Expressway traffic condition detection management method, device, equipment and medium

Abstract

The invention relates to a highway traffic condition detection management method, device and equipment and a medium, and is applied to the technical field of traffic management, and the method comprises the steps: obtaining video data, weather data and road information; identifying the video data based on an image identification model, and determining abnormal information, the abnormal information including an abnormal type and an abnormal position; if the number of the abnormal information is larger than 1, abnormal association is determined based on the abnormal information, and the abnormal association is association among multiple pieces of abnormal information when the multiple pieces of abnormal information exist; and determining an exception management strategy based on the exception association, the weather data and the road information. The method has the effect of improving the traffic condition detection management efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of traffic management, and in particular to a method, device, equipment and medium for detecting and managing highway traffic conditions. Background Art

[0002] With the rapid development of highway construction and traffic demand in my country, the total mileage of highways has continued to grow, among which expressways have developed particularly rapidly. As expressways have the characteristics of good linearity, high design standards, large traffic flow, and high driving speed, most travelers choose to take expressways, which has also led to a sharp increase in traffic flow, and traffic congestion and traffic accidents have become increasingly serious. If accidents or traffic jams are not handled in a timely manner, it will inevitably affect the operating efficiency of the expressway, causing huge losses to the expressway operating company, and also bring inconvenience to road users. Therefore, the timely handling of expressway accidents and congestion is of great significance.

[0003] Although many video surveillance systems have been established on highways, striving to achieve full coverage monitoring of the entire road section without blind spots, due to the limited energy of monitoring personnel and the limited number of images displayed at the same time, it is impossible to pay attention to all road conditions in real time, and thus it is impossible to promptly discover and deal with accidents and congestion on the highway, resulting in low efficiency in traffic condition detection and management. Summary of the invention

[0004] In order to improve the efficiency of traffic condition detection and management, the present application provides a highway traffic condition detection and management method, device, equipment and medium.

[0005] In the first aspect, the present application provides a method for detecting and managing highway traffic conditions, which adopts the following technical solutions: A method for detecting and managing highway traffic conditions, comprising: Obtain video data, weather data, and road information; Identify the video data based on an image recognition model to determine abnormal information, where the abnormal information includes an abnormal type and an abnormal location; If the number of the abnormal information is greater than 1, determining an abnormal association based on the abnormal information, wherein the abnormal association is an association between multiple abnormal information when there are multiple abnormal information; An anomaly management strategy is determined based on the anomaly association, the weather data, and the road information.

[0006] By adopting the above technical solution, video data can be quickly identified through the image recognition model, so that abnormal information on the highway can be discovered in time, improving the efficiency of abnormal detection. When there are multiple abnormal information, the abnormal correlation between the multiple abnormal information is determined, and the abnormal management strategy is determined by combining weather data and road information, thereby improving the accuracy of the abnormal management strategy, so that abnormal handling can be carried out in a timely and accurate manner, improving the efficiency of traffic condition detection and management.

[0007] Optionally, the identifying the video data based on an image recognition model to determine abnormal information includes: Identify the video data based on an image recognition model to obtain a recognition result, wherein the recognition result includes an abnormal type, an abnormal location, and an abnormal vehicle; If the abnormality type is an accident type, obtaining guardrail monitoring data and abnormal vehicle information; Determining an abnormality level based on the guardrail monitoring data and the abnormal vehicle information; Abnormality information is determined based on the abnormality level and the recognition result.

[0008] By adopting the above technical solution, the video data is identified through the image recognition model to obtain the recognition result. When the abnormal type in the recognition result is an accident type, the abnormal level is determined by the guardrail monitoring data and the abnormal vehicle information, and the abnormal information is determined jointly by the abnormal level and the recognition result, thereby improving the reliability and richness of the abnormal information.

[0009] Optionally, determining the abnormality level based on the guardrail monitoring data and the abnormal vehicle information includes: determining a collision level based on the guardrail monitoring data; determining the vehicle type and the number of vehicles based on the vehicle information; determining an accident level based on the vehicle type and the number of vehicles; An abnormality level is determined based on the collision level and the accident level.

[0010] By adopting the above technical solution, when determining the abnormality level, the collision level, vehicle type and number of vehicles are fully considered, so that the abnormality level is more reliable, the referenceability of the abnormality level is improved, and the abnormal information is determined according to the abnormality level, which improves the reliability of the abnormal information.

[0011] Optionally, determining the abnormal association based on the abnormal information includes: Determine the abnormal location and abnormal time based on the abnormal information; Dividing the abnormal information based on the abnormal positions to obtain at least one abnormal combination, wherein the abnormal positions in each abnormal combination are located in the same road section; Sorting the abnormal information in each abnormal combination according to the abnormal time to obtain a sorting result; Determine a first abnormal association between two adjacent abnormal information based on the sorting result and the preset association; Determine a second abnormal association of the abnormal combination based on the first abnormal association of the two adjacent abnormal information; An abnormal correlation is determined based on the first abnormal correlation and the second abnormal correlation.

[0012] By adopting the above technical solution, when determining the abnormal association, the location of the abnormal information is first considered, that is, whether the abnormal information is in the same road section, and then the first abnormal association between two adjacent abnormal information is determined according to the abnormal time and the preset association, and then the second abnormal association of the abnormal combination is determined according to the first abnormal association between the two adjacent abnormal information, that is, in the same road section, the association between two abnormal information is first determined according to the time sequence and the preset association, and then the association between multiple abnormal information is determined, which improves the reliability of the abnormal association, determines the abnormal management strategy through the abnormal association, and improves the accuracy of the abnormal management strategy, so that the abnormality can be handled in a timely and accurate manner, and the efficiency of traffic condition detection and management is improved.

[0013] Optionally, the determining an abnormality management strategy based on the abnormality association, the weather data, and the road information includes: Determine the first abnormal information in the abnormal association as the originating abnormal information; Determine an originating abnormality type based on the originating abnormality information; Determining whether on-site processing is required based on the originating abnormality type; If on-site processing is required, obtain staff information; Determine the arrival time based on the staff information, the weather data and the road information; An abnormality management strategy is determined based on the arrival time, the weather data, the road information, and the abnormality information.

[0014] By adopting the above technical solution, when determining the exception management strategy, the originating exception information is first determined based on the exception association, that is, the initial situation that caused the exception in the exception association to occur, and whether on-site processing is required is determined based on the originating exception type. If on-site processing is required, the arrival time is determined based on the staff information, weather data and road information, and the exception management strategy is determined based on the arrival time, weather data, road information and exception information, that is, the exception is processed from the source of the exception, thereby improving the efficiency of exception handling.

[0015] Optionally, the determining an abnormality management strategy based on the arrival time, the weather data, the road information, and the abnormality information includes: Obtaining an exception handling duration based on the originating exception type; Determining an exception handling level based on the exception handling duration and the weather data; Determine processing personnel information based on the exception processing level and the personnel information; Determining an exception handling strategy based on the processing personnel information, the road information, and the originating exception information; Determine an estimated dredging time based on the arrival time and the exception handling time; Determine the congestion situation based on the abnormal information and the estimated dredging time; Determine an impact processing strategy based on the abnormal information, the congestion situation and the road information; An exception management policy is determined based on the exception handling policy and the impact handling policy.

[0016] Optionally, the determining of the impact processing strategy based on the abnormal information, the congestion situation and the road information includes: determining a traversable width based on the video data; Determine a congestion area and a deceleration area based on the congestion situation, the passable width and the road information; Determining passable vehicles based on the congested area and the passable width; determining a recommended driving speed based on the deceleration area and the weather conditions; An impact handling strategy is determined based on the passable vehicles and the recommended driving speed.

[0017] By adopting the above technical solution, when there is congestion in the abnormal information, the efficiency of congestion clearing is improved by determining the congestion area and passable vehicles, and the possibility of further aggravation of congestion is reduced by determining the deceleration area and the recommended driving speed, thereby improving the efficiency of abnormal handling.

[0018] In the second aspect, the present application provides a highway traffic condition detection and management device, which adopts the following technical solution: A highway traffic condition detection and management device, comprising: A data acquisition module, used to acquire video data, weather data and road information; A video recognition module, used to recognize the video data based on an image recognition model and determine abnormal information, wherein the abnormal information includes an abnormal type and an abnormal location; An association determination module, configured to determine an abnormal association based on the abnormal information if the number of the abnormal information is greater than 1, wherein the abnormal association is an association between multiple abnormal information when multiple abnormal information exist; An anomaly management module is used to determine an anomaly management strategy based on the anomaly association, the weather data and the road information.

[0019] By adopting the above technical solution, video data can be quickly identified through the image recognition model, so that abnormal information on the highway can be discovered in time, improving the efficiency of abnormal detection. When there are multiple abnormal information, the abnormal correlation between the multiple abnormal information is determined, and the abnormal management strategy is determined by combining weather data and road information, thereby improving the accuracy of the abnormal management strategy, so that abnormal handling can be carried out in a timely and accurate manner, improving the efficiency of traffic condition detection and management.

[0020] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device comprises a processor, wherein the processor is coupled to a memory; The memory stores a computer program that can be loaded by the processor and execute the highway traffic condition detection and management method described in any one of the first aspects.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and execute the highway traffic condition detection and management method described in any one of the first aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a highway traffic condition detection and management method provided in an embodiment of the present application.

[0023] Figure 2 It is a structural block diagram of a highway traffic condition detection and management device provided in an embodiment of the present application.

[0024] Figure 3It is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The present application is further described in detail below in conjunction with the accompanying drawings.

[0026] The embodiment of the present application provides a method for detecting and managing highway traffic conditions, which can be executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a desktop computer, etc., but is not limited thereto.

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0029] like Figure 1 As shown, a method for detecting and managing highway traffic conditions is described below (steps S101 to S104): Step S101: Acquire video data, weather data, and road information.

[0030] Multiple visible light and infrared cameras are installed on the highway. The visible light and infrared cameras switch between day and night to monitor road traffic conditions in real time, obtain video data from each visible light and infrared camera, obtain weather data from the meteorological department, and obtain road information from the traffic management department. The road information includes but is not limited to road name, road length, road location, section information, and number of lanes.

[0031] Step S102: Identify the video data based on the image recognition model to determine abnormal information.

[0032] Exception information includes exception type and exception location.

[0033] The video data is recognized by a pre-trained image recognition model to identify various types of abnormal events and corresponding abnormal locations on the highway. The abnormal types include parking, wrong-way driving, pedestrians, spilled objects, congestion, construction, accidents, departure, speeding, etc. The image recognition model can be implemented by a deep learning target detection algorithm such as the Yolov5 model, which is not specifically limited here.

[0034] Optionally, the video data is identified based on an image recognition model to determine abnormal information, including: identifying the video data based on the image recognition model to obtain a recognition result, the recognition result including the abnormal type, abnormal location and abnormal vehicle; if the abnormal type is an accident type, obtaining guardrail monitoring data and abnormal vehicle information; determining the abnormal level based on the guardrail monitoring data and abnormal vehicle information; determining the abnormal information based on the abnormal level and the recognition result.

[0035] In this embodiment, video data is identified through an image recognition model to obtain the abnormal type, abnormal position and abnormal vehicle (which can be represented by the license plate number), that is, the identification result. If the abnormal type is an accident type, the guardrail number corresponding to the abnormal position is searched from the database according to the abnormal position. Monitoring sensors such as pressure sensors and vibration sensors are installed on the guardrail, and guardrail monitoring data monitored by the guardrail monitoring sensor is obtained from the database through the guardrail number. Abnormal vehicle information is obtained from the transportation department through the abnormal vehicle. The abnormal vehicle information includes vehicle type and owner information, etc. The abnormal level of the accident is determined through the guardrail monitoring data and the abnormal vehicle information, and the abnormal level and the identification result are jointly determined as abnormal information.

[0036] Furthermore, determining the abnormality level based on the guardrail monitoring data and the abnormal vehicle information includes: determining the collision level based on the guardrail monitoring data; determining the vehicle type and the number of vehicles based on the vehicle information; determining the accident level based on the vehicle type and the number of vehicles; and determining the abnormality level based on the collision level and the accident level.

[0037] In this embodiment, the database stores the correspondence between guardrail monitoring data and collision level, and the collision level is searched from the database based on the guardrail monitoring data. The vehicle type of the accident vehicle is searched from the vehicle information, and the number of vehicle information, i.e. the number of vehicles involved in the accident, is counted. The database stores the correspondence between vehicle type, number of vehicles and accident level, and the accident level is searched from the database based on the vehicle type and number of vehicles. The database also stores the correspondence between collision level, accident level and abnormal level, and the abnormal level is searched from the database based on the collision level and accident level.

[0038] Step S103: If the amount of abnormal information is greater than 1, determine the abnormal association based on the abnormal information.

[0039] The abnormal association is the association between multiple abnormal information when there are multiple abnormal information.

[0040] When an abnormal situation occurs on a highway, it often leads to other abnormal situations. That is, there is a causal relationship between several abnormalities. For example, when a traffic accident occurs, it is often accompanied by congestion. By analyzing the relationship between abnormalities and finding the initial cause of the abnormality, it is easier to solve the abnormal situation.

[0041] Specifically, determining abnormal associations based on abnormal information includes: determining abnormal positions and abnormal time based on the abnormal information; dividing the abnormal information based on the abnormal positions to obtain at least one abnormal combination, and the abnormal positions in each abnormal combination are in the same road section; sorting the abnormal information in each abnormal combination according to the abnormal time to obtain a sorting result; determining a first abnormal association between two adjacent abnormal information based on the sorting result and a preset association; determining a second abnormal association between the abnormal combination based on the first abnormal association between the two adjacent abnormal information; and determining the abnormal association based on the first abnormal association and the second abnormal association.

[0042] In this embodiment, when there are multiple abnormal information, the abnormal position and abnormal time are searched from the abnormal information. The possibility of association between abnormalities in different sections is small, so the abnormal association is determined in sections, wherein the sections are pre-divided and are not specifically limited here. The abnormal information of the same section is divided into an abnormal combination according to the abnormal position to obtain at least one abnormal combination. The abnormal information in each abnormal combination is sorted from front to back according to the abnormal time to obtain at least one sorting result. Each abnormal combination corresponds to a sorting result, and a preset association is obtained from the database. The preset association is a rule for judging whether there is an association between two adjacent abnormal information according to the abnormal type and abnormal time. For example: if the abnormal types of two adjacent abnormal information are accident and congestion respectively, and the abnormal time of the two adjacent abnormal information is If the time interval between the two adjacent abnormal information is less than the preset time length, there is an association between the two adjacent abnormal information. According to the sorting result and the preset association, it is determined whether there is an association between all the two adjacent abnormal information, and the association relationship between all the two adjacent abnormal information is determined as the first abnormal association. The association relationship is transitive. According to the first abnormal association and the transitivity of the association relationship, the association relationship between multiple abnormal information is determined, so as to obtain the second abnormal association of each abnormal combination. For example, the abnormal combination includes 3 abnormal information, and the 3 abnormal information are 1, 2, and 3 respectively. The sorting result according to the abnormal time is 1→2→3, among which 1 and 2 are abnormally associated, and 2 and 3 are abnormally associated. According to the transitivity of the association relationship, 1 and 3 are also abnormally associated. All the first abnormal associations and the second abnormal associations are jointly determined as abnormal associations.

[0043] Step S104: determining an abnormality management strategy based on abnormality association, weather data and road information.

[0044] Specifically, an exception management strategy is determined based on exception association, weather data and road information, including: determining the first exception information in the exception association as the originating exception information; determining the originating exception type based on the originating exception information; determining whether on-site processing is required based on the originating exception type; if on-site processing is required, obtaining staff information; determining the arrival time based on the staff information, weather data and road information; determining the exception management strategy based on the arrival time, weather data, road information and exception information.

[0045] In this embodiment, the first abnormal information that occurs earliest among all abnormal associations, that is, is determined as the originating abnormal information. It can also be understood that the abnormal time of the abnormal information associated with the originating abnormal information is later than the abnormal time of the originating abnormal information. The abnormal type of the originating abnormal information is determined as the originating abnormal type, that is, the originating abnormal type is the initial abnormal type that causes at least one abnormal information to occur. The database stores the corresponding relationship between the abnormal type and whether on-site processing is required. For example, if the abnormal type is an accident, on-site processing is required; if the abnormal type is speeding, on-site processing is not required. According to the originating abnormal type, whether the originating abnormal information needs on-site processing is searched from the database. If on-site processing is required, the staff information corresponding to the originating abnormal type is obtained from the traffic department. The arrival time required for the staff to arrive at the abnormal position is calculated according to the staff position in the staff information, the current weather data, and the road information. Specifically, the distance is calculated according to the staff position, the abnormal position, and the route in the road information. The recommended driving speed is obtained from the database according to the current weather data. The arrival time=distance / recommended driving speed. The abnormal management strategy is determined based on the arrival time, weather data, road information, and abnormal information.

[0046] If the originating exception information does not need to be processed on-site, the corresponding exception management strategy can be searched from the strategy database according to the exception type corresponding to the exception information, such as issuing an early warning, which will not be repeated here.

[0047] Specifically, an exception management strategy is determined based on arrival time, weather data, road information and exception information, including: obtaining exception handling time based on the originating exception type; determining the exception handling level based on the exception handling time and weather data; determining the handling personnel information based on the exception handling level and staff information; determining the exception handling strategy based on the handling personnel information, road information and originating exception information; determining the expected clearing time based on arrival time and exception handling time; determining the congestion situation based on the exception information and the expected clearing time; determining the impact handling strategy based on the exception information, congestion situation and road information; determining the exception management strategy based on the exception handling strategy and the impact handling strategy.

[0048] In this embodiment, different types of exception handling have different durations. The exception handling duration is obtained from the database according to the originating exception type. The database stores the correspondence between the exception handling duration, weather data and exception handling level. The exception handling level is obtained from the database according to the exception handling duration and weather data. Since the staff have different levels of exception handling, different exception handling levels require different handlers. The staff information includes the exception handling level that the staff can handle. Therefore, the handler information can be determined according to the exception handling level and the staff information. The exception handling strategy is to send road information and originating exception information to the handler, and send all exception information of the section to the drivers of the section and adjacent sections via wireless or Bluetooth, so that the handler can understand the abnormal situation in advance and arrive at the abnormal location as soon as possible for processing, and the drivers of the section and adjacent sections can understand the abnormal situation in more detail, so as to re-plan the route or slow down as needed.

[0049] Exception information other than the originating exception information is determined as associated exception information. If the exception type corresponding to the associated exception information does not include the congestion type, there is no congestion. According to the exception type corresponding to the associated exception information, the associated processing strategy corresponding to the exception type is obtained from the database, and the exception processing strategy and the associated exception strategy are jointly determined as the exception management strategy.

[0050] The congestion situation includes the estimated clearing time, congestion location, congested vehicles and the number of congested vehicles. If the abnormal type corresponding to the abnormal information includes the congestion type, the arrival time and the abnormal processing time are added to obtain the estimated clearing time, the abnormal location and the abnormal vehicle are found from the abnormal information, and the number of abnormal vehicles is counted. The abnormal location is determined as the congested location, the abnormal vehicle is determined as the congested vehicle, and the number of abnormal vehicles is determined as the number of congested vehicles, thereby obtaining the congestion situation. The impact processing strategy is determined according to the abnormal information, congestion situation and road information, that is, the processing strategy of the associated abnormal information, and the exception processing strategy and the impact processing strategy are jointly determined as the exception management strategy.

[0051] Specifically, the impact handling strategy is determined based on the abnormal information, congestion conditions and road information, including: determining the passable width based on video data; determining the congested area and the deceleration area based on the congested area and the passable width; determining the passable vehicles based on the congested area and the passable width; determining the recommended driving speed based on the deceleration area and weather conditions; determining the impact handling strategy based on the passable vehicles and the recommended driving speed.

[0052] In this embodiment, when congestion occurs, the number of passable lanes is obtained by identifying video data, and the passable width = the number of passable lanes × lane width. The length of the congestion area and the length of the deceleration area are found from the database according to the congestion situation and the passable width. The length of the congestion area and the length of the deceleration area both decrease as the passable width increases. The congestion end position is calculated according to the abnormal position and the length of the congestion area, and the area between the abnormal position and the congestion end position is determined as the congestion area through road information. The deceleration end position is calculated according to the congestion end position and the length of the deceleration area, and the area between the congestion end position and the deceleration end position is determined as the deceleration area through road information. Vehicles in the congestion area whose vehicle width is less than the passable width are determined as passable vehicles. The recommended driving speed is found from the data according to the length of the deceleration area and weather conditions. The impact processing strategy is to send sequential passage information to passable vehicles and send recommended driving speed information to vehicles in the deceleration area.

[0053] After step S102, if there is only one abnormal information, the corresponding abnormal management policy can be searched from the policy database according to the abnormal type corresponding to the abnormal information, such as issuing an early warning, which will not be repeated here.

[0054] Figure 2 This is a structural block diagram of a highway traffic condition detection and management device 200 provided in an embodiment of the present application.

[0055] like Figure 2 As shown, the highway traffic condition detection and management device 200 mainly includes: Data acquisition module 201, used to acquire video data, weather data and road information; The video recognition module 202 is used to recognize the video data based on the image recognition model and determine abnormal information, where the abnormal information includes the abnormal type and abnormal location; The association determination module 203 is used to determine an abnormal association based on the abnormal information if the number of abnormal information is greater than 1. The abnormal association is the association between multiple abnormal information when there are multiple abnormal information. The anomaly management module 204 is used to determine anomaly management strategies based on anomaly association, weather data, and road information.

[0056] As an optional implementation of this embodiment, the video recognition module 202 is also specifically used to identify video data based on an image recognition model and determine abnormal information, including: identifying video data based on an image recognition model to obtain a recognition result, the recognition result including the abnormal type, abnormal location and abnormal vehicle; if the abnormal type is an accident type, obtaining guardrail monitoring data and abnormal vehicle information; determining the abnormal level based on the guardrail monitoring data and abnormal vehicle information; determining the abnormal information based on the abnormal level and the recognition result.

[0057] As an optional implementation of this embodiment, the video recognition module 202 is also specifically used to determine the abnormality level based on guardrail monitoring data and abnormal vehicle information, including: determining the collision level based on guardrail monitoring data; determining the vehicle type and the number of vehicles based on vehicle information; determining the accident level based on the vehicle type and the number of vehicles; determining the abnormality level based on the collision level and the accident level.

[0058] As an optional implementation of this embodiment, the association determination module 203 is also specifically used to determine abnormal associations based on abnormal information, including: determining the abnormal position and abnormal time based on the abnormal information; dividing the abnormal information based on the abnormal position to obtain at least one abnormal combination, and the abnormal position in each abnormal combination is in the same road section; sorting the abnormal information in each abnormal combination according to the abnormal time to obtain a sorting result; determining a first abnormal association between two adjacent abnormal information based on the sorting result and a preset association; determining a second abnormal association of the abnormal combination based on the first abnormal association of two adjacent abnormal information; determining the abnormal association based on the first abnormal association and the second abnormal association.

[0059] As an optional implementation of this embodiment, the exception management module 204 is also specifically used to determine the exception management strategy based on exception association, weather data and road information, including: determining the first exception information in the exception association as the originating exception information; determining the originating exception type based on the originating exception information; determining whether on-site processing is required based on the originating exception type; if on-site processing is required, obtaining staff information; determining the arrival time based on the staff information, weather data and road information; determining the exception management strategy based on the arrival time, weather data, road information and exception information.

[0060] As an optional implementation of this embodiment, the exception management module 204 is also specifically used to determine the exception management strategy based on the arrival time, weather data, road information and exception information, including: obtaining the exception processing time based on the originating exception type; determining the exception processing level based on the exception processing time and weather data; determining the processing personnel information based on the exception processing level and staff information; determining the exception processing strategy based on the processing personnel information, road information and the originating exception information; determining the expected clearing time based on the arrival time and the exception processing time; determining the congestion situation based on the exception information and the expected clearing time; determining the impact processing strategy based on the exception information, congestion situation and road information; determining the exception management strategy based on the exception processing strategy and the impact processing strategy.

[0061] As an optional implementation of this embodiment, the exception management module 204 is also specifically used to determine the impact processing strategy based on the exception information, congestion conditions and road information, including: determining the passable width based on video data; determining the congested area and the deceleration area based on the congested area and the passable width; determining the passable vehicles based on the congested area and the passable width; determining the recommended driving speed based on the deceleration area and weather conditions; determining the impact processing strategy based on the passable vehicles and the recommended driving speed.

[0062] In one example, the module in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0063] For another example, when the modules in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0064] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0065] Figure 3A structural block diagram of an electronic device 300 provided in an embodiment of the present application.

[0066] like Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302 , and may further include an information input / information output (I / O) interface 303 , one or more of a communication component 304 , and a communication bus 305 .

[0067] The processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps of the above-mentioned highway traffic condition detection management method; the memory 302 is used to store various types of data to support the operation of the electronic device 300, and these data may include, for example, instructions for any application or method operated on the electronic device 300, and data related to the application. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0068] The I / O interface 303 provides an interface between the processor 301 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 304 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 304 can include: Wi-Fi components, Bluetooth components, NFC components.

[0069] The electronic device 300 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the highway traffic condition detection and management method given in the above embodiment.

[0070] The communication bus 305 may include a path to transmit information between the above components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 may be divided into an address bus, a data bus, a control bus, etc.

[0071] The electronic device 300 may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and may also be servers, etc.

[0072] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned highway traffic condition detection and management method are implemented.

[0073] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0074] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0075] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A method for detecting and managing highway traffic conditions, characterized in that: include: Obtain video data, weather data, and road information; Identify the video data based on an image recognition model to determine abnormal information, where the abnormal information includes an abnormal type and an abnormal location; If the number of the abnormal information is greater than 1, determining an abnormal association based on the abnormal information, wherein the abnormal association is an association between multiple abnormal information when there are multiple abnormal information; An anomaly management strategy is determined based on the anomaly association, the weather data, and the road information.

2. The method according to claim 1, characterized in that The identifying the video data based on the image recognition model to determine abnormal information includes: Identify the video data based on an image recognition model to obtain a recognition result, wherein the recognition result includes an abnormal type, an abnormal location, and an abnormal vehicle; If the abnormality type is an accident type, obtaining guardrail monitoring data and abnormal vehicle information; Determining an abnormality level based on the guardrail monitoring data and the abnormal vehicle information; Abnormality information is determined based on the abnormality level and the recognition result.

3. The method according to claim 2, characterized in that The determining of the abnormality level based on the guardrail monitoring data and the abnormal vehicle information includes: determining a collision level based on the guardrail monitoring data; determining the vehicle type and the number of vehicles based on the vehicle information; determining an accident level based on the vehicle type and the number of vehicles; An abnormality level is determined based on the collision level and the accident level.

4. The method according to claim 1, characterized in that: The determining the abnormal association based on the abnormal information includes: Determine the abnormal location and abnormal time based on the abnormal information; Dividing the abnormal information based on the abnormal positions to obtain at least one abnormal combination, wherein the abnormal positions in each abnormal combination are located in the same road section; Sorting the abnormal information in each abnormal combination according to the abnormal time to obtain a sorting result; Determine a first abnormal association between two adjacent abnormal information based on the sorting result and the preset association; Determine a second abnormal association of the abnormal combination based on the first abnormal association of two adjacent abnormal information; An abnormal correlation is determined based on the first abnormal correlation and the second abnormal correlation.

5. The method according to claim 1, characterized in that The determining of an abnormality management strategy based on the abnormality association, the weather data, and the road information includes: Determine the first abnormal information in the abnormal association as the originating abnormal information; Determine an originating abnormality type based on the originating abnormality information; Determining whether on-site processing is required based on the originating abnormality type; If on-site processing is required, obtain staff information; Determine the arrival time based on the staff information, the weather data and the road information; An abnormality management strategy is determined based on the arrival time, the weather data, the road information, and the abnormality information.

6. The method according to claim 5, characterized in that The determining of an abnormality management strategy based on the arrival time, the weather data, the road information, and the abnormality information includes: Obtaining an exception handling duration based on the originating exception type; Determining an exception handling level based on the exception handling duration and the weather data; Determine processing personnel information based on the exception processing level and the personnel information; Determining an exception handling strategy based on the processing personnel information, the road information, and the originating exception information; Determine an estimated dredging time based on the arrival time and the exception handling time; Determine the congestion situation based on the abnormal information and the estimated dredging time; Determine an impact processing strategy based on the abnormal information, the congestion situation and the road information; An exception management policy is determined based on the exception handling policy and the impact handling policy.

7. The method according to claim 6, characterized in that The determining of the impact processing strategy based on the abnormal information, the congestion situation and the road information includes: determining a traversable width based on the video data; Determine a congestion area and a deceleration area based on the congestion situation, the passable width and the road information; Determining passable vehicles based on the congested area and the passable width; determining a recommended driving speed based on the deceleration area and the weather conditions; An impact handling strategy is determined based on the passable vehicles and the recommended driving speed.

8. A highway traffic condition detection and management device, characterized in that: include: A data acquisition module, used to acquire video data, weather data and road information; A video recognition module, used to recognize the video data based on an image recognition model and determine abnormal information, wherein the abnormal information includes an abnormal type and an abnormal location; An association determination module, configured to determine an abnormal association based on the abnormal information if the number of the abnormal information is greater than 1, wherein the abnormal association is an association between multiple abnormal information when multiple abnormal information exist; An anomaly management module is used to determine an anomaly management strategy based on the anomaly association, the weather data and the road information.

9. An electronic device, characterized in that: comprising a processor coupled to a memory; The processor is configured to execute a computer program stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The method comprises a computer program or an instruction, which, when executed on a computer, causes the computer to execute the method according to any one of claims 1 to 7.

Images