Low-speed vehicle identification method and device

Abstract

The embodiment of the invention provides a low-speed vehicle identification method and device. The method comprises the following steps: acquiring continuous multiple image data of a target vehicle and a driving speed of the target vehicle, and identifying feature information of the target vehicle; determining passing vehicles adjacent to the target vehicle based on the feature information, determining a vehicle distance between the target vehicle and the passing vehicles, obtaining a traffic flow density, determining a traffic state of a road where the current target vehicle is located based on a preset traffic flow density and a current traffic flow density, and adjusting and determining a slow speed threshold and a safe vehicle distance of a dangerous slow speed vehicle, and determining the target vehicle as a dangerous low-speed vehicle and sending a prompt message to the dangerous low-speed vehicle under the conditions that the current traffic state is an unblocked state, the driving speed is not greater than the low-speed threshold value and the vehicle distance is greater than the safe vehicle distance. According to the method, the defects of insufficient accuracy in real-time monitoring of the driving state of the vehicle and the like are effectively overcome, and the accuracy of monitoring the driving state of the vehicle is remarkably improved.

Description

Technical Field

[0001] This application relates to the field of image recognition technology, specifically to a method and apparatus for identifying slow-moving vehicles. Background Technology

[0002] In traffic management, speeding is a concern in order to reduce the probability of traffic accidents. However, dangerously slow driving on smooth roads can also cause traffic accidents or affect traffic flow. For example, when a vehicle suddenly slows down or continues to drive at a low speed even when there is sufficient distance between vehicles, it will negatively impact traffic flow and increase the risk of rear-end collisions and other traffic accidents.

[0003] In existing technologies, the average speed is determined by simple two-point speed measurement, which makes it impossible to effectively distinguish between reasonable slow speed and dangerous slow speed. Reasonable slow speed includes normal slow traffic in congested areas. At the same time, the accuracy of the speed measurement results obtained by the existing speed measurement method is easily affected by different weather conditions, making it difficult to accurately judge the driving status of the vehicle. Summary of the Invention

[0004] To address the problems in the prior art, this application provides a slow vehicle identification method and device, which can effectively solve the shortcomings of traditional technologies in terms of the accuracy of real-time monitoring of vehicle driving status, significantly improve the accuracy of monitoring vehicle driving status, and improve traffic flow.

[0005] To solve at least one of the above problems, this application provides the following technical solution: In a first aspect, this application provides a method for identifying slow-moving vehicles, including: Multiple cameras deployed within a preset monitoring area collect continuous image data of the target vehicle and its driving speed. Based on the image data, the characteristic information of the target vehicle is identified, including the vehicle's license plate number, body color, and vehicle model. Based on feature information, identify passing vehicles adjacent to the target vehicle, determine the vehicle spacing between the target vehicle and passing vehicles, obtain the traffic density of the road where the target vehicle is currently located, and determine the traffic status of the road where the target vehicle is currently located based on the comparison between the preset traffic density and the current traffic density. The traffic status includes congestion, slow traffic, and smooth traffic. Based on traffic conditions, traffic density, and real-time weather conditions, the slow speed threshold and safe following distance for identifying dangerous slow-moving vehicles are adjusted. When the current traffic conditions are smooth, the driving speed is not greater than the slow speed threshold, and the distance between vehicles is greater than the safe following distance, the target vehicle is identified as a dangerous slow-moving vehicle, and a warning message is sent to the driver of the dangerous slow-moving vehicle to prompt him to adjust his driving speed.

[0006] Furthermore, it also includes: collecting multiple consecutive image data of the target vehicle and the timestamps corresponding to the image data through multiple cameras, wherein each camera is facing the road at a preset acquisition angle; Obtain the location information of each camera, and determine the speed of the target vehicle based on the timestamp and location information.

[0007] Furthermore, before adjusting the slow speed threshold and safe following distance for identifying dangerous slow-moving vehicles based on traffic conditions, traffic density, and real-time weather conditions, the following steps are also included: By using a visual feature compensation algorithm to perform edge detection on the ground reflectivity in the image data, the proportion of the water reflection area in the ground of the image data is obtained. If the proportion of a region exceeds a preset proportion threshold, the real-time weather condition will be determined as rainy weather, and the rain level will be determined based on the proportion of the region. The rain level includes light rain level and heavy rain level.

[0008] Furthermore, it also includes: when the rain level is light rain, reducing the slow speed threshold to the first rainy slow speed threshold and increasing the safe following distance to the first rainy safe following distance; When the rain level is heavy rain, the slow speed threshold is reduced to the second rainy day slow speed threshold, and the safe following distance is increased to the second rainy day safe following distance. The first rainy day slow speed threshold is greater than the second rainy day slow speed threshold, and the first rainy day safe following distance is less than the second rainy day safe following distance.

[0009] Furthermore, it also includes: determining the total number and distribution of vehicles passing through the preset monitoring interval within the preset period based on image data, and determining the current traffic density of the road where the target vehicle is located based on the total vehicle data volume and distribution. Obtain a preset relationship mapping table between preset traffic flow density thresholds and speed ranges, determine the theoretical speed range corresponding to the current traffic flow density in the preset relationship mapping table, and determine the traffic status of the road where the current target vehicle is located based on the theoretical speed range.

[0010] Furthermore, after adjusting the slow speed threshold and safe following distance for determining dangerous slow-moving vehicles, it also includes: If the target vehicle's speed decreases beyond a preset deceleration threshold within a preset time, the target vehicle will be identified as a dangerous slow-moving vehicle. Send alert messages to dangerously slow-moving vehicles to prompt their drivers to adjust their speed.

[0011] Furthermore, the alert messages include standard alert messages, escalation alert messages, and critical alert messages, and also include: Based on the characteristic information of the target vehicle, obtain the historical driving behavior record of the target vehicle, and determine the number of times the target vehicle is a dangerous slow vehicle in the historical driving behavior record. If the number of slow speeds is less than the first threshold and less than the second threshold, a standard alert message is sent to the driver of the dangerous slow-moving vehicle. If the number of slow speeds is not less than the first threshold and less than the second threshold, an escalation warning message is sent to the driver of the dangerous slow-moving vehicle. If the number of slow-moving incidents is not less than the threshold for the second incident, a serious warning message is sent to the driver of the dangerous slow-moving vehicle, and an abnormal behavior report of the dangerous slow-moving vehicle is sent to the management platform.

[0012] Secondly, this application provides a slow-speed vehicle identification device, comprising: The acquisition module is used to collect multiple consecutive image data of the target vehicle and the driving speed of the target vehicle through multiple cameras deployed in a preset monitoring range, and to identify the characteristic information of the target vehicle based on the image data. The characteristic information includes the license plate number, body color and vehicle model of the target vehicle. The environment module is used to determine the passing vehicles adjacent to the target vehicle based on feature information, determine the vehicle distance between the target vehicle and the passing vehicles, obtain the traffic density of the road where the target vehicle is currently located, and determine the traffic status of the road where the target vehicle is currently located based on the comparison between the preset traffic density and the current traffic density. The traffic status includes congestion, slow traffic and smooth traffic. The decision-making module is used to adjust the slow speed threshold and safe distance for identifying dangerous slow vehicles based on traffic conditions, traffic density, and real-time weather conditions. When the current traffic conditions are smooth, the driving speed is not greater than the slow speed threshold, and the distance between vehicles is greater than the safe distance, the target vehicle is identified as a dangerous slow vehicle, and a prompt message is sent to the dangerous slow vehicle to prompt the driver of the dangerous slow vehicle to adjust the driving speed.

[0013] Thirdly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the slow vehicle identification method.

[0014] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the slow vehicle identification method described above.

[0015] Fifthly, this application provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the slow vehicle identification method described above.

[0016] As can be seen from the above technical solution, this application provides a slow vehicle identification method and device. It innovatively uses multiple cameras deployed within a preset monitoring range to collect continuous multiple image data of a target vehicle and the vehicle's speed. Based on the image data, it identifies the target vehicle's feature information, including the license plate number, body color, and vehicle model. Based on the feature information, it determines adjacent passing vehicles and the distance between the target vehicle and passing vehicles, obtains the traffic density of the road where the target vehicle is currently located, and determines the traffic state of the road where the target vehicle is currently located based on a comparison between a preset traffic density and the current traffic density. The traffic state includes congested, slow-moving, and free-flowing conditions. Based on the traffic state, traffic density, and actual... Based on weather conditions, the slow speed threshold and safe following distance for identifying dangerous slow-moving vehicles are adjusted. When traffic is flowing smoothly, the speed does not exceed the slow speed threshold, and the distance between vehicles is greater than the safe following distance, the target vehicle is identified as a dangerous slow-moving vehicle, and a warning message is sent to its driver to prompt them to adjust their speed. This method utilizes multiple cameras in collaboration and comprehensively analyzes various parameters related to the target vehicle to distinguish between reasonably slow-moving and dangerous slow-moving vehicles, improving the accuracy and comprehensiveness of vehicle driving status assessment. When a dangerous slow-moving vehicle is identified, a warning is issued, allowing its driver to adjust their speed promptly, reducing the risk of traffic congestion and accidents caused by slow driving, and improving traffic efficiency and safety. This method effectively addresses the shortcomings of traditional technologies in terms of accuracy in real-time vehicle driving status monitoring, significantly improving the accuracy of vehicle driving status monitoring and enhancing traffic flow. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the slow vehicle identification method in the embodiments of this application; Figure 2 This is a structural diagram of the slow vehicle identification device in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the electronic device in the embodiments of this application.

[0019] Figure label: Electronic device 9600, central processing unit 9100, memory 9140, communication module 9110, input unit 9120, audio processor 9130, display 9160, power supply 9170, buffer memory 9141, application / function storage unit 9142, data storage unit 9143, driver storage unit 9144, antenna 9111, speaker 9131, microphone 9132. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0022] In view of the problems existing in the prior art, this application provides a method and device for identifying slow vehicles. By jointly analyzing target vehicles through multiple cameras and combining real-time road conditions and weather conditions, dangerous slow vehicles are accurately identified and alert messages are sent to them, thereby improving traffic efficiency and safety.

[0023] To effectively address the shortcomings of traditional technologies in terms of accuracy in real-time vehicle status monitoring, and to significantly improve the accuracy of vehicle status monitoring and enhance traffic flow, this application provides an embodiment of a slow vehicle identification method. See [link to embodiment]. Figure 1 The slow-moving vehicle identification method specifically includes the following: Step S101: Collect multiple consecutive image data of the target vehicle and the driving speed of the target vehicle by multiple cameras deployed in the preset monitoring range, and identify the feature information of the target vehicle based on the image data.

[0024] The feature information includes the target vehicle's license plate number, body color, and vehicle model.

[0025] Optionally, this embodiment deploys multiple cameras within a preset monitoring range and collects continuous multiple image data of the target vehicle and its speed through these cameras. The preset monitoring range can be a section of expressway, and the deployed cameras can be positioned at fixed angles and intervals to create continuous, blind-spot-free coverage of the same road segment, thereby enabling the collection of continuous image sequences of vehicles traveling in the same direction.

[0026] Among them, the continuous multiple image data is obtained by multiple cameras continuously capturing image data of the air in a time sequence at a fixed frequency. The movement trajectory and speed changes of the target vehicle can be analyzed based on the continuous multiple image data.

[0027] The term "target vehicle" refers to the same vehicle in multiple consecutive image data sets, and any vehicle present in the image data can be considered the target vehicle.

[0028] Furthermore, the acquired image data can be transmitted to a data processing center for preprocessing, including noise reduction, contrast enhancement, and distortion correction. Preprocessed image data can improve the accuracy of target vehicle analysis.

[0029] In addition, the feature information of the target vehicle is identified based on the image data. This identification can be performed using deep learning image recognition algorithms. The feature information includes, but is not limited to, the target vehicle's license plate number, body color, and vehicle model, which are used to uniquely identify the target vehicle.

[0030] This embodiment achieves the collaborative layout of multiple cameras, avoiding the problem of limited field of view of a single camera, ensuring the continuity of image data, obtaining the feature information of the target vehicle based on the image data, and maintaining the accuracy of the target vehicle's identity determination through multi-feature combination.

[0031] Step S102: Based on feature information, determine the passing vehicles adjacent to the target vehicle, determine the vehicle distance between the target vehicle and the passing vehicles, obtain the traffic density of the road where the target vehicle is currently located, and determine the traffic status of the road where the target vehicle is currently located based on the comparison between the preset traffic density and the current traffic density.

[0032] Traffic conditions include congestion, slow traffic, and smooth traffic.

[0033] Optionally, this embodiment distinguishes between target vehicles and passing vehicles in multiple consecutive image data based on the identified vehicle features. Passing vehicles are other vehicles that appear in the image data at the same time as the target vehicle.

[0034] In addition, determining the passing vehicles adjacent to the target vehicle and the vehicle distance between the target vehicle and the passing vehicles, that is, determining the vehicle distance between the target vehicle and the passing vehicles in front of the target vehicle, and between the target vehicle and the passing vehicles after the target vehicle, can be done by combining the calibration parameters of the camera to determine the real-time physical distance between the target vehicle and the passing vehicles.

[0035] In addition, the traffic density of the road where the target vehicle is located is obtained by statistically analyzing the number and distribution of vehicles passing through the current preset monitoring interval within a certain time and space range. Based on the comparison between the preset traffic density and the current traffic density, the traffic status of the road where the target vehicle is located is determined. The traffic status includes congested, slow-moving, and smooth traffic, which allows for a more comprehensive assessment of the traffic situation. The unit of traffic density can be vehicles / km / lane, which can directly reflect the degree of road congestion.

[0036] This embodiment measures vehicle spacing to determine whether the current vehicle spacing is safe. It can also determine traffic conditions through traffic density, making it more fundamental. In congested and slow-moving conditions, low-speed driving of vehicles is a common phenomenon and can be considered a reasonable slow speed. In unobstructed conditions, abnormally low speed of a target vehicle can lead to dangerous slow speed, which has a negative impact on traffic conditions. This embodiment distinguishes between normal low-speed vehicles and dangerous slow-speed vehicles, thus providing a guarantee for traffic safety.

[0037] Step S103: Based on traffic conditions, traffic density, and real-time weather conditions, adjust the slow speed threshold and safe distance for identifying dangerous slow vehicles. If the current traffic conditions are smooth, the driving speed is not greater than the slow speed threshold, and the distance between vehicles is greater than the safe distance, identify the target vehicle as a dangerous slow vehicle and send a prompt message to the driver of the dangerous slow vehicle to prompt him to adjust his driving speed.

[0038] Optionally, after determining the target vehicle's speed, vehicle spacing, and traffic density, this embodiment can dynamically adjust the slow speed threshold and safe distance for identifying dangerous slow-moving vehicles by combining real-time weather conditions. That is, it can adaptively adjust the slow speed threshold and safe distance for identifying dangerous slow-moving vehicles based on traffic conditions, traffic density, and real-time weather conditions.

[0039] For example, in smooth traffic conditions, a higher slow speed threshold can be used to identify dangerous slow vehicles in order to maintain traffic flow efficiency. However, in rainy or snowy weather, the slow speed threshold can be appropriately lowered for safety reasons. Similarly, the safe following distance can be increased as visibility and road surface adhesion coefficient deteriorate due to weather conditions.

[0040] In addition, if the traffic is smooth, the target vehicle's speed is lower than the dynamically adjusted slow speed threshold, and the distance between the target vehicle and passing vehicles is greater than the safe distance, the target vehicle will be identified as a dangerous slow vehicle.

[0041] In addition, alert messages are sent to dangerous slow-moving vehicles to remind drivers to adjust their speed. These messages may include vehicle identification information such as license plate numbers and instructions. The alert messages can be sent to dangerous slow-moving vehicles via integrated communication interfaces in the form of voice or SMS broadcasts to remind drivers to adjust their speed.

[0042] Furthermore, it can be combined with roadside units, not limited to SMS or voice prompts, to send prompt messages to connected vehicles that support this function via V2I communication.

[0043] This embodiment enables decision-making based on real-time weather conditions, traffic conditions, and vehicle density. It can also dynamically adjust the slow speed threshold and vehicle spacing for identifying dangerous slow-moving vehicles based on real-time weather conditions, traffic conditions, and vehicle density, making the identification of dangerous slow-moving vehicles closer to actual safety needs. In addition, when a target vehicle is identified as a dangerous slow-moving vehicle, a warning message can be sent to the dangerous slow-moving vehicle, realizing immediate feedback to move the safety defense line forward and reduce the occurrence of traffic accidents.

[0044] This embodiment achieves the collaborative acquisition of multiple images of a target vehicle by multiple cameras. By analyzing the image data, vehicle spacing, traffic density, and real-time weather conditions, the criteria for determining dangerous slow-moving vehicles are dynamically adjusted. When a target vehicle is determined to be a dangerous slow-moving vehicle, a warning message is sent to the vehicle to prompt the driver to adjust their speed. Through multi-dimensional analysis and dynamic adjustment, the efficiency and driving safety within the preset monitoring area are improved, as well as the driving safety of individual vehicles. It can also accurately identify dangerous slow-moving vehicles that may cause traffic jams or safety accidents in smooth traffic conditions and effectively intervene by sending warning messages, thereby improving the user experience.

[0045] In some embodiments, acquiring multiple consecutive image data of the target vehicle and the vehicle's speed using multiple cameras deployed within a preset monitoring range includes: Multiple cameras are used to collect multiple consecutive images of the target vehicle and the timestamps corresponding to the image data. Each camera is facing the road at a preset acquisition angle. Obtain the location information of each camera, and determine the speed of the target vehicle based on the timestamp and location information.

[0046] Optionally, in this embodiment, multiple cameras are installed at preset intervals and preset acquisition angles within a preset monitoring range. This allows the cameras to capture multiple consecutive image data of the target vehicle in real time. While the cameras are acquiring each image data, they record the timestamp of the acquired image data. Thus, through the collaborative work of multiple cameras, multi-angle image data of the target vehicle at different locations can be obtained.

[0047] In addition, by obtaining the location information of each camera and combining it with the timestamps of the target vehicle passing each camera, the driving speed of the target vehicle within the preset monitoring range is determined through time-space analysis.

[0048] The location information of each camera can be geographic coordinates, which are pre-entered into the database as known parameters. In the process of determining the driving speed, the camera can be matched and associated with multiple consecutive image data to determine the driving speed of the target vehicle.

[0049] Furthermore, a short-term trajectory prediction model based on deep learning can be used to predict the most likely position and state of the target vehicle at the next moment when it is about to leave the field of view of a camera. This can assist adjacent cameras in collecting image data containing the target vehicle, reduce matching ambiguity, and improve the consistency and efficiency of target vehicle tracking.

[0050] This embodiment achieves the acquisition of multiple continuous image data of a target vehicle from different angles and positions using multiple cameras. By combining timestamps and camera location information, the driving speed of the target vehicle within the preset monitoring range can be determined more accurately, improving the accuracy and reliability of speed monitoring. At the same time, deploying multiple cameras within the preset monitoring range to work together can achieve comprehensive coverage of multiple lanes within the preset monitoring range, ensuring that all passing vehicles can be accurately monitored, increasing the monitoring coverage, reducing blind spots, and thus facilitating the improvement of road traffic efficiency and driving safety.

[0051] In some embodiments, before adjusting the slow speed threshold and safe following distance for determining dangerous slow vehicles based on traffic conditions, traffic density, and real-time weather conditions, the method further includes: By using a visual feature compensation algorithm to perform edge detection on the ground reflectivity in the image data, the proportion of the water reflection area in the ground of the image data is obtained. If the proportion of a region exceeds a preset proportion threshold, the real-time weather condition will be determined as rainy weather, and the rain level will be determined based on the proportion of the region. The rain level includes light rain level and heavy rain level.

[0052] Optionally, before determining the slow threshold and safe distance of dangerous slow vehicles based on traffic conditions, traffic density, and real-time weather conditions, this embodiment needs to obtain real-time weather conditions. This can be done by analyzing the image sequence using visual feature compensation algorithms based on the environmental information contained in the image data collected by existing cameras.

[0053] In addition, edge detection of ground reflectivity in image data using visual feature compensation algorithms requires excluding interference from irrelevant areas such as vehicles, guardrails, and the sky. By performing dense analysis of pixels in the road surface area and focusing on the distribution characteristics of reflectivity, the proportion of water reflectivity in the ground area of ​​the image data can be obtained.

[0054] For example, dry asphalt pavement will present a relatively uniform, low-reflection texture pattern, while wet pavement will produce a specular reflection effect due to the formation of a water film, resulting in bright areas at certain angles. Therefore, the image data can be edge-detected by visual feature compensation algorithms to capture the boundary of light intensity abrupt change caused by water reflection, and the pavement in the image data can be divided into suspected water accumulation and reflective areas and normal dry areas.

[0055] Among them, the visual feature compensation algorithm is an image processing algorithm used to extract and enhance the features of the environment from complex visual scenes, which can compensate for the lack of perception of environmental factors by conventional object recognition algorithms.

[0056] In addition, if the area proportion exceeds the preset proportion threshold, that is, if the proportion of the ground in the suspected waterlogged reflective area in the total ground area exceeds the preset proportion threshold, the real-time weather condition will be determined as rainy weather.

[0057] Furthermore, the regional proportion is positively correlated with the rainfall intensity. That is, the larger the regional proportion, the more widespread the water accumulation on the road surface or the thicker the water film on the road surface, the stronger the reflection, and the greater the real-time rainfall. Therefore, the rain weather level can be determined based on the regional proportion, which includes light rain level and heavy rain level.

[0058] For example, if the area proportion exceeds the preset proportion threshold but does not exceed the rainy day proportion, the real-time weather condition will be determined as light rain level for rainy days; if the area proportion exceeds the rainy day proportion, the real-time weather condition will be determined as heavy rain level for rainy days.

[0059] Furthermore, by combining the analysis of visible light and near-infrared bands, we can better distinguish between water reflection and bright areas caused by oil stains, shadows, and other reasons, thereby improving the accuracy and anti-interference ability of rainy weather recognition. We can also analyze image data through time series analysis to avoid the situation where the proportion of areas that are continuously present and stable or slowly increasing exceeds the preset proportion threshold and are identified as rainy weather, which may be affected by the instantaneous strong light such as vehicle headlight reflection in a single frame image data.

[0060] Furthermore, it can also identify whether the real-time weather is snowy by analyzing the white areas in the image data, and can also verify the real-time weather conditions by combining local weather forecasts.

[0061] This embodiment implements edge detection of ground reflectivity in image data through a visual feature compensation algorithm, which can accurately determine real-time weather conditions. This enables the identification of dangerous slow-moving vehicles to proactively sense adverse weather conditions and dynamically adjust the judgment conditions, improving the practicality, reliability, and safety in complex environments, and making it more realistic.

[0062] In some embodiments, adjusting the slow speed threshold and safe following distance for determining dangerous slow-moving vehicles includes: When the rain level is light rain, the slow speed threshold is reduced to the first rainy slow speed threshold, and the safe following distance is increased to the first rainy safe following distance. When the rain level is heavy rain, the slow speed threshold is reduced to the second rainy day slow speed threshold, and the safe following distance is increased to the second rainy day safe following distance. The first rainy day slow speed threshold is greater than the second rainy day slow speed threshold, and the first rainy day safe following distance is less than the second rainy day safe following distance.

[0063] Optionally, in this embodiment, when the rain level is determined to be light rain, it indicates that the road surface is starting to wet, the coefficient of friction between the tires and the road surface has decreased, the braking distance is longer than when the road surface is dry, and the impact on the driver's visibility is relatively limited. The slow speed threshold for determining dangerous slow speed can be appropriately lowered from the baseline value under clear weather to a higher first rainy slow speed threshold. That is, under light rain conditions, the tolerance for dangerous slow speed is appropriately increased. Simultaneously, considering the reduction in braking performance, the reference standard for safe following distance is raised to a relatively conservative first rainy safe following distance, reminding vehicles to maintain a relatively longer safe following distance than that corresponding to dry road surfaces.

[0064] In addition, when the rain level is heavy rain, the road environment becomes significantly more dangerous, the road surface friction coefficient decreases further, and there is a risk of hydroplaning. At the same time, the rain lines are denser during heavy rain, which severely reduces the driver's visibility. Under heavy rain conditions, the slow speed threshold is further lowered to the second rainy day slow speed threshold, which is lower than the first rainy day slow speed threshold corresponding to light rain. Simultaneously, the safe following distance is increased to a larger second rainy day safe following distance to require that adjacent vehicles maintain a sufficiently large safety buffer space.

[0065] Among them, the slow speed threshold is greater than the first rainy day slow speed threshold, the first rainy day slow speed threshold is greater than the second rainy day slow speed threshold, the safe following distance is less than the first rainy day safe following distance, and the first rainy day safe following distance is less than the second rainy day safe following distance.

[0066] Furthermore, since different road surface materials have different friction coefficient decay characteristics after wetting, different first rainy day slow speed thresholds, second rainy day slow speed thresholds, first rainy day safe following distances, and second rainy day safe following distances can be determined based on the road surface material data of the road where the target vehicle is located.

[0067] This embodiment enables the dynamic adjustment of slow speed thresholds and safe following distances by recognizing real-time weather conditions. This allows it to break free from reliance on static and fixed safety standards. By establishing a clear mapping relationship between the severity of weather and core safety parameters, the safety alert level can be reasonably increased when external conditions deteriorate, thus more accurately identifying dangerous slow-moving vehicles and improving the adaptability and accuracy of monitoring.

[0068] In some embodiments, obtaining the traffic density of the road where the current target vehicle is located, and determining the traffic state of the road where the current target vehicle is located based on a preset traffic density, includes: Based on image data, determine the total number and distribution of vehicles passing through the preset monitoring interval within the preset period, and determine the current traffic density of the road where the target vehicle is located based on the total vehicle data volume and distribution. Obtain a preset relationship mapping table between preset traffic flow density thresholds and speed ranges, determine the theoretical speed range corresponding to the current traffic flow density in the preset relationship mapping table, and determine the traffic status of the road where the current target vehicle is located based on the theoretical speed range.

[0069] Optionally, this embodiment achieves a quantitative assessment of road load within a preset monitoring interval by analyzing image data. It can count all passing vehicles within the preset monitoring interval within a preset period to obtain the total number of vehicles. At the same time, it analyzes the distribution of passing vehicles in each lane, such as whether passing vehicles are evenly distributed in each lane or densely concentrated in a certain lane. Combining the known length and number of lanes of the preset monitoring interval, the current traffic flow density is obtained, that is, the average number of vehicles per unit length of lane. The traffic flow density is used to objectively reflect the degree of road congestion.

[0070] The preset cycle can be every minute, every half minute, etc. The preset cycle needs to be set according to the traffic flow pattern and monitoring needs to ensure the accuracy and timeliness of traffic density.

[0071] In addition, a preset relationship mapping table between preset traffic flow density thresholds and speed ranges is obtained. This preset relationship mapping table is obtained based on statistical analysis of a large amount of historical traffic flow data, establishing a correspondence between speed ranges and preset traffic flow density thresholds. For example, when the preset traffic flow density threshold is less than 10 vehicles per kilometer per lane, the theoretical speed range is the current road speed limit, indicating a smooth traffic flow. When the preset traffic flow density threshold is between 10 and 25 vehicles per kilometer per lane, the theoretical speed range decreases, indicating a slow traffic flow. When the preset traffic flow density threshold is above 25 vehicles per kilometer per lane, the theoretical speed range drops to a very low level, such as 10 km / h, indicating a congested traffic flow.

[0072] In addition, the calculated real-time traffic density is substituted into a preset relational mapping table to query the theoretical speed range under the current conditions, and the traffic status of the road where the target vehicle is located is determined based on the comparison between the driving speed and the theoretical speed range.

[0073] Furthermore, it can realize the calculation of traffic flow density and the judgment of traffic conditions for each lane, and establish a preset relationship mapping table for each lane or set different preset traffic flow density thresholds to identify the non-uniform state of each lane.

[0074] This embodiment realizes a way to determine traffic status by traffic density, thereby enabling the identification of reasonable slow speeds caused by obstruction in high-density traffic flows, as well as abnormal slow speeds without clear causes in low-density traffic flows. This significantly reduces invalid alarms and driver interference in congested sections, making driver intervention highly context-sensitive, improving safety, and ensuring that the overall efficiency of road traffic is not negatively affected.

[0075] In some embodiments, after adjusting the slow speed threshold for determining dangerous slow-moving vehicles and the safe following distance, the method further includes: If the target vehicle's speed decreases beyond a preset deceleration threshold within a preset time, the target vehicle will be identified as a dangerous slow-moving vehicle. Send alert messages to dangerously slow-moving vehicles to prompt their drivers to adjust their speed.

[0076] Optionally, this embodiment continuously calculates and records the driving speed of the target vehicle, and sets a preset time window to capture abnormal driving behavior changes of the target vehicle. It also sets a preset deceleration threshold, which represents the critical value of the decrease in the driving speed of the target vehicle within a preset time. If the driving speed of the target vehicle exceeds the preset deceleration threshold, the driving speed of the target vehicle is regarded as an abnormal situation.

[0077] In addition, the current speed of the target vehicle is compared with its historical speed in real time to determine the amount of speed reduction of the target vehicle within a preset time. If the speed reduction exceeds a preset deceleration threshold, the target vehicle is marked as a dangerous slow vehicle regardless of whether its current speed is lower than the slow threshold adjusted according to traffic conditions and real-time weather conditions.

[0078] In addition, a warning message is sent to dangerously slow-moving vehicles to prompt their drivers to adjust their speed. The content of the warning message may include a request to confirm whether the vehicle is in normal condition.

[0079] Furthermore, the location of sudden deceleration events can be linked to map data to help determine whether the vehicle decelerating suddenly is in a reasonable location such as at a ramp or in front of a toll station, thereby reducing false alarms and improving the accuracy of identifying dangerous slow-moving vehicles.

[0080] This embodiment, based on adjusting the slow speed threshold and safe following distance for identifying dangerous slow-moving vehicles, adds monitoring of the dynamic changes in the target vehicle's speed. When the target vehicle's speed decreases beyond the preset deceleration threshold within a preset time, the target vehicle can be identified as a dangerous slow-moving vehicle and a warning message can be sent. This improves risk warning capabilities, allows for earlier detection of potential hazards, helps drivers adjust their speed, enhances driving safety, and reduces the risk of traffic accidents.

[0081] In some embodiments, the notification message includes a standard notification message, an escalation notification message, and a critical notification message; Send alert messages to dangerously slow-moving vehicles to prompt their drivers to adjust their speed, including: Based on the characteristic information of the target vehicle, obtain the historical driving behavior record of the target vehicle, and determine the number of times the target vehicle is a dangerous slow vehicle in the historical driving behavior record. If the number of slow speeds is less than the threshold for the first time, a standard alert message is sent to the driver of the dangerously slow vehicle. If the number of slow speeds is not less than the first threshold and less than the second threshold, an escalation warning message is sent to the driver of the dangerous slow-moving vehicle. If the number of slow-moving incidents is not less than the threshold for the second incident, a serious warning message is sent to the driver of the dangerous slow-moving vehicle, and an abnormal behavior report of the dangerous slow-moving vehicle is sent to the management platform.

[0082] Optionally, in this embodiment, the target vehicle's characteristic information is used as an index to access the corresponding historical database, obtain the target vehicle's historical driving behavior records, and determine the number of times the target vehicle was identified as a dangerous slow-moving vehicle.

[0083] Among them, the number of slow speeds can be the cumulative number of times the target vehicle has been judged as a dangerous slow vehicle within a preset period in the past. The preset period can be a calendar month, half a year, etc.

[0084] In addition, when the number of slow-moving incidents is less than the threshold for the first incident, a standard warning message is sent to the dangerously slow-moving vehicle. The content of the standard warning message is relatively concise and neutral, such as "Friendly reminder: Your current speed is low. Please keep in sync with the traffic flow to ensure safety." This is used to remind the driver to pay attention and avoid causing resentment.

[0085] If the number of slow-speed incidents is not less than the threshold for the first incident but less than the threshold for the second incident, an escalation warning message will be sent to the dangerously slow-speed vehicle. The content of the escalation warning message is more serious and can include warning language on top of the standard warning message, such as "Friendly reminder: You have been detected driving at low speeds multiple times on open roads. This behavior is likely to cause rear-end collisions. Please check your speed immediately and accelerate safely."

[0086] If the number of slow-moving incidents is not less than the threshold for the second incident, a serious message warning will be sent to the dangerous slow-moving vehicle. The content of the upgraded warning message is more serious, and additional warning language can be added to the upgraded warning message to remind the driver to stop and check whether there are any safety hazards in the target vehicle, or to increase the driving speed.

[0087] In addition, while sending a serious warning message, a report on the abnormal behavior of a dangerous slow-moving vehicle is sent to the management platform so that the management personnel may need to pay close attention to the dangerous slow-moving vehicle offline or make manual intervention.

[0088] Furthermore, a time decay factor can be introduced in the process of determining the number of slow events. For example, a higher weight can be given to recent slow events, while the weight of earlier slow events can be gradually reduced, so that the number of slow events can better reflect the driving behavior tendencies of the dangerous slow-moving vehicle.

[0089] This embodiment, based on adjusting the slow speed threshold and safe following distance for judging dangerous slow-moving vehicles, further enhances the monitoring of dynamic changes in the target vehicle's speed and sends different levels of alert messages based on the target vehicle's historical driving behavior records. This improves the targeting and effectiveness of the alerts, enabling drivers to adjust their speed more effectively and avoid traffic congestion and accidents caused by slow driving. It also enhances the accuracy of traffic management and improves the overall level of traffic management.

[0090] To effectively address the shortcomings of traditional technologies in terms of accuracy in real-time vehicle status monitoring, and to significantly improve the accuracy of vehicle status monitoring and enhance traffic flow, this application provides an embodiment of a slow vehicle identification device for implementing all or part of the aforementioned slow vehicle identification. See [link to embodiment]. Figure 2 The slow-speed vehicle identification device specifically includes the following components: The acquisition module 10 is used to collect multiple consecutive image data of the target vehicle and the driving speed of the target vehicle through multiple cameras deployed in a preset monitoring range, and to identify the feature information of the target vehicle based on the image data. The feature information includes the license plate number, body color and vehicle model of the target vehicle. The environment module 20 is used to determine the passing vehicles adjacent to the target vehicle based on feature information, determine the vehicle distance between the target vehicle and the passing vehicles, obtain the traffic density of the road where the target vehicle is currently located, and determine the traffic status of the road where the target vehicle is currently located based on the comparison result between the preset traffic density and the current traffic density. The traffic status includes congestion, slow traffic and smooth traffic. The decision module 30 is used to adjust the slow speed threshold and safe distance for judging dangerous slow vehicles based on traffic conditions, traffic density and real-time weather conditions. When the current traffic condition is smooth, the driving speed is not greater than the slow speed threshold and the distance between vehicles is greater than the safe distance, the target vehicle is identified as a dangerous slow vehicle and a prompt message is sent to the dangerous slow vehicle to prompt the driver of the dangerous slow vehicle to adjust the driving speed.

[0091] As described above, the slow vehicle recognition device provided in this application embodiment can innovatively acquire multiple consecutive image data of a target vehicle and its speed using multiple cameras deployed within a preset monitoring range. Based on the image data, it identifies the target vehicle's feature information, including the license plate number, body color, and vehicle model. It then determines adjacent passing vehicles based on this feature information, establishes the vehicle distance between the target vehicle and the passing vehicles, obtains the traffic density of the road where the target vehicle is currently located, and determines the traffic state of the road based on a preset traffic density. The traffic state includes congestion, slow traffic, and free flow. Based on the traffic state, traffic density, and real-time weather conditions, it adjusts... This method determines dangerous slow-moving vehicles by establishing a slow speed threshold and safe following distance. Under conditions of smooth traffic flow, speed not exceeding the slow speed threshold, and vehicle spacing greater than the safe following distance, the target vehicle is identified as a dangerous slow-moving vehicle. A warning message is sent to the driver of the dangerous slow-moving vehicle to prompt them to adjust their speed. By collaborating with multiple cameras and comprehensively analyzing various parameters related to the target vehicle, the method distinguishes between reasonably slow-moving and dangerous slow-moving vehicles, improving the accuracy and comprehensiveness of vehicle driving status assessment. When a dangerous slow-moving vehicle is identified, a warning is sent to its driver, allowing them to adjust their speed promptly, reducing the risk of traffic congestion and accidents caused by slow driving, and improving traffic efficiency and safety. This method effectively addresses the shortcomings of traditional technologies in terms of accuracy in real-time vehicle driving status monitoring, significantly improving the accuracy of vehicle driving status monitoring and enhancing traffic flow.

[0092] From a hardware perspective, in order to effectively address the shortcomings of traditional technologies in terms of accuracy in real-time vehicle driving status monitoring, significantly improve the accuracy of vehicle driving status monitoring, and enhance traffic flow, this application provides an embodiment of an electronic device for implementing all or part of the aforementioned slow vehicle identification method. The electronic device specifically includes the following components: The system comprises a processor, memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to realize information transmission between the slow vehicle identification device and core business systems, user terminals, and related databases and other related devices; the logic controller can be a desktop computer, tablet computer, or mobile terminal, etc., and this embodiment is not limited to these. In this embodiment, the logic controller can be implemented with reference to the embodiments of the slow vehicle identification method and the slow vehicle identification device in the embodiments, the contents of which are incorporated herein, and repeated details will not be described again.

[0093] It is understood that the user terminal may include smartphones, tablet computers, network set-top boxes, portable computers, desktop computers, personal digital assistants (PDAs), in-vehicle devices, smart wearable devices, etc. Among these, the smart wearable devices may include smart glasses, smartwatches, smart bracelets, etc.

[0094] In practical applications, parts of the slow-moving vehicle recognition method can be executed on the electronic device side as described above, or all operations can be completed in the client device. The choice can be made based on the processing power of the client device and the limitations of the user's usage scenario. This application does not impose any limitations on this. If all operations are completed in the client device, the client device may further include a processor.

[0095] The aforementioned client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side; in other implementation scenarios, it may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, a server cluster consisting of multiple servers, or a distributed server structure.

[0096] Figure 3 This is a schematic block diagram illustrating the system configuration of the electronic device 9600 according to an embodiment of this application. Figure 3As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that... Figure 3 This is an example; other types of structures can also be used to supplement or replace this structure to achieve telecommunications functions or other functions.

[0097] In one embodiment, the slow vehicle recognition method functionality can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control: Step S101: Collect multiple consecutive image data of the target vehicle and the driving speed of the target vehicle by multiple cameras deployed in the preset monitoring range, and identify the feature information of the target vehicle based on the image data, wherein the feature information includes the license plate number, body color and vehicle model of the target vehicle. Step S102: Based on feature information, determine the passing vehicles adjacent to the target vehicle, determine the vehicle distance between the target vehicle and the passing vehicles, obtain the traffic density of the road where the target vehicle is currently located, and determine the traffic status of the road where the target vehicle is currently located based on the comparison result between the preset traffic density and the current traffic density. The traffic status includes congestion, slow traffic and smooth traffic. Step S103: Based on traffic conditions, traffic density, and real-time weather conditions, adjust the slow speed threshold and safe distance for identifying dangerous slow vehicles. If the current traffic conditions are smooth, the driving speed is not greater than the slow speed threshold, and the distance between vehicles is greater than the safe distance, identify the target vehicle as a dangerous slow vehicle and send a prompt message to the driver of the dangerous slow vehicle to prompt him to adjust his driving speed.

[0098] As described above, the electronic device provided in this application innovatively acquires multiple consecutive image data of a target vehicle and its speed using multiple cameras deployed within a preset monitoring range. Based on the image data, it identifies the target vehicle's feature information, including its license plate number, body color, and vehicle model. It then determines adjacent passing vehicles based on this feature information, establishes the vehicle distance between the target vehicle and the passing vehicles, obtains the traffic density of the road where the target vehicle is currently located, and determines the traffic state of the road based on a preset traffic density. The traffic state includes congestion, slow traffic, and free flow. The system adjusts the judgment based on the traffic state, traffic density, and real-time weather conditions. This method identifies dangerous slow-moving vehicles by determining their slow speed threshold and safe following distance. Under conditions of smooth traffic flow, speed not exceeding the slow speed threshold, and vehicle spacing greater than the safe following distance, a target vehicle is designated as a dangerous slow-moving vehicle. A warning message is sent to the driver of the dangerous slow-moving vehicle to prompt them to adjust their speed. This method utilizes multi-camera collaboration and comprehensive analysis of various parameters related to the target vehicle to distinguish between reasonably slow-moving and dangerous slow-moving vehicles, improving the accuracy and comprehensiveness of vehicle driving status assessment. When a dangerous slow-moving vehicle is identified, a warning is sent to its driver, allowing them to adjust their speed promptly, reducing the risk of traffic congestion and accidents caused by slow driving, and improving traffic efficiency and safety. This method effectively addresses the shortcomings of traditional technologies in terms of accuracy in real-time vehicle driving status monitoring, significantly improving the accuracy of vehicle driving status monitoring and enhancing traffic flow.

[0099] In another embodiment, the slow vehicle recognition device can be configured separately from the central processing unit 9100. For example, the slow vehicle recognition device can be configured as a chip connected to the central processing unit 9100, and the slow vehicle recognition method function can be implemented through the control of the central processing unit.

[0100] like Figure 3 As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily need to include these components. Figure 3 All components shown; in addition, the electronic device 9600 may also include Figure 3 For components not shown, please refer to existing technologies.

[0101] like Figure 3 As shown, the central processing unit 9100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device, which receives inputs and controls the operation of various components of the electronic device 9600.

[0102] The memory 9140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 9100 may execute the program stored in the memory 9140 to perform information storage or processing, etc.

[0103] Input unit 9120 provides input to central processing unit 9100. Input unit 9120 may be, for example, a keypad or touch input device. Power supply 9170 provides power to electronic device 9600. Display 9160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0104] The memory 9140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs. The memory 9140 can also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 via the central processing unit 9100.

[0105] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for the electronic device for communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0106] The communication module 9110 is a transmitter / receiver that sends and receives signals via the antenna 9111. The communication module 9110 (transmitter / receiver) is coupled to the central processing unit 9100 to provide input signals and receive output signals, which is the same as in a conventional mobile communication terminal.

[0107] Based on different communication technologies, multiple communication modules 9110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module 9110 (transmitter / receiver) is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby realizing typical telecommunications functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 9130 is coupled to a central processing unit 9100, enabling on-device recording via the microphone 9132 and on-device playback of stored audio via the speaker 9131.

[0108] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the slow vehicle identification method with a server or client as the execution subject in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the slow vehicle identification method with a server or client as the execution subject in the above embodiments. For example, when the processor executes the computer program, it implements the following steps: Step S101: Collect multiple consecutive image data of the target vehicle and the driving speed of the target vehicle by multiple cameras deployed in the preset monitoring range, and identify the feature information of the target vehicle based on the image data, wherein the feature information includes the license plate number, body color and vehicle model of the target vehicle. Step S102: Based on feature information, determine the passing vehicles adjacent to the target vehicle, determine the vehicle distance between the target vehicle and the passing vehicles, obtain the traffic density of the road where the target vehicle is currently located, and determine the traffic status of the road where the target vehicle is currently located based on the comparison result between the preset traffic density and the current traffic density. The traffic status includes congestion, slow traffic and smooth traffic. Step S103: Based on traffic conditions, traffic density, and real-time weather conditions, adjust the slow speed threshold and safe distance for identifying dangerous slow vehicles. If the current traffic conditions are smooth, the driving speed is not greater than the slow speed threshold, and the distance between vehicles is greater than the safe distance, identify the target vehicle as a dangerous slow vehicle and send a prompt message to the driver of the dangerous slow vehicle to prompt him to adjust his driving speed.

[0109] As described above, the computer-readable storage medium provided in this application embodiment innovatively acquires continuous multiple image data of a target vehicle and its speed using multiple cameras deployed within a preset monitoring range. Based on the image data, it identifies the target vehicle's feature information, including the license plate number, body color, and vehicle model. It then determines adjacent passing vehicles based on this feature information, determines the vehicle distance between the target vehicle and passing vehicles, obtains the traffic density of the road where the target vehicle is currently located, and determines the traffic state of the road based on a preset traffic density. The traffic state includes congestion, slow traffic, and free flow. Based on the traffic state, traffic density, and real-time weather conditions, it adjusts... This method determines dangerous slow-moving vehicles by establishing a slow speed threshold and safe following distance. Under conditions of smooth traffic flow, speed not exceeding the slow speed threshold, and vehicle spacing greater than the safe following distance, the target vehicle is identified as a dangerous slow-moving vehicle. A warning message is sent to the driver of the dangerous slow-moving vehicle to prompt them to adjust their speed. By collaborating with multiple cameras and comprehensively analyzing various parameters related to the target vehicle, the method distinguishes between reasonably slow-moving and dangerous slow-moving vehicles, improving the accuracy and comprehensiveness of vehicle driving status assessment. When a dangerous slow-moving vehicle is identified, a warning is sent to its driver, allowing them to adjust their speed promptly, reducing the risk of traffic congestion and accidents caused by slow driving, and improving traffic efficiency and safety. This method effectively addresses the shortcomings of traditional technologies in terms of accuracy in real-time vehicle driving status monitoring, significantly improving the accuracy of vehicle driving status monitoring and enhancing traffic flow.

[0110] Embodiments of this application also provide a computer program product capable of implementing all steps of the slow vehicle identification method in the above embodiments, where the execution subject is a server or a client. When executed by a processor, this computer program / instruction implements the steps of the slow vehicle identification method. For example, the computer program / instruction implements the following steps: Step S101: Collect multiple consecutive image data of the target vehicle and the driving speed of the target vehicle by multiple cameras deployed in the preset monitoring range, and identify the feature information of the target vehicle based on the image data, wherein the feature information includes the license plate number, body color and vehicle model of the target vehicle. Step S102: Based on feature information, determine the passing vehicles adjacent to the target vehicle, determine the vehicle distance between the target vehicle and the passing vehicles, obtain the traffic density of the road where the target vehicle is currently located, and determine the traffic status of the road where the target vehicle is currently located based on the comparison result between the preset traffic density and the current traffic density. The traffic status includes congestion, slow traffic and smooth traffic. Step S103: Based on traffic conditions, traffic density, and real-time weather conditions, adjust the slow speed threshold and safe distance for identifying dangerous slow vehicles. If the current traffic conditions are smooth, the driving speed is not greater than the slow speed threshold, and the distance between vehicles is greater than the safe distance, identify the target vehicle as a dangerous slow vehicle and send a prompt message to the driver of the dangerous slow vehicle to prompt him to adjust his driving speed.

[0111] As described above, the computer program product provided in this application innovatively acquires continuous multiple image data of a target vehicle and its speed using multiple cameras deployed within a preset monitoring range. Based on the image data, it identifies the target vehicle's characteristic information, including its license plate number, body color, and vehicle model. It then determines adjacent passing vehicles based on this characteristic information and the distance between the target vehicle and the passing vehicles. The program also obtains the traffic density of the road where the target vehicle is currently located and determines the traffic state of the road based on a preset traffic density. The traffic state includes congestion, slow traffic, and free flow. Finally, it adjusts the system based on the traffic state, traffic density, and real-time weather conditions. This method determines the slow speed threshold and safe following distance for dangerous slow-moving vehicles. Under conditions of smooth traffic flow, speed not exceeding the slow speed threshold, and vehicle spacing greater than the safe following distance, the target vehicle is identified as a dangerous slow-moving vehicle. A warning message is sent to the driver of the dangerous slow-moving vehicle to prompt them to adjust their speed. By collaborating with multiple cameras and comprehensively analyzing various parameters related to the target vehicle, the method distinguishes between reasonably slow-moving and dangerous slow-moving vehicles, improving the accuracy and comprehensiveness of vehicle driving status assessment. When a dangerous slow-moving vehicle is identified, a warning is sent to its driver, allowing them to adjust their speed promptly, reducing the risk of traffic congestion and accidents caused by slow driving, and improving traffic efficiency and safety. This method effectively addresses the shortcomings of traditional technologies in terms of accuracy in real-time vehicle driving status monitoring, significantly improving the accuracy of vehicle driving status monitoring and enhancing traffic flow.

[0112] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0113] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0114] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0115] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0116] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A method for identifying slow-moving vehicles, characterized in that, The method includes: Multiple cameras deployed within a preset monitoring area collect continuous image data of the target vehicle and its driving speed. Based on the image data, the characteristic information of the target vehicle is identified, including the vehicle's license plate number, body color, and vehicle model. Based on the feature information, the passing vehicles adjacent to the target vehicle are determined, and the vehicle distance between the target vehicle and the passing vehicles is determined. The traffic density of the road where the target vehicle is currently located is obtained. Based on the comparison result between the preset traffic density and the current traffic density, the traffic state of the road where the target vehicle is currently located is determined. The traffic state includes congestion, slow traffic, and smooth traffic. Based on the traffic conditions, traffic density, and real-time weather conditions, the slow speed threshold and safe distance for identifying dangerous slow-moving vehicles are adjusted. When the current traffic conditions are smooth, the driving speed is not greater than the slow speed threshold, and the distance between vehicles is greater than the safe distance, the target vehicle is identified as a dangerous slow-moving vehicle, and a warning message is sent to the dangerous slow-moving vehicle to prompt its driver to adjust its driving speed.

2. The method according to claim 1, characterized in that, The step of acquiring multiple consecutive image data of the target vehicle and the driving speed of the target vehicle through multiple cameras deployed within a preset monitoring range includes: Multiple consecutive image data of the target vehicle and the timestamps corresponding to the image data are collected by multiple cameras, wherein each camera is facing the road at a preset acquisition angle; The location information of each camera is obtained, and the driving speed of the target vehicle is determined based on the timestamp and the location information.

3. The method according to claim 1, characterized in that, Before adjusting the slow speed threshold and safe following distance for determining dangerous slow-moving vehicles based on the traffic conditions, traffic density, and real-time weather conditions, the method further includes: The edge detection of ground reflectivity in the image data is performed by a visual feature compensation algorithm to obtain the proportion of water reflection area in the ground of the image data. If the proportion of the area exceeds a preset proportion threshold, the real-time weather condition is determined as rainy weather, and the rain level is determined based on the proportion of the area, wherein the rain level includes light rain level and heavy rain level.

4. The method according to claim 3, characterized in that, The adjustment of the slow speed threshold and safe following distance for determining dangerous slow-moving vehicles includes: When the rain level is light rain, the slow speed threshold is reduced to the first rainy slow speed threshold, and the safe following distance is increased to the first rainy safe following distance. When the rain level is heavy rain, the slow speed threshold is reduced to the second rainy slow speed threshold, and the safe following distance is increased to the second rainy safe following distance, wherein the first rainy slow speed threshold is greater than the second rainy slow speed threshold, and the first rainy safe following distance is less than the second rainy safe following distance.

5. The method according to claim 1, characterized in that, The step of obtaining the traffic density of the road where the target vehicle is currently located, and determining the traffic status of the road where the target vehicle is currently located based on the preset traffic density, includes: Based on the image data, determine the total number and distribution of vehicles passing through the preset monitoring interval within a preset period, and determine the current traffic density of the road where the target vehicle is located based on the total vehicle data and the distribution. Obtain a preset relationship mapping table between a preset traffic flow density threshold and a vehicle speed range, determine the theoretical vehicle speed range corresponding to the current traffic flow density in the preset relationship mapping table, and determine the traffic status of the road where the target vehicle is located based on the theoretical vehicle speed range.

6. The method according to claim 1, characterized in that, After adjusting the slow speed threshold and safe following distance for determining dangerous slow-moving vehicles, the method further includes: If the speed of the target vehicle decreases by more than a preset deceleration threshold within a preset time, the target vehicle will be identified as a dangerous slow-moving vehicle. A warning message is sent to the driver of the dangerously slow-moving vehicle to prompt him to adjust his speed.

7. The method according to claim 1, characterized in that, The notification messages include standard notification messages, escalation notification messages, and critical notification messages; Sending a warning message to the dangerously slow-moving vehicle to prompt the driver of the target vehicle to adjust the driving speed includes: Based on the characteristic information of the target vehicle, the historical driving behavior record of the target vehicle is obtained, and the number of times the target vehicle is the dangerous slow vehicle in the historical driving behavior record is determined. If the number of slow speeds is less than the threshold for the first time, the standard alert message is sent to the driver of the dangerously slow vehicle. If the number of slow speeds is not less than the first threshold and less than the second threshold, the escalation prompt message is sent to the driver of the dangerous slow-moving vehicle. If the number of slow speeds is not less than the second threshold, a serious warning message is sent to the driver of the dangerous slow-moving vehicle, and an abnormal behavior report of the dangerous slow-moving vehicle is sent to the management platform.

8. A slow-moving vehicle identification device, characterized in that, The device includes: The acquisition module is used to collect multiple consecutive image data of the target vehicle and the driving speed of the target vehicle through multiple cameras deployed in a preset monitoring range, and to identify the feature information of the target vehicle based on the image data, wherein the feature information includes the license plate number, body color and vehicle model of the target vehicle; An environment module is used to determine, based on the feature information, passing vehicles adjacent to the target vehicle, determine the vehicle distance between the target vehicle and the passing vehicles, obtain the traffic density of the road where the target vehicle is currently located, and determine the traffic state of the road where the target vehicle is currently located based on the comparison result between the preset traffic density and the current traffic density, wherein the traffic state includes congestion, slow traffic and smooth traffic. The decision module is used to adjust the slow speed threshold and safe distance for identifying dangerous slow-moving vehicles based on the traffic conditions, traffic density, and real-time weather conditions. When the current traffic conditions are smooth, the driving speed is not greater than the slow speed threshold, and the distance between vehicles is greater than the safe distance, the target vehicle is identified as a dangerous slow-moving vehicle, and a prompt message is sent to the dangerous slow-moving vehicle to prompt the driver of the dangerous slow-moving vehicle to adjust the driving speed.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the slow vehicle identification method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the slow vehicle identification method according to any one of claims 1 to 7.

Images