at least one third screen area, wherein the event confidence level is determined based on historical recognition data and historical result verification data of the first camera device; and In response to the confidence level being greater than or equal to the confidence threshold, the first target event is determined as the identification result.

2. The method of claim 1, wherein, The event confidence level is determined by performing a first operation, the first operation including: If the fourth image region among the plurality of first image regions lacks event confidence, in response to the identification of a second target event based on the second image, and the overlap between the second identification region corresponding to the second target event and the fourth image region is greater than a first overlap threshold, An initial confidence level is determined for the fourth image region as the event confidence level of the fourth image region, wherein the second image is acquired based on the first camera device, the second recognition region is located in the second image, and the initial confidence level is determined based on the historical recognition data and historical result verification data of the first camera device.

3. The method of claim 2, wherein, The first operation also includes: If the fifth image region among the plurality of first image regions has an event confidence level, in response to the recognition of a third target event based on the third image, and the overlap between the third recognition region corresponding to the third target event and the fifth image region is greater than a second overlap threshold, Based on the third target event and the result verification information of the third target event, the event confidence level corresponding to the fifth screen area is updated, wherein the third image is acquired based on the first camera device, the third recognition area is located in the third image, and the result verification information indicates whether the recognition of the third target event is correct.

4. The method of claim 3, wherein, The process of updating the event confidence level corresponding to the fifth screen area based on the third target event and the result verification information of the third target event includes: Based on the third target event and the result verification information, update the historical recognition accuracy and the first recognition accuracy within a preset time range corresponding to the fifth screen area; and Based on the updated historical recognition accuracy and the updated first recognition accuracy, the event confidence level corresponding to the fifth screen area is updated.

5. The method of claim 4, wherein, The process of updating the event confidence level corresponding to the fifth screen region based on the updated historical recognition accuracy and the updated first recognition accuracy includes: Based on the updated historical recognition accuracy, the updated first recognition accuracy, and the first parameter, the event confidence level corresponding to the fifth screen area is updated. The first parameter is used to adjust the degree of influence of the updated first recognition accuracy on the event confidence level corresponding to the fifth screen area.

6. The method according to claim 2, further comprising: In response to the first camera device meeting a second preset condition, a second camera device is obtained based on the first image feature matching of the image captured by the first camera device, thereby establishing an association between the first camera device and the second camera device. The second preset condition includes that the plurality of first image regions corresponding to the first camera device include at least one sixth image region, the update count of the event confidence corresponding to each of the at least one sixth image region is greater than a first preset count, the similarity between the second image feature and the first image feature of the image captured by the second camera device is greater than a preset similarity threshold, and the update count of the event confidence of each image region of the second camera device is less than or equal to the second preset count; and Based on the event confidence level of each sixth frame region corresponding to the at least one sixth frame region corresponding to the first camera device, the event confidence level of the seventh frame region corresponding to the sixth frame region of the second camera device is determined.

7. The method of claim 6, further comprising: When the second camera device and the first camera device have the aforementioned association relationship, in response to the second camera device meeting a third preset condition, the association relationship is cancelled, wherein the third preset condition includes the second camera device having a target event recognition count greater than a third preset number in at least one eighth frame region; and For each of the at least one eighth screen regions, the event confidence level of the eighth screen region is re-determined based on the recognition result of each target event recognition corresponding to the eighth screen region and the corresponding result verification information.

8. The method according to any one of claims 2 to 7, wherein the target traffic event is a trajectory-determining traffic event, and the first operation further includes: Before determining the event confidence level of the ninth screen area among the plurality of first screen areas, the vehicle type involved in the target traffic event is determined; In response to the fact that the ninth screen area does not have an event confidence level corresponding to the vehicle model, based on the historical recognition data and historical result verification data of the first camera device corresponding to the vehicle model, the initial confidence level of the ninth screen area corresponding to the vehicle model is determined as the event confidence level of the ninth screen area corresponding to the vehicle model; as well as In response to the fact that the ninth screen area has an event confidence level corresponding to the vehicle model, the event confidence level of the ninth screen area corresponding to the vehicle model is updated based on the target traffic event and the corresponding result verification information.

9. A target traffic incident identification device, comprising: The first acquisition unit is configured to acquire a first image captured by a first camera device, wherein the image captured by the first camera device includes multiple first screen areas; The first recognition unit is configured to recognize a first target event in the first image, wherein the first target event is located in a first recognition region of the first image; The first determining unit is configured to determine at least one second image region in a plurality of first image regions in the first image based on the first recognition region, wherein the overlap between each second image region in the at least one second image region and the first recognition region satisfies a first preset condition. The second determining unit is configured to, in response to the at least one second screen region including at least one third screen region with event confidence, determine the confidence level of the first target event based on the event confidence level of each third screen region in the at least one third screen region, wherein the event confidence level is determined based on historical recognition data and historical result verification data of the first camera device; and The third determining unit is configured to determine the first target event as the identification result in response to the confidence level being greater than or equal to the confidence level threshold.

10. The apparatus according to claim 9, further comprising: A fourth determining unit, configured to determine the confidence level of the event by performing a first operation, the fourth determining unit comprising: The first determining subunit is configured to, in the case that the fourth screen region among the plurality of first screen regions does not have event confidence, respond to the recognition of a second target event based on the second image, and the overlap between the second recognition region corresponding to the second target event and the fourth screen region is greater than a first overlap threshold, determine the initial confidence of the fourth screen region as the event confidence of the fourth screen region, wherein the second image is acquired based on the first camera device, the second recognition region is located in the second image, and the initial confidence is determined based on the historical recognition data and historical result verification data of the first camera device.

11. The apparatus according to claim 10, wherein the fourth determining unit further comprises: The first update subunit is configured to, when the fifth screen region among the plurality of first screen regions has an event confidence level, respond to the recognition of a third target event based on a third image, and the overlap between the third recognition region corresponding to the third target event and the fifth screen region is greater than a second overlap threshold, update the event confidence level corresponding to the fifth screen region based on the third target event and the result verification information of the third target event, wherein the third image is acquired based on the first camera device, the third recognition region is located in the third image, and the result verification information indicates whether the recognition of the third target event is correct.

12. The apparatus of claim 11, wherein, The first update subunit is further configured as follows: Based on the third target event and the result verification information, update the historical recognition accuracy and the first recognition accuracy within a preset time range corresponding to the fifth screen area; as well as Based on the updated historical recognition accuracy and the updated first recognition accuracy, the event confidence level corresponding to the fifth screen area is updated.

13. The apparatus of claim 12, wherein, The process of updating the event confidence level corresponding to the fifth screen region based on the updated historical recognition accuracy and the updated first recognition accuracy includes: Based on the updated historical recognition accuracy, the updated first recognition accuracy, and the first parameter, the event confidence level corresponding to the fifth screen area is updated. The first parameter is used to adjust the degree of influence of the updated first recognition accuracy on the event confidence level corresponding to the fifth screen area.

14. The apparatus of claim 10, further comprising: A matching unit is configured to, in response to the first camera device meeting a second preset condition, obtain a second camera device based on first image features of the image captured by the first camera device, thereby establishing an association between the first camera device and the second camera device. The second preset condition includes that the plurality of first image regions corresponding to the first camera device include at least one sixth image region, the update count of the event confidence corresponding to each of the at least one sixth image region is greater than a first preset count, the similarity between the second image features of the image captured by the second camera device and the first image features is greater than a preset similarity threshold, and the update count of the event confidence of each image region of the second camera device is less than or equal to the second preset count. The fifth determining unit is configured to determine the event confidence of the seventh screen area of ​​the second camera device corresponding to the sixth screen area based on the event confidence of each sixth screen area corresponding to the first camera device.

15. The apparatus of claim 14, further comprising: The cancellation unit is configured to, when the second camera device and the first camera device have the aforementioned association relationship, cancel the association relationship in response to the second camera device meeting a third preset condition, wherein the third preset condition includes that the number of target event recognitions in at least one eighth frame region of the second camera device is greater than a third preset number; and The sixth determining unit is configured to, for each of the at least one eighth screen area, re-determine the event confidence level of the eighth screen area based on the recognition result of each target event recognition corresponding to the eighth screen area and the corresponding result verification information.

16. The apparatus according to any one of claims 10 to 15, wherein the target traffic event is a trajectory-determining traffic event, and the fourth determining unit further comprises: The second determining subunit is configured to determine the vehicle type involved in the target traffic event before determining the event confidence level of the ninth screen area among the plurality of first screen areas; The third determining subunit is configured to, in response to the fact that the ninth screen area does not have an event confidence level corresponding to the vehicle model, determine the initial confidence level of the ninth screen area corresponding to the vehicle model based on the historical recognition data and historical result verification data of the first camera device corresponding to the vehicle model, so as to serve as the event confidence level of the ninth screen area corresponding to the vehicle model; as well as The second update subunit is configured to update the event confidence level of the ninth screen area corresponding to the vehicle model in response to the ninth screen area having an event confidence level corresponding to the vehicle model, based on the target traffic event and the corresponding result verification information.

17. An electronic device comprising: At least one processor; as well as A memory that is communicatively connected to the at least one processor; in The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-8.

19. A computer program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the method of any one of claims 1-8.

20. An edge computing device, comprising the electronic device of claim 17.

Images