Abnormal state detection method for vehicle, electronic device, and storage medium

Abstract

This application provides a method, electronic device, and storage medium for detecting abnormal vehicle conditions. The method for detecting abnormal vehicle conditions includes: acquiring image information of the surrounding environment of the main vehicle; determining at least one processing end of the image information based on the complexity of the surrounding environment; the processing end identifying surrounding vehicles in the surrounding environment based on the image information, and identifying the abnormal condition type of an abnormal vehicle among the surrounding vehicles based on the image information; and in response to determining the abnormal condition type of the abnormal vehicle, the processing end sending an alert to the abnormal vehicle.

Description

Technical Field

[0001] The embodiments of this application relate to the technical field of vehicle anomaly detection, specifically to a method for detecting abnormal vehicle conditions, an electronic device, and a storage medium. Background Technology

[0002] When a vehicle malfunctions (such as internal or external abnormalities), its own onboard computer cannot detect these anomalies. It relies on drivers of surrounding vehicles to proactively alert the vehicle (e.g., by honking or flashing their horns). However, this method of alerting is highly dependent on the drivers of surrounding vehicles. If they fail to notice the anomaly or notice it but fail to alert the driver in a timely manner, the vehicle may pose a safety hazard and compromise road safety. Summary of the Invention

[0003] The embodiments of this application provide a method, electronic device, and storage medium for detecting abnormal conditions of a vehicle that at least partially solves one or more of the problems mentioned above or other problems in the prior art.

[0004] One embodiment of this application provides a method for detecting abnormal states of a vehicle. The method includes: acquiring image information of the surrounding environment of the main vehicle; determining at least one processing end of the image information based on the complexity of the surrounding environment; the processing end identifying surrounding vehicles in the surrounding environment based on the image information, and identifying the abnormal state type of an abnormal state vehicle among the surrounding vehicles based on the image information; and in response to determining the abnormal state type of the abnormal state vehicle, the processing end sending a reminder to the abnormal state vehicle.

[0005] In some implementations, the complexity of the surrounding environment includes at least one of weather recognition complexity, road condition recognition complexity, lighting condition recognition complexity, main vehicle speed recognition complexity, building distribution recognition complexity, and surrounding vehicle recognition complexity; wherein, the influencing factors of the surrounding vehicle recognition complexity include at least one of the external features of the surrounding vehicles, the driving speed of the surrounding vehicles, and the background environment of the surrounding vehicles.

[0006] In some implementations, the processing end includes the vehicle's first in-vehicle terminal and / or cloud service terminal.

[0007] In some implementations, identifying the abnormal state type of an abnormal vehicle among surrounding vehicles based on image information includes: determining whether an abnormal vehicle exists among surrounding vehicles based on image information; and in response to determining that an abnormal vehicle exists among surrounding vehicles, identifying the license plate number and abnormal state type of the abnormal vehicle based on image information, wherein the image information is detected by image sensors located at different positions on the main vehicle.

[0008] In some implementations, determining whether there are vehicles in an abnormal state among the surrounding vehicles based on image information includes: filtering out target image information containing surrounding vehicles from the image information; and determining whether there are vehicles in an abnormal state among the surrounding vehicles based on the target image information.

[0009] In some implementations, identifying the license plate number and abnormal state type of a vehicle in an abnormal state based on image information includes: filtering out abnormal image information of vehicles in an abnormal state from target image information; and identifying the license plate number and abnormal state type of a vehicle in an abnormal state based on the abnormal image information, wherein the abnormal state type includes external abnormal state type and internal abnormal state type.

[0010] In some implementations, identifying the license plate number and abnormal state type of a vehicle in an abnormal state based on abnormal image information includes: identifying the license plate number of a vehicle in an abnormal state based on abnormal image information; and determining the abnormal state type of the vehicle in an abnormal state based on abnormal image information, license plate number, and a preset standard vehicle image library. The abnormal state type includes external abnormal state type. The standard vehicle image library includes preset license plate numbers and standard image information corresponding to the preset license plate numbers.

[0011] In some implementations, identifying the abnormal state type of a vehicle based on abnormal image information includes: determining the exhaust color of the vehicle based on the exhaust image in the abnormal image information; and determining the abnormal state type of the vehicle based on the exhaust color and a preset exhaust color anomaly database. The abnormal state type includes internal abnormal state types, wherein the exhaust color anomaly database includes preset exhaust colors and preset abnormal state types corresponding to the preset exhaust colors.

[0012] In some implementations, determining the exhaust color of a vehicle in an abnormal state based on an exhaust image of abnormal image information includes: acquiring the grayscale value of the exhaust image and determining the exhaust color of the vehicle in an abnormal state based on the grayscale value of the exhaust image.

[0013] In some implementations, identifying the license plate number and abnormal state type of a vehicle in an abnormal state based on image information includes: filtering abnormal image information of vehicles in an abnormal state from image information; identifying the license plate number of the vehicle in an abnormal state based on the abnormal image information, wherein abnormal image information of the vehicle in an abnormal state corresponding to the same license plate number from different perspectives within a preset time period constitutes an abnormal image information pool of the vehicle in an abnormal state; and identifying the abnormal state type of the vehicle in an abnormal state based on the abnormal image information pool; wherein abnormal image information of the same vehicle in an abnormal state from different perspectives is detected by image sensors at different locations of the same main vehicle, and / or, abnormal image information of the same vehicle in an abnormal state from different perspectives is detected by image sensors of different main vehicles.

[0014] In some implementations, the processing terminal is the first vehicle-mounted terminal of the main vehicle. The processing terminal sends an alert to a vehicle in an abnormal state by: the first vehicle-mounted terminal sending the license plate number and abnormal state type of the abnormal vehicle to the cloud server, so that the cloud server sends an alert to the abnormal vehicle based on the license plate number, which at least includes the abnormal state type.

[0015] In some implementations, the processing end includes a cloud server. The processing end sending alerts to vehicles in abnormal states includes: the cloud server sending an alert to the vehicle in abnormal state based on the vehicle's license plate number, which at least includes the type of abnormal state.

[0016] In some implementations, the cloud server sends an alert to the vehicle in an abnormal state based on the vehicle's license plate number, which includes at least the type of abnormal state. This includes: the cloud server identifying the vehicle's IoT card based on the license plate number; and the cloud server sending an alert to the vehicle in an abnormal state via the IoT card, which includes at least the type of abnormal state and image information corresponding to the vehicle in an abnormal state.

[0017] Another embodiment of this application provides an electronic device, which includes 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 above-described abnormal state detection method for a vehicle.

[0018] Another embodiment of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the above-described method for detecting abnormal states of a vehicle.

[0019] In some embodiments of this application, at least one processing terminal is pre-allocated to the image information based on the environmental complexity of the surrounding environment of the main vehicle. Then, the processing terminal is used to identify the abnormal state type of vehicles in the surrounding environment from the image information and sends an alert to these vehicles to indicate the presence of anomalies. This abnormal alert method enables automatic detection and alerting of vehicles in abnormal states in the surrounding environment of the main vehicle, minimizing safety hazards posed by such vehicles and contributing to improved road safety. Attached Figure Description

[0020] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings. Wherein:

[0021] Figure 1 This is a system architecture applicable to a vehicle abnormality detection method according to some embodiments of this application;

[0022] Figure 2 This is a flowchart illustrating a method for detecting abnormal conditions of a vehicle according to some embodiments of this application.

[0023] Figure 3 This is a schematic diagram illustrating the interaction between an image sensor of a main vehicle, a first vehicle-mounted terminal of the main vehicle, a cloud server, and a second vehicle-mounted terminal of a vehicle in an abnormal state, according to some embodiments of this application.

[0024] Figure 4 This is a schematic diagram illustrating the interaction between an image sensor of a main vehicle, a first vehicle-mounted terminal of the main vehicle, a cloud server, and a second vehicle-mounted terminal of a vehicle in an abnormal state, according to some embodiments of this application.

[0025] Figure 5 This is a schematic diagram illustrating the interaction between an image sensor of a main vehicle, a first vehicle-mounted terminal of the main vehicle, a cloud server, and a second vehicle-mounted terminal of a vehicle in an abnormal state, according to some embodiments of this application.

[0026] Figure 6 This is a schematic block diagram of an electronic device according to some embodiments of this application. Detailed Implementation

[0027] To better understand this application, various aspects of this application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are merely illustrative of exemplary embodiments of this application and are not intended to limit the scope of this application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0028] Unless otherwise specified, all terms used in this application (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms (e.g., those defined in common dictionaries) should be understood to have a meaning consistent with their meaning in the context of the relevant art, and should not be interpreted in an idealized or overly formal sense, unless expressly so defined in this application.

[0029] Furthermore, in the technical solution of this application, the acquisition, storage, and application of image information of the surrounding environment of the main vehicle, license plate numbers of vehicles in abnormal states, and IoT cards all comply with relevant laws and regulations and do not violate public order and good morals. Additionally, the acquired information / data is not intended to characterize a specific type of vehicle and therefore cannot reflect information about a specific type of vehicle.

[0030] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. Furthermore, unless explicitly limited or contradicted by the context, the specific steps included in the methods described in this application are not limited to the order in which they are described, but can be performed in any order or in parallel. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0031] Figure 1 The present invention provides a system architecture 1000 for a vehicle abnormality detection method applicable to some embodiments of this application.

[0032] refer to Figure 1 The system architecture 1000 may include a main vehicle 1100, a cloud server 1200, and an abnormal state vehicle 1300. The main vehicle 1100 may include image sensors 1110 and a first vehicle-mounted terminal 1120 disposed at different locations. The image sensors 1110 can be used to detect image information of the surrounding environment of the main vehicle 1100 and are communicatively connected to the first vehicle-mounted terminal 1120; the first vehicle-mounted terminal 1120 is communicatively connected to the cloud server 1200. The abnormal state vehicle 1300 may include a second vehicle-mounted terminal 1310, which is communicatively connected to the cloud server 1200.

[0033] The first vehicle-mounted terminal 1120 of the main vehicle 1100 acquires image information detected by the image sensor 1110, and determines at least one processing terminal for the image information based on the complexity of the surrounding environment. This processing terminal may include the first vehicle-mounted terminal 1120 of the main vehicle 1100 and / or a cloud service terminal 1200. This processing terminal can identify surrounding vehicles in the surrounding environment and the abnormal state type of the abnormal state vehicle 1300 among the surrounding vehicles based on the image information, and send an alert to the abnormal state vehicle 1300 after determining the abnormal state type.

[0034] In this embodiment, the first vehicle-mounted terminal 1120 pre-allocates at least one processing terminal to the image information based on the environmental complexity of the surrounding environment of the main vehicle 1100. Then, the processing terminal identifies the abnormal state type of the abnormal vehicle 1300 in the surrounding environment from the image information and sends an alert to the abnormal vehicle 1300 to indicate the presence of an anomaly. This anomaly alert method enables automatic detection and alerting of abnormal vehicles 1300 in the surrounding environment of the main vehicle 1100, minimizing safety hazards associated with abnormal vehicles 1300 and contributing to improved road safety.

[0035] In some embodiments of this application, the image sensor 1110 may include, but is not limited to, one or more of a front view image sensor, a surround view image sensor, a rear view image sensor, and a side view image sensor. The front view image sensor can be used to detect image information in front of the main vehicle 1100, the surround view image sensor can be used to detect all-around image information around the main vehicle 1100, the rear view image sensor can be used to detect image information behind the main vehicle 1100, and the side view image sensor can be used to detect image information to the side of the main vehicle 1100.

[0036] In some embodiments of this application, the complexity of the surrounding environment may include, but is not limited to, at least one of weather recognition complexity, road condition recognition complexity, lighting condition recognition complexity, main vehicle speed recognition complexity, building distribution recognition complexity, and surrounding vehicle recognition complexity. Factors influencing the complexity of surrounding vehicle recognition may include, but are not limited to, at least one of the external features of surrounding vehicles, the speed of surrounding vehicles, and the background environment of surrounding vehicles.

[0037] In some embodiments of this application, the first vehicle-mounted terminal 1120 can determine at least one processing terminal for the image information based on a comparison between the complexity of the surrounding environment of the image information and a threshold. This processing terminal may include the first vehicle-mounted terminal 1120 of the main vehicle 1100 and / or the cloud service terminal 1200. It should be noted that the specific value of the threshold can be set according to actual needs, and this application does not impose specific limitations on it.

[0038] In this embodiment, image information is assigned to processing terminals with corresponding processing capabilities based on the complexity of the surrounding environment. For example, image information with high surrounding environment complexity is assigned to the cloud server 1200, and image information with low surrounding environment complexity is assigned to the first vehicle terminal 1120. This helps to rationally allocate processing terminal resources, improve the processing efficiency and accuracy of image information, and reduce the processing time of image information. This allows for more timely and accurate identification of vehicles 1300 in abnormal states in the surrounding environment and their abnormal state types, minimizing potential safety hazards and improving road driving safety.

[0039] In some embodiments of this application, when the environmental complexity of the image information is less than or equal to a threshold, the processing power of the image information is relatively small, and only the first vehicle terminal 1120 is needed to process the image information quickly and accurately. In other words, in response to the environmental complexity of the image information being less than or equal to the threshold, the first vehicle terminal 1120 can determine that the processing terminal for the image information is the first vehicle terminal 1120. The first vehicle terminal 1120 can identify surrounding vehicles in the surrounding environment and the abnormal state type of abnormal vehicles among the surrounding vehicles based on the image information, and send an alert to the abnormal vehicle 1300 after determining the abnormal state type of the abnormal vehicle. In other examples, the first vehicle terminal 1120 can also identify the license plate number of the abnormal vehicle 1300 based on the image information.

[0040] For example, the first vehicle-mounted terminal 1120 sends the license plate number and abnormal status type of the abnormal vehicle 1300 to the cloud server 1200, so that the cloud server 1200 sends an alert to the abnormal vehicle 1300 based on the license plate number, which includes at least the abnormal status type. In other examples, the alert may also include image information corresponding to the abnormal vehicle 1300. For example, the cloud server 1200 determines the IoT card of the abnormal vehicle 1300 based on the license plate number, and then sends an alert to the abnormal vehicle 1300 (such as the second vehicle-mounted terminal 1310 of the abnormal vehicle 1300) via the IoT card, which includes at least the abnormal status type and the image information corresponding to the abnormal vehicle.

[0041] For example, before recognizing the image information, the first vehicle-mounted terminal 1120 can preprocess the image information. Preprocessing may include one or more of denoising, enhancement, and grayscale processing. Denoising may employ methods such as mean filtering, median filtering, and Gaussian filtering to remove noise from the image information, such as random noise and speckle noise. Enhancement may include, for example, sharpening, smoothing, edge enhancement, and contrast enhancement. Grayscale processing may include, for example, converting the image information into a grayscale image. By preprocessing the image information, the quality of the image information and the recognition efficiency can be improved.

[0042] In some embodiments of this application, when the complexity of the surrounding environment of the image information exceeds a threshold, the processing power of the image information is large, and the first vehicle-mounted terminal 1120 cannot process the image information quickly and accurately. Therefore, the cloud server 1200 is needed to perform more refined processing of the image information. In other words, in response to the complexity of the surrounding environment of the image information exceeding the threshold, the first vehicle-mounted terminal 1120 can determine that the processing terminal for the image information is the cloud server 1200. The first vehicle-mounted terminal 1120 sends the image information to the cloud server 1200. The cloud server 1200 can identify surrounding vehicles and the abnormal status type of abnormal vehicles in the surrounding environment based on the received image information, and send a reminder to the abnormal vehicle 1300 after determining the abnormal status type. In other examples, the cloud server 1200 can also identify the license plate number of the abnormal vehicle 1300 based on the image information.

[0043] For example, cloud server 1200 sends an alert to vehicle 1300 in an abnormal state, containing at least the type of abnormal state, based on the license plate number of the vehicle. In other examples, the alert may also include image information corresponding to vehicle 1300 in an abnormal state. For instance, cloud server 1200 identifies the IoT card of vehicle 1300 in an abnormal state based on the license plate number of vehicle 1300, and then sends an alert to vehicle 1300 in an abnormal state (such as the second vehicle terminal 1310 of vehicle 1300) via the IoT card, containing at least the type of abnormal state and image information corresponding to the vehicle in an abnormal state.

[0044] For example, before recognizing the image information, the cloud server 1200 can preprocess the image information. Preprocessing may include one or more of denoising, enhancement, and grayscale processing. Denoising may employ methods such as mean filtering, median filtering, and Gaussian filtering to remove noise from the image information, such as random noise and speckle noise. Enhancement may include, for example, sharpening, smoothing, edge enhancement, and contrast enhancement. Grayscale processing may include, for example, converting the image information to a grayscale image. By preprocessing the image information, the quality of the image information and the recognition efficiency can be improved.

[0045] In some embodiments of this application, in response to the environmental complexity of the image information exceeding a threshold, the first vehicle-mounted terminal 1120 determines that the image information processing terminal includes the first vehicle-mounted terminal 1120 and the cloud server 1200. The first vehicle-mounted terminal 1120 can preprocess the image information and send the preprocessed image information to the cloud server 1200. Based on the received preprocessed image information, the cloud server 1200 identifies surrounding vehicles in the surrounding environment and the abnormal state type of abnormal state vehicles among the surrounding vehicles, and sends an alert to the abnormal state vehicle 1300 after determining the abnormal state type of the abnormal state vehicle.

[0046] For example, preprocessing includes one or more of denoising, enhancement, and grayscale processing. Denoising may employ methods such as mean filtering, median filtering, and Gaussian filtering to remove noise from the image information, such as random noise and speckle noise. Enhancement may include, for example, sharpening, smoothing, edge enhancement, and contrast enhancement. Grayscale processing may include, for example, converting the image information to a grayscale image. By preprocessing the image information, the quality of the image information and the recognition efficiency can be improved.

[0047] For example, the cloud server 1200 can also identify the license plate number of the abnormal vehicle 1300 based on image information. The alert may also include image information corresponding to the abnormal vehicle 1300. For instance, the cloud server 1200 determines the IoT card of the abnormal vehicle 1300 based on its license plate number, and then sends an alert containing at least the abnormal status type and image information corresponding to the abnormal vehicle to the abnormal vehicle 1300 (such as the second vehicle terminal 1310 of the abnormal vehicle 1300) via the IoT card.

[0048] In this embodiment, when the surrounding environment of the image information is highly complex, the image information processing terminals include a first vehicle-mounted terminal 1120 and a cloud server 1200. The first vehicle-mounted terminal 1120 preprocesses the image information, while the cloud server 1200 identifies surrounding vehicles and the abnormal status types of abnormal vehicles from the preprocessed image information. This helps to rationally allocate processing tasks between the two terminals (e.g., tasks with high real-time requirements are handled by the first vehicle-mounted terminal 1120, while complex and time-consuming tasks are handled by the cloud server 1200), enabling the two terminals to work collaboratively and reducing the overall image information processing time. By having the first vehicle-mounted terminal 1120 and the cloud server 1200 handle their respective tasks, rational resource allocation and efficient processing can be achieved, thereby improving the processing efficiency and accuracy of image information, reducing processing time, and thus more timely and accurately identifying abnormal vehicles 1300 and their abnormal status types in the surrounding environment, minimizing potential safety hazards, and improving road safety.

[0049] Figure 2 This is a flowchart illustrating a vehicle anomaly detection method 2000 according to some embodiments of this application. The vehicle anomaly detection method 2000 may be executed, for example, by a first vehicle-mounted terminal 1120 of the main vehicle 1100; or, one or more steps of the vehicle anomaly detection method 2000 may be executed, for example, by the first vehicle-mounted terminal 1120 of the main vehicle 1100, and the remaining steps may be executed, for example, by a cloud service terminal 1200. It should be understood that the vehicle anomaly detection method 2000 may also include additional steps not shown and / or steps shown may be omitted, and the scope of this application is not limited in this respect. The vehicle anomaly detection method 2000 can be applied to application scenarios such as the automatic detection and alerting of anomaly status vehicles 1300 in the surrounding environment by the main vehicle 1100.

[0050] refer to Figure 2 The abnormal condition detection method 2000 for vehicles may include the following steps:

[0051] S2100: Acquire image information of the surrounding environment of the main vehicle.

[0052] S2200. Determine at least one processing end for the image information based on the complexity of the surrounding environment of the image information.

[0053] The S2300 processing unit identifies surrounding vehicles in the environment based on image information, and identifies the abnormal status type of abnormal vehicles among the surrounding vehicles based on image information.

[0054] S2400: In response to determining the abnormal status type of the vehicle, the processing terminal sends a reminder to the vehicle in abnormal status.

[0055] In some embodiments of this application, at least one processing terminal is pre-allocated to the image information based on the environmental complexity of the surrounding environment of the main vehicle 1100. Then, the processing terminal is used to identify the abnormal state type of the abnormal vehicle 1300 in the surrounding environment from the image information, and a reminder is sent to the abnormal vehicle 1300 to alert it of an anomaly. This anomaly alerting method enables automatic detection and alerting of abnormal vehicles 1300 in the surrounding environment of the main vehicle 1100, minimizing safety hazards posed by abnormal vehicles 1300 and contributing to improved road safety.

[0056] The steps S2100 to S2400 of the exemplary embodiments of this application will be described in detail below.

[0057] In step S2100, image information of the surrounding environment of the main vehicle is acquired.

[0058] In some embodiments of this application, the first vehicle-mounted terminal 1120 of the main vehicle 1100 acquires image information of the surrounding environment of the main vehicle 1100. This image information can be detected, for example, by image sensors 1110 disposed at different locations on the main vehicle. The image sensors 1110 may include, but are not limited to, one or more of a front view image sensor, a surround view image sensor, a rear view image sensor, and a side view image sensor. The front view image sensor can be used to detect image information in front of the main vehicle 1100, the surround view image sensor can be used to detect omnidirectional image information around the main vehicle 1100, the rear view image sensor can be used to detect image information behind the main vehicle 1100, and the side view image sensor can be used to detect image information to the sides of the main vehicle 1100.

[0059] In step S2200, at least one processing end of the image information is determined based on the complexity of the surrounding environment of the image information.

[0060] In some embodiments of this application, after acquiring image information detected by image sensor 1110, the first vehicle terminal 1120 can determine at least one processing terminal for the image information based on the complexity of the surrounding environment of the image information. The processing terminal may include the first vehicle terminal 1120 of the main vehicle 1100 and / or the cloud service terminal 1200.

[0061] In some embodiments of this application, the assessment of the complexity of the surrounding environment is a multi-dimensional process, influenced by multiple factors. These factors may include, but are not limited to, at least one of the following: the driving speed of the main vehicle 1100, weather, road conditions, lighting conditions, building distribution, and surrounding vehicles. Each influencing factor corresponds to a weight, reflecting the importance of each factor to the complexity of the surrounding environment. The weight of each factor can be set based on its impact on safety, as well as its predictability and / or frequency of occurrence. (Surrounding Environment Complexity) Where Ci is the identification complexity of the i-th influencing factor, Wi is the weight of the i-th influencing factor, and n is the number of influencing factors related to the complexity of the surrounding environment.

[0062] For example, the complexity of the surrounding environment may include, but is not limited to, at least one of the following: the complexity of recognizing the driving speed of the main vehicle 1100 (C1), the complexity of recognizing the weather (C2), the complexity of recognizing the road conditions (C3), the complexity of recognizing the lighting conditions (C4), the complexity of recognizing the building distribution (C5), and the complexity of recognizing the surrounding vehicles (C6). The weights for the driving speed of the main vehicle 1100 are W1, for the weather W2, for the road conditions W3, for the lighting conditions W4, for the building distribution W5, and for the surrounding vehicles W6. The complexity of the surrounding environment TC = C1×W1 + C2×W2 + C3×W3 + C4×W4 + C5×W5 + C6×W6.

[0063] For example, the assessment of the complexity of surrounding vehicle recognition is a multi-dimensional process influenced by multiple factors. These factors may include, but are not limited to, at least one of the external features of surrounding vehicles, their speed, and their background environment. Each factor has a corresponding weight, reflecting its importance to the complexity of surrounding vehicle recognition. The weight of each factor can be set based on its impact on safety, predictability, and / or frequency of occurrence. (Surrounding Vehicle Recognition Complexity) Where Ai is the recognition complexity of the i-th influencing factor, Ri is the weight of the i-th influencing factor, and m is the number of influencing factors affecting the recognition complexity of surrounding vehicles. For example, the recognition complexity of surrounding vehicles C6 = A1×R1 + A2×R2 + A3×R3, where A1 is the recognition complexity of the external features of surrounding vehicles, R1 is the weight of the external features of surrounding vehicles, A2 is the recognition complexity of the driving speed of surrounding vehicles, R2 is the weight of the driving speed of surrounding vehicles, A3 is the background environment complexity of surrounding vehicles, and R3 is the weight of the background environment of surrounding vehicles.

[0064] In this implementation, by assigning a weight to each influencing factor of the surrounding environment complexity, the complexity of the surrounding environment can be assessed more accurately, thereby more rationally allocating processing terminals to image information, which helps to improve the processing efficiency and accuracy of image information.

[0065] It should be understood that the influencing factors of the surrounding environment complexity and the surrounding vehicle recognition complexity are merely exemplary. The influencing factors of the surrounding environment complexity and the surrounding vehicle recognition complexity can be set according to actual needs. Without departing from the teachings of this application, the surrounding environment complexity and the surrounding vehicle recognition complexity may also include other influencing factors, and this application does not impose specific restrictions on them.

[0066] In some embodiments of this application, the first vehicle-mounted terminal 1120 can determine at least one processing terminal for the image information based on a comparison between the complexity of the surrounding environment of the image information and a threshold. This processing terminal may include the first vehicle-mounted terminal 1120 of the main vehicle 1100 and / or the cloud service terminal 1200. It should be noted that the specific value of the threshold can be set according to actual needs, and this application does not impose specific limitations on it.

[0067] For example, when the environmental complexity TC of the image information is less than or equal to the threshold, the processing power of the image information is relatively small, and the image information can be processed quickly and accurately by only the first vehicle terminal 1120. In other words, in response to the environmental complexity TC of the image information being less than or equal to the threshold, the first vehicle terminal 1120 can determine that the processing terminal for the image information is the first vehicle terminal 1120.

[0068] For example, when the environmental complexity TC of the image information exceeds a threshold, the processing power of the image information is relatively large, and the first vehicle-mounted unit 1120 cannot process the image information quickly and accurately. Therefore, it needs to utilize the cloud server 1200 to perform more refined processing of the image information. In other words, in response to the environmental complexity TC of the image information exceeding the threshold, the first vehicle-mounted unit 1120 can determine that the processing terminal for the image information is the cloud server 1200. In this case, the first vehicle-mounted unit 1120 sends the image information to the cloud server 1200 so that the cloud server 1200 can process the received image information.

[0069] For example, in response to the environmental complexity TC of the image information exceeding a threshold, the first vehicle-mounted terminal 1120 can determine that the image information processing end includes the first vehicle-mounted terminal 1120 and the cloud server 1200. The first vehicle-mounted terminal 1120 can be used to preprocess the image information and send the preprocessed image information to the cloud server 1200. The cloud server 1200 can be used to process the received preprocessed image information. Preprocessing may include one or more of denoising, enhancement, and grayscale processing. Denoising may, for example, employ methods such as mean filtering, median filtering, and Gaussian filtering to remove noise from the image information, such as random noise and speckle noise. Enhancement may, for example, include sharpening, smoothing, edge enhancement, and contrast enhancement. Grayscale processing may, for example, include converting the image information to a grayscale image. By preprocessing the image information, the quality of the image information and the recognition efficiency can be improved.

[0070] In this embodiment, image information is assigned to processing terminals with corresponding processing capabilities based on the complexity of the surrounding environment. For example, image information with high surrounding environment complexity is assigned to the cloud server 1200, and image information with low surrounding environment complexity is assigned to the first vehicle terminal 1120. This helps to rationally allocate processing terminal resources, improve the processing efficiency and accuracy of image information, and reduce the processing time of image information. This allows for more timely and accurate identification of vehicles 1300 in abnormal states in the surrounding environment and their abnormal state types, minimizing potential safety hazards and improving road driving safety.

[0071] In step S2300, the processing end identifies surrounding vehicles in the surrounding environment based on image information, and identifies the abnormal state type of abnormal vehicles among the surrounding vehicles based on image information.

[0072] In some embodiments of this application, when the processing terminal is a first vehicle-mounted terminal 1120 or a cloud service terminal 1200, the processing terminal can determine whether there is an abnormal vehicle 1300 among the surrounding vehicles based on image information. For example, the processing terminal can filter out target image information containing surrounding vehicles from the image information and determine whether there is an abnormal vehicle 1300 among the surrounding vehicles based on the target image information. As an example, the processing terminal can process the target image information using a pre-trained convolutional neural network model. If an abnormal vehicle 1300 is identified from the target image information, the processing terminal determines that there is an abnormal vehicle 1300 among the surrounding vehicles; if no abnormal vehicle 1300 is identified from the target image information, the processing terminal determines that there is no abnormal vehicle 1300 among the surrounding vehicles.

[0073] When an abnormal vehicle 1300 is found among the surrounding vehicles, the processing unit can identify the license plate number and abnormal status type of the abnormal vehicle 1300 based on image information. For example, the processing unit filters abnormal image information of the abnormal vehicle 1300 from the target image information and identifies the license plate number and abnormal status type of the abnormal vehicle 1300 based on the abnormal image information. The abnormal status type can include external abnormal status type and internal abnormal status type. The external abnormal status type can include, but is not limited to, abnormalities of vehicle external components, including, but not limited to, one or more of the following: bumper, rearview mirror, headlights, doors, side pillars, and tires. The internal abnormal status type can include, but is not limited to, one or more of the following: engine abnormality, intake system abnormality, turbocharger abnormality, and fuel supply system abnormality.

[0074] For example, the processing end can process the abnormal image information through a pre-trained convolutional neural network model and identify the license plate number and abnormal state type of the abnormal vehicle 1300. The abnormal state type may include external abnormal state type and internal abnormal state type.

[0075] For example, the processing terminal can identify the license plate number of the abnormal vehicle 1300 based on the abnormal image information, and determine the abnormal state type of the abnormal vehicle 1300 based on the abnormal image information, the license plate number, and a preset standard vehicle image library. The abnormal state type may include external abnormal state types, which may include, but are not limited to, abnormalities of external vehicle components. External vehicle components may include, but are not limited to, one or more of the following: bumpers, rearview mirrors, headlights, doors, side pillars, and tires. The standard vehicle image library may include preset license plate numbers and standard image information corresponding to the preset license plate numbers. That is, there is a mapping relationship between the preset license plate numbers and the standard image information. Through this mapping relationship, the processing terminal can quickly identify the abnormal state type of the abnormal vehicle 1300 based on the abnormal image information. For example, the processing terminal queries the standard vehicle image library to see if there is a preset license plate number that matches the license plate number. If the preset license plate number exists in the standard vehicle image library, the processing terminal compares the abnormal image information with the standard image information corresponding to the preset license plate number, and determines the abnormal state type of the abnormal vehicle 1300 based on the comparison result.

[0076] For example, the exhaust color may include, but is not limited to, at least one of colorless and transparent, white, blue, and black. When the exhaust color is white, blue, or black, there is an internal malfunction in the vehicle. For example, when the exhaust color is white, the vehicle's engine is malfunctioning; when the exhaust color is blue, at least one of the vehicle's engine, turbocharger, and intake system is malfunctioning; and when the exhaust color is black, at least one of the vehicle's intake system, turbocharger, and fuel supply system is malfunctioning.

[0077] The processing unit can determine the exhaust color of the abnormal vehicle 1300 based on the exhaust gas image in the abnormal image information. For example, the processing unit can extract the exhaust gas image from the abnormal image information and obtain the grayscale value of the exhaust gas image, and then determine the exhaust gas color of the abnormal vehicle 1300 based on the grayscale value of the exhaust gas image. Then, the processing unit can determine the abnormal state type of the abnormal vehicle 1300 based on the exhaust gas color of the abnormal vehicle 1300 and a preset exhaust gas color anomaly library. The abnormal state type may include internal abnormal state types, which may include, but are not limited to, one or more of the following: engine abnormality, intake system abnormality, turbocharger abnormality, and fuel supply system abnormality. The exhaust gas color anomaly library may include preset exhaust gas colors and preset abnormal state types corresponding to the preset exhaust gas colors. That is, there is a mapping relationship between preset exhaust gas colors and preset abnormal state types. Through this mapping relationship, the processing unit can quickly identify the abnormal state type of the abnormal vehicle 1300 based on the exhaust gas color of the abnormal vehicle 1300. For example, the processing terminal queries the exhaust color anomaly database to see if there is a preset exhaust color that matches the exhaust color. If the preset exhaust color exists in the exhaust color anomaly database, the processing terminal determines the abnormal state type of vehicle 1300 based on the preset abnormal state type corresponding to the preset exhaust color.

[0078] For example, before identifying surrounding vehicles in the environment based on image information, the processing unit can preprocess the image information. Preprocessing may include one or more of denoising, enhancement, and grayscale processing. Denoising may employ methods such as mean filtering, median filtering, and Gaussian filtering to remove noise from the image information, such as random noise and speckle noise. Enhancement may include, for example, sharpening, smoothing, edge enhancement, and contrast enhancement. Grayscale processing may include, for example, converting the image information to a grayscale image. Preprocessing the image information can improve the quality of the image information and the recognition efficiency.

[0079] In some embodiments of this application, when the processing terminal is a first vehicle terminal 1120 or a cloud service terminal 1200, the processing terminal can filter out abnormal image information of vehicles 1300 in abnormal states from the image information, and identify the license plate number of the abnormal state vehicle 1300 based on the abnormal image information. The abnormal image information of the same license plate number corresponding to the abnormal state vehicle 1300 from different perspectives within a preset time period constitutes the abnormal image information pool of the abnormal state vehicle 1300. Abnormal image information of the same abnormal state vehicle 1300 from different perspectives can be detected by image sensors 1110 at different locations of the same main vehicle 1100, and / or, abnormal image information of the same abnormal state vehicle 1300 from different perspectives can be detected by image sensors 1110 of different main vehicles 1100. After determining the abnormal image information pool of the abnormal state vehicle 1300, the processing terminal can identify the abnormal state type of the abnormal state vehicle 1300 based on the abnormal image information pool.

[0080] In this embodiment, by integrating abnormal image information of abnormal vehicles 1300 with the same license plate number from different perspectives within a preset time period to form an abnormal image information pool for the abnormal vehicle 1300, rich data support can be provided for subsequent identification of the abnormal state type of the abnormal vehicle 1300, which helps to improve the accuracy and reliability of the identification of the abnormal state type of the abnormal vehicle 1300, minimize potential safety hazards, and improve road driving safety.

[0081] In some embodiments of this application, when the processing terminal includes a first vehicle-mounted terminal 1120 and a cloud server 1200, the first vehicle-mounted terminal 1120 can preprocess the image information and send the preprocessed image information to the cloud server 1200; the cloud server 1200 identifies surrounding vehicles in the surrounding environment based on the preprocessed image information, and identifies the abnormal state type of abnormal vehicles among the surrounding vehicles based on the preprocessed image information. Preprocessing may include one or more of denoising, enhancement, and grayscale processing. For example, denoising may use methods such as mean filtering, median filtering, and Gaussian filtering to remove noise from the image information, such as random noise and speckle noise; enhancement may include, for example, sharpening, smoothing, edge enhancement, and contrast enhancement; grayscale processing may include, for example, converting the image information into a grayscale image. By preprocessing the image information, the quality of the image information and the recognition efficiency can be improved. It should be noted that the steps of the cloud server 1200 in identifying surrounding vehicles and abnormal status types of vehicles in the surrounding environment based on preprocessed image information are the same as the steps of the processing end in identifying surrounding vehicles and abnormal status types of vehicles in the surrounding environment based on image information mentioned above, and will not be repeated here.

[0082] In this embodiment, when the surrounding environment of the image information is highly complex, the image information processing terminals include a first vehicle-mounted terminal 1120 and a cloud server 1200. The first vehicle-mounted terminal 1120 preprocesses the image information, while the cloud server 1200 identifies surrounding vehicles and the abnormal status types of abnormal vehicles from the preprocessed image information. This helps to rationally allocate processing tasks between the two terminals (e.g., tasks with high real-time requirements are handled by the first vehicle-mounted terminal 1120, while complex and time-consuming tasks are handled by the cloud server 1200), enabling the two terminals to work collaboratively and reducing the overall image information processing time. By having the first vehicle-mounted terminal 1120 and the cloud server 1200 handle their respective tasks, rational resource allocation and efficient processing can be achieved, thereby improving the processing efficiency and accuracy of image information, reducing processing time, and thus more timely and accurately identifying abnormal vehicles 1300 and their abnormal status types in the surrounding environment, minimizing potential safety hazards, and improving road safety.

[0083] In step S2400, in response to determining the abnormal state type of the abnormal vehicle, the processing terminal sends a reminder to the abnormal vehicle.

[0084] In some embodiments of this application, when the processing terminal is the first vehicle-mounted terminal 1120 of the main vehicle 1100, the first vehicle-mounted terminal 1120 sends the license plate number and abnormal status type of the abnormal vehicle 1300 to the cloud server 1200, so that the cloud server 1200 sends an alert to the abnormal vehicle 1300 based on the license plate number of the abnormal vehicle 1300, which includes at least the abnormal status type. In other examples, the alert may also include image information corresponding to the abnormal vehicle 1300. For example, the cloud server 1200 may determine the IoT card of the abnormal vehicle 1300 based on the license plate number of the abnormal vehicle 1300, and then send an alert to the abnormal vehicle 1300 (such as the second vehicle-mounted terminal 1310 of the abnormal vehicle 1300) through the IoT card, which includes at least the abnormal status type and the image information corresponding to the abnormal vehicle. The second vehicle-mounted terminal 1310 of the abnormal vehicle 1300 receives and displays the above alert to remind the user corresponding to the abnormal vehicle 1300 that the abnormal vehicle 1300 is abnormal.

[0085] In some embodiments of this application, when the processing terminal includes a cloud server 1200 (i.e., the processing terminal is a cloud server 1200, or the processing terminal includes a first vehicle-mounted terminal 1120 and a cloud server 1200), the cloud server 1200 can send an alert to the abnormal vehicle 1300 based on the license plate number of the abnormal vehicle 1300, which includes at least the type of abnormality. In other examples, the alert may also include image information corresponding to the abnormal vehicle 1300. For example, the cloud server 1200 can determine the IoT card of the abnormal vehicle 1300 based on the license plate number of the abnormal vehicle 1300, and then send an alert to the abnormal vehicle 1300 (such as the second vehicle-mounted terminal 1310 of the abnormal vehicle 1300) via the IoT card, which includes at least the type of abnormality and image information corresponding to the abnormal vehicle. The second vehicle-mounted terminal 1310 of the abnormal vehicle 1300 receives and displays the above alert to remind the user corresponding to the abnormal vehicle 1300 that the abnormal vehicle 1300 is abnormal.

[0086] In this embodiment, the IoT card of the abnormal vehicle 1300 is pre-determined using the license plate number of the abnormal vehicle 1300. Then, an alert is sent to the abnormal vehicle 1300 (such as the second vehicle terminal 1310 of the abnormal vehicle 1300) through the IoT card. This can promptly and efficiently alert the user corresponding to the abnormal vehicle 1300 that the abnormal vehicle 1300 is abnormal, minimize the safety hazards of the abnormal vehicle 1300, and help improve the safety of road driving.

[0087] Figure 3 This is an interactive schematic diagram of the image sensor 1110 of the main vehicle 1100, the first vehicle terminal 1120 of the main vehicle 1100, the cloud server 1200, and the second vehicle terminal 1310 of the abnormal state vehicle 1300 according to some embodiments of this application.

[0088] refer to Figure 3 The abnormal condition detection method for vehicles may include the following steps:

[0089] S301, the first vehicle terminal 1120 sends a request to the image sensor 1110 to obtain image information of the surrounding environment of the main vehicle 1100.

[0090] S302, the image sensor 1110 sends the image information of the surrounding environment of the main vehicle 1100, which it has obtained based on the above request, to the first vehicle terminal 1120.

[0091] S303, in response to the fact that the complexity of the surrounding environment of the image information is less than or equal to the threshold, the first vehicle terminal 1120 determines that the processing terminal of the image information is the first vehicle terminal 1120.

[0092] S304, the first vehicle terminal 1120 identifies the license plate number and abnormal status type of surrounding vehicles and abnormal status vehicles 1300 in the surrounding environment based on image information.

[0093] S305, the first vehicle terminal 1120 sends the license plate number and abnormal status type of the abnormal vehicle 1300 to the cloud server 1200.

[0094] S306, the cloud server 1200 sends an alert containing at least the abnormal status type to the second vehicle terminal 1310 of the abnormal vehicle 1300 based on the license plate number of the abnormal vehicle 1300.

[0095] S307, the second vehicle-mounted terminal 1310 receives and displays the above reminder.

[0096] In this embodiment, image information is assigned to a processing terminal with corresponding processing capabilities based on the complexity of the surrounding environment. For example, image information with low surrounding environment complexity is assigned to the first vehicle terminal 1120. This helps to rationally allocate processing terminal resources, improve the processing efficiency and accuracy of image information, and reduce the processing time of image information. This allows for more timely and accurate identification of abnormal vehicles 1300 and their abnormal state types in the surrounding environment, minimizing potential safety hazards and improving road driving safety.

[0097] Figure 4 This is an interactive schematic diagram of the image sensor 1110 of the main vehicle 1100, the first vehicle terminal 1120 of the main vehicle 1100, the cloud server 1200, and the second vehicle terminal 1310 of the abnormal state vehicle 1300 according to some embodiments of this application.

[0098] refer to Figure 4 The abnormal condition detection method for vehicles may include the following steps:

[0099] S401, the first vehicle terminal 1120 sends a request to the image sensor 1110 to obtain image information of the surrounding environment of the main vehicle 1100.

[0100] S402, the image sensor 1110 sends the image information of the surrounding environment of the main vehicle 1100, which it has obtained based on the above request, to the first vehicle terminal 1120.

[0101] S403, in response to the complexity of the surrounding environment of the image information being greater than a threshold, the first vehicle terminal 1120 determines that the processing terminal of the image information is the cloud server 1200.

[0102] S404, the first vehicle-mounted terminal 1120 sends image information to the cloud server 1200.

[0103] S405, cloud server 1200 identifies the license plate number and abnormal status type of surrounding vehicles and vehicles in abnormal status 1300 in the surrounding environment based on image information.

[0104] S406, the cloud server 1200 sends an alert containing at least the abnormal status type to the second vehicle terminal 1310 of the abnormal vehicle 1300 based on the license plate number of the abnormal vehicle 1300.

[0105] S407, the second vehicle-mounted terminal 1310 receives and displays the above reminder.

[0106] In this embodiment, image information is assigned to a processing terminal with corresponding processing capabilities based on the complexity of the surrounding environment. For example, image information with high surrounding environment complexity is assigned to the cloud server 1200. This helps to rationally allocate processing terminal resources, improve the processing efficiency and accuracy of image information, and reduce the processing time of image information. This allows for more timely and accurate identification of vehicles 1300 in abnormal states in the surrounding environment and their abnormal state types, minimizing potential safety hazards and improving road driving safety.

[0107] Figure 5 This is an interactive schematic diagram of the image sensor 1110 of the main vehicle 1100, the first vehicle terminal 1120 of the main vehicle 1100, the cloud server 1200, and the second vehicle terminal 1310 of the abnormal state vehicle 1300 according to some embodiments of this application.

[0108] refer to Figure 5 The abnormal condition detection method for vehicles may include the following steps:

[0109] S501, the first vehicle terminal 1120 sends a request to the image sensor 1110 to obtain image information of the surrounding environment of the main vehicle 1100.

[0110] S502, the image sensor 1110 sends the image information of the surrounding environment of the main vehicle 1100, which it has obtained based on the above request, to the first vehicle terminal 1120.

[0111] S503, in response to the fact that the complexity of the surrounding environment of the image information is greater than a threshold, the first vehicle terminal 1120 determines that the processing terminal of the image information includes the first vehicle terminal 1120 and the cloud service terminal 1200.

[0112] S504, the first vehicle-mounted unit 1120 preprocesses the image information.

[0113] S505, the first vehicle-mounted terminal 1120 sends pre-processed image information to the cloud server 1200.

[0114] S506, the cloud server 1200 identifies the license plate numbers and abnormal status types of surrounding vehicles and vehicles in abnormal states 1300 in the surrounding environment based on preprocessed image information.

[0115] S507, the cloud server 1200 sends an alert containing at least the abnormal status type to the second vehicle terminal 1310 of the abnormal vehicle 1300 based on the license plate number of the abnormal vehicle 1300.

[0116] S508, the second vehicle terminal 1310 receives and displays the above reminder.

[0117] In this embodiment, when the surrounding environment of the image information is highly complex, the image information processing terminals include a first vehicle-mounted terminal 1120 and a cloud server 1200. The first vehicle-mounted terminal 1120 preprocesses the image information, while the cloud server 1200 identifies surrounding vehicles and the abnormal status types of abnormal vehicles from the preprocessed image information. This helps to rationally allocate processing tasks between the two terminals (e.g., tasks with high real-time requirements are handled by the first vehicle-mounted terminal 1120, while complex and time-consuming tasks are handled by the cloud server 1200), enabling the two terminals to work collaboratively and reducing the overall image information processing time. By having the first vehicle-mounted terminal 1120 and the cloud server 1200 handle their respective tasks, rational resource allocation and efficient processing can be achieved, thereby improving the processing efficiency and accuracy of image information, reducing processing time, and thus more timely and accurately identifying abnormal vehicles 1300 and their abnormal status types in the surrounding environment, minimizing potential safety hazards, and improving road safety.

[0118] Some embodiments of this application also provide an electronic device, which includes 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 one or more steps of the above-described abnormal state detection method for a vehicle.

[0119] Some embodiments of this application also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements one or more steps of the above-described vehicle abnormal state detection method.

[0120] Figure 6 This is a schematic block diagram of an electronic device according to some embodiments of this application. (Reference) Figure 6The electronic device 6000 includes a processor 6001, which can execute various appropriate steps and processes according to computer program instructions stored in read-only memory (ROM) 6002 or loaded from memory 6008 into random access memory (RAM) 6003. The RAM 6003 may also store various programs and data required for the operation of the electronic device 6000. The processor 6001, ROM 6002, and RAM 6003 are interconnected via a bus 6004. An input / output (I / O) interface 6005 is also connected to the bus 6004.

[0121] Multiple components in electronic device 6000 are connected to I / O interface 6005, including: input unit 6006; output unit 6007; memory 6008, such as disk, optical disk, etc.; and communication unit 6009, such as network card, modem, wireless transceiver, etc. Communication unit 6009 allows electronic device 6000 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0122] Processor 6001 can be various general-purpose and / or special-purpose processing units with processing and computing capabilities. Some examples of processor 6001 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 6001 can execute the various methods and processes described above, such as performing one or more steps of the above-described vehicle abnormality detection method. For example, in some embodiments, one or more steps of the above-described vehicle abnormality detection method can be implemented as a computer software program stored in a machine-readable medium, such as memory 6008. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 6000 via ROM 6002 and / or communication unit 6009. When the computer program is loaded into RAM 6003 and executed by processor 6001, one or more steps of the above-described vehicle abnormality detection method can be performed. Alternatively, in other embodiments, the processor 6001 may be configured by any other suitable means (e.g., by means of firmware) to perform one or more steps of the above-described vehicle abnormality detection method.

[0123] Various aspects of this application have been described herein with reference to flowchart illustrations and / or step diagrams of methods, apparatus (systems), and computer program products according to exemplary embodiments of this application. It should be understood that each step in the flowchart illustrations and / or step diagrams, as well as combinations of steps in the flowchart illustrations and / or step diagrams, can be implemented by computer-readable program instructions.

[0124] These computer-readable program instructions can be provided to a processor, general-purpose computer, special-purpose computer, or other programmable data processing device in an electronic device to produce a machine such that, when executed by the processing device of the computer or other programmable data processing device, they create means for implementing the functions / steps specified in one or more steps of the flowchart and / or diagram of steps. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing device, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / steps specified in one or more steps of the flowchart and / or diagram of steps.

[0125] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / steps specified in one or more steps of a flowchart and / or a diagram of steps.

[0126] The flowcharts and step diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of this application. In this regard, each step in a flowchart or step diagram may represent a module, segment, or part of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions indicated in the steps may occur in a different order than indicated in the drawings. For example, two consecutive steps may actually be performed substantially in parallel, and they may sometimes be performed in reverse order, depending on the functions involved. It should also be noted that each step in the step diagrams and / or flowcharts, and combinations of steps in the step diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0127] The above description is merely an exemplary embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of protection involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the technical concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for detecting abnormal conditions of a vehicle, characterized in that, include: Acquire image information of the surrounding environment of the main vehicle; At least one processing end for the image information is determined based on the complexity of the surrounding environment of the image information. The processing terminal identifies surrounding vehicles in the surrounding environment based on the image information, and identifies the abnormal state type of abnormal vehicles among the surrounding vehicles based on the image information. as well as In response to determining the abnormal state type of the abnormal vehicle, the processing terminal sends an alert to the abnormal vehicle.

2. The method according to claim 1, wherein, The complexity of the surrounding environment includes at least one of the following: weather recognition complexity, road condition recognition complexity, lighting condition recognition complexity, the driving speed recognition complexity of the main vehicle, building distribution recognition complexity, and surrounding vehicle recognition complexity. The factors influencing the complexity of surrounding vehicle recognition include at least one of the external features of the surrounding vehicles, the driving speed of the surrounding vehicles, and the background environment of the surrounding vehicles.

3. The method according to claim 1, wherein, The processing terminal includes the first vehicle-mounted terminal and / or cloud service terminal of the main vehicle.

4. The method according to any one of claims 1 to 3, wherein, Based on the image information, the abnormal state type of the vehicles in the surrounding area is identified, including: Based on the image information, determine whether there is a vehicle in the abnormal state among the surrounding vehicles; and In response to determining that an abnormal vehicle exists among the surrounding vehicles, the license plate number and abnormal status type of the abnormal vehicle are identified based on the image information. The image information is detected by image sensors located at different positions on the main vehicle.

5. The method according to claim 4, wherein, Determining whether the abnormal vehicle exists among the surrounding vehicles based on the image information includes: Filter out target image information containing surrounding vehicles from the image information; and Based on the target image information, determine whether there is a vehicle in the abnormal state among the surrounding vehicles.

6. The method according to claim 5, wherein, Identifying the license plate number and abnormal status type of the vehicle in the abnormal state based on the image information includes: Filter out abnormal image information containing vehicles in the abnormal state from the target image information; and Based on the abnormal image information, the license plate number and abnormal state type of the vehicle in the abnormal state are identified, wherein the abnormal state type includes external abnormal state type and internal abnormal state type.

7. The method according to claim 6, wherein, Identifying the license plate number and abnormal status type of the vehicle in the abnormal state based on the abnormal image information includes: The license plate number of the vehicle in the abnormal state is identified based on the abnormal image information; and Based on the abnormal image information, the license plate number, and a preset standard vehicle image library, the abnormal state type of the vehicle is determined. The abnormal state type includes external abnormal state types. The standard vehicle image library includes preset license plate numbers and standard image information corresponding to the preset license plate numbers.

8. The method according to claim 6, wherein, Identifying the abnormal state type of the abnormal vehicle based on the abnormal image information includes: The exhaust color of the abnormal vehicle is determined based on the exhaust image in the abnormal image information; and The abnormal state type of the vehicle is determined based on the exhaust color and a preset exhaust color anomaly database. The abnormal state type includes internal abnormal state types. The exhaust gas color anomaly database includes preset exhaust gas colors and preset anomaly status types corresponding to the preset exhaust gas colors.

9. The method according to claim 8, wherein, Determining the exhaust color of the abnormal vehicle based on the exhaust image of the abnormal image information includes: The grayscale value of the exhaust gas image is obtained, and the exhaust gas color of the abnormal vehicle is determined based on the grayscale value of the exhaust gas image.

10. The method according to claim 4, wherein, Identifying the license plate number and abnormal status type of the vehicle in the abnormal state based on the image information includes: Filter out abnormal image information of vehicles exhibiting the abnormal state from the image information; The license plate number of the abnormal vehicle is identified based on the abnormal image information, wherein the abnormal image information of the abnormal vehicle corresponding to the same license plate number from different perspectives within a preset time period constitutes an abnormal image information pool for the abnormal vehicle; and The abnormal state type of the abnormal vehicle is identified based on the abnormal image information pool; Specifically, the abnormal image information of the same abnormal vehicle from different perspectives is detected by image sensors at different locations of the same main vehicle, and / or, the abnormal image information of the same abnormal vehicle from different perspectives is detected by image sensors of different main vehicles.

11. The method according to claim 4, wherein, The processing terminal is the first vehicle-mounted terminal of the main vehicle, wherein the processing terminal sends an alert to the vehicle in the abnormal state, including: The first vehicle-mounted terminal sends the license plate number and abnormal status type of the vehicle in abnormal status to the cloud server, so that the cloud server can send an alert to the vehicle in abnormal status based on the license plate number of the vehicle in abnormal status, which at least includes the abnormal status type.

12. The method according to claim 4, wherein, The processing terminal includes a cloud server, wherein the processing terminal sends an alert to the vehicle in the abnormal state, including: The cloud server sends a notification to the vehicle in the abnormal state, which includes at least the type of abnormal state, based on the vehicle's license plate number.

13. The method according to claim 12, wherein, The cloud server sends an alert to the vehicle in the abnormal state based on the vehicle's license plate number, which includes at least the type of abnormal state: The cloud server determines the IoT card of the vehicle in abnormal condition based on the license plate number; and The cloud server sends an alert to the vehicle in the abnormal state via the IoT card, which includes at least the type of abnormal state and the image information corresponding to the vehicle in the abnormal state.

14. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to cause the at least one processor to perform the abnormal state detection method for a vehicle according to any one of claims 1 to 11.

15. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the abnormal state detection method for a vehicle as described in any one of claims 1 to 11.

Images