Road incident analysis method and device

Abstract

The application discloses a highway emergency event analysis method and device, a server method comprising: determining a key monitoring area; based on the key monitoring area, establishing an adjacent relationship between each video point and adjacent gantries corresponding to each video point; obtaining highway roadside videos of each video point in a historical time period, obtaining highway gantry data of adjacent gantries corresponding to each video point through the adjacent relationship, and determining a high-value time period according to the highway roadside videos and the highway gantry data; obtaining floating car data on a highway section in the key monitoring area, generating an abnormal clue according to traffic flow data or the floating car data in the high-value time period, the abnormal clue comprising a flow abnormal clue or a speed abnormal clue, and sending the clue to a client to determine an emergency event. Therefore, the application can improve the identification ability of the emergency event and realize differentiated and targeted monitoring of a high-risk area.

Description

Methods and devices for analyzing highway emergencies Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a method and apparatus for analyzing emergencies on highways. Background Technology

[0002] In the field of intelligent traffic management, especially in highway operation and management, a typical application scenario is handling traffic disruptions caused by emergencies such as severe weather, geological disasters, or traffic accidents. These events not only affect traffic flow but may also trigger serious safety incidents. Therefore, quickly and accurately identifying and responding to these emergencies is crucial for ensuring road traffic safety and efficiency.

[0003] Related technologies include using surveillance cameras deployed along highways to capture real-time video streams and monitoring traffic conditions and events using visual recognition technology. Alternatively, combining meteorological monitoring data can predict traffic events that may be caused by weather changes and issue early warnings. Another approach is to regularly or as needed dispatch personnel to conduct on-site inspections of highways to detect and report emergencies. However, existing monitoring methods are limited and fail to effectively utilize multiple data sources and monitoring technologies, resulting in limited ability to identify emergencies and difficulty in achieving differentiated and targeted monitoring of high-risk areas. Summary of the Invention

[0004] This application provides a method and apparatus for analyzing highway emergencies. To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0005] In a first aspect, embodiments of this application provide a method for analyzing highway emergencies, applied to a server, the method comprising:

[0006] Identify key monitoring areas

[0007] Based on key monitoring areas, establish the adjacency relationship between each video point and its corresponding adjacent gantry.

[0008] Acquire highway roadside videos for each video point within a historical time period, and obtain highway gantry data for adjacent gantries corresponding to each video point through adjacency relationships;

[0009] High-value time periods are determined based on highway roadside video and highway gantry data;

[0010] Acquire floating car data on highway sections within key monitoring areas, and generate anomaly clues based on traffic flow data or floating car data during high-value periods. Anomaly clues include traffic flow anomaly clues or speed anomaly clues.

[0011] Send traffic anomaly and speed anomaly clues to the client used for emergency investigation to determine whether there is an emergency in the abnormal road segment.

[0012] Secondly, embodiments of this application provide a method for analyzing highway emergencies, applied to a client-side application, including:

[0013] Receive traffic anomaly and speed anomaly clues sent by the server;

[0014] Determine whether there are high-speed videos with a resolution greater than a preset threshold on the road segments indicated by abnormal traffic flow clues and abnormal speed clues;

[0015] If it exists, retrieve and display the high-speed video.

[0016] If it does not exist, generate and display instructions for on-site verification.

[0017] Thirdly, embodiments of this application provide a highway emergency analysis device, the device comprising:

[0018] The extraction module is used to determine key monitoring areas and, based on these key monitoring areas, establish the adjacency relationship between each video point and its corresponding adjacent gantries.

[0019] The acquisition module is used to acquire highway roadside videos of each video point within a historical time period, and to acquire highway gantry data of adjacent gantries corresponding to each video point through adjacency relationships.

[0020] The determination module is used to determine high-value time periods based on the highway roadside video and the highway gantry data;

[0021] The generation module is used to acquire floating car data on highway sections within the key monitoring area, and generate abnormal clues based on traffic flow data during the high-value period or the floating car data. The abnormal clues include traffic flow abnormal clues or speed abnormal clues.

[0022] The sending module is used to send traffic anomaly clues and speed anomaly clues to the client used for emergency investigation in order to determine whether there is an emergency in the abnormal road segment.

[0023] The technical solutions provided in this application embodiment may include the following beneficial effects:

[0024] In this embodiment, on the one hand, traffic flow anomaly clues are generated based on highway roadside video and highway gantry data. This process not only utilizes video surveillance data but also combines it with gantry data to form a three-dimensional monitoring network. This combination enables the system to capture abnormal changes in traffic flow from multiple angles, thereby more accurately identifying emergencies. On the other hand, speed anomaly clues are generated based on floating car data. This process uses floating car data to provide real-time speed and location information, which is crucial for identifying speed changes caused by traffic accidents or other events. By combining this data with traffic flow anomaly clues, the system can more accurately monitor high-risk areas, promptly detect and respond to possible emergencies. This differentiated and targeted monitoring strategy not only improves monitoring efficiency but also enhances the response speed and processing capability for emergencies.

[0025] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0027] Figure 1 is a schematic flowchart of a method for analyzing highway emergencies provided in an embodiment of this application;

[0028] Figure 2 is a schematic diagram of a monitoring object and a sensing device provided in an embodiment of this application;

[0029] Figure 3 is a schematic diagram of a gantry and service area existing on an abnormal road section provided in this application;

[0030] Figure 4 is a schematic flowchart of a highway emergency analysis process provided in this application;

[0031] Figure 5 is a structural schematic diagram of a highway emergency analysis device provided in this application;

[0032] Figure 6 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0033] The following description and accompanying drawings fully illustrate specific embodiments of this application to enable those skilled in the art to practice them.

[0034] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0035] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0036] In the description of this application, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances. Furthermore, in the description of this application, unless otherwise stated, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0037] The method for analyzing highway emergencies provided in this application will be described in detail below with reference to Figures 1-4. This method can be implemented using a computer program and can run on a highway emergency analysis device based on the von Neumann architecture. This computer program can be integrated into the application or run as a standalone tool application.

[0038] Please refer to Figure 1, which is a flowchart illustrating a method for analyzing highway emergencies according to an embodiment of this application, applied to the server side. As shown in Figure 1, the method of this embodiment may include the following steps:

[0039] S101, determine the key monitoring area, and based on the key monitoring area, establish the adjacency relationship between each video point and the adjacent gantry corresponding to each video point;

[0040] In some embodiments of this application, the specific process of determining key monitoring areas includes: extracting high-risk facilities and road sections in the road network as key monitoring areas by using real-time acquired meteorological data, preset facility data and geological disaster data of the road network.

[0041] Meteorological data for the road network refers to meteorological information related to the road traffic network, including but not limited to data on meteorological conditions such as temperature, humidity, precipitation, wind speed, and visibility. Pre-installed facility data involves data on various infrastructures on highways, such as the location and characteristics of bridges, tunnels, toll stations, and service areas. Geological hazard data includes information on geological hazards that may affect road traffic, such as landslides, debris flows, and ground subsidence. This data is usually provided by geological monitoring departments to assess the geological hazard risk of specific areas. High-risk facilities and road sections are the result of a comprehensive analysis of meteorological data, pre-installed facility data, and geological hazard data. They refer to road sections and facilities that have a higher risk of sudden incidents due to various reasons (such as severe weather, aging facilities, and geological instability).

[0042] In some embodiments of this application, the detailed methods for determining key monitoring areas include: analyzing real-time meteorological data of the road network to identify areas in the road network where severe weather exists as screening areas; overlaying the screening areas with preset facility data and geological disaster data to extract high-risk key facilities and disaster-risk road sections as key monitoring areas; and starting a countdown to continue the step of analyzing real-time meteorological data of the road network after the preset countdown ends, so as to update the key monitoring areas in real time.

[0043] For example, areas within the road network prone to severe weather can be designated as screening zones, including areas affected by heavy rainfall, heavy snowfall, dense fog, and typhoons. By overlaying and analyzing data from these screening zones with pre-set facility data and geological hazard data, high-risk key facilities and road sections can be identified as key monitoring areas. The above calculations are performed over a time interval (e.g., 1 hour), and the key monitoring areas are updated in real time.

[0044] In other embodiments of this application, the specific method of extracting high-risk facilities and road sections in the road network as key monitoring areas by real-time acquired meteorological data, preset facility data and geological disaster data of the road network includes: determining key monitoring areas in response to the user's key monitoring area selection instruction.

[0045] For example, to meet the needs of special application scenarios (such as the security of major events), it is possible to manually select key facilities and disaster-risk sections of highways to obtain key monitoring areas.

[0046] Specifically, the establishment of adjacency relationships between each video point and its corresponding adjacent gantry, based on the key monitoring area, is explained as follows:

[0047] Video points refer to the locations of surveillance cameras installed on highways. These cameras are used to monitor road traffic conditions in real time, including vehicle flow, speed, accidents, and other anomalies. ETC gantries typically refer to ETC (Electronic Toll Collection) gantries on highways, which are distributed at different locations on the highway for automatic vehicle identification and toll collection. Adjacency relationships refer to the spatial topological relationships between detection facility points. Specifically, it refers to adjacent points that are connected in the road network topology.

[0048] In some embodiments of this application, the specific process of establishing the adjacency relationship between traffic monitoring facility locations based on key detection areas includes: unifying key detection areas, highway network data, video point data, and ETC gantry data into the same topological space; using spatial location relationships, matching the monitoring area range and detection facility locations to the corresponding locations in the highway network; and based on the connectivity of the highway network, retrieving the nearest reachable point for each path of the monitoring facility locations within the monitoring area and determining it as its adjacent point.

[0049] For example, as shown in Figure 2, the key monitoring area is a section of road in the middle. Therefore, gantry 1, gantry 2, gantry 3, video point 1, and all road sections in Figure 2 can be considered as relevant monitoring equipment in the key monitoring area. Among them, the ETC gantry mainly senses traffic flow information on the highway; the video equipment uses AI to identify traffic flow data and encrypts and fills in blind spots at the ETC gantry points; the highway section serves as a data carrier for GPS floating car data, monitoring vehicle traffic status.

[0050] Among them, adjacent gantries of video points can be obtained based on key monitoring areas and adjacent relationships;

[0051] Among them, the adjacent gantries of the video point refer to the ETC gantries that are closest to the video point on each reachable path in the highway network.

[0052] In some embodiments of this application, the specific process of obtaining adjacent gantries of video points based on the key monitoring area and the adjacency relationship of the points includes: searching for topologically adjacent ETC gantry points at both ends of the key monitoring area; taking the road segment range between adjacent ETC gantry points as the monitoring range; obtaining all ETC gantries, all video points, and highway segments within the monitoring range; starting from the location of each video point, searching upstream and downstream along the road to retrieve its adjacent gantries from all ETC gantries; associating each video point with the adjacent gantries retrieved for each video point to obtain the adjacency relationship between each video point and its corresponding adjacent gantries. S102, obtaining highway roadside videos of each video point within a historical time period, and obtaining highway gantry data of the adjacent gantries corresponding to each video point through the adjacency relationship;

[0053] The historical time period refers to a period of time in the past, which can be several hours, several days, or longer. Highway roadside video refers to video data captured by video surveillance systems installed along highways. Highway gantry data refers to data collected by ETC gantries installed on highways, including information such as the time, speed, and traffic flow of vehicles passing through the gantries.

[0054] S103, Based on the highway roadside video and the highway gantry data, determine the high-value time period;

[0055] High-value periods refer to the periods with good lighting conditions and high vehicle recognition accuracy remaining after excluding periods of poor lighting conditions at night when the video recognition rate is low.

[0056] In some embodiments of this application, high-value time periods are determined based on highway roadside video and highway gantry data: the historical time period is divided into multiple sub-time periods; the number of vehicles in each sub-time period is identified and counted in the highway roadside video to obtain the video traffic of each sub-time period; the gantry traffic of the adjacent gantries corresponding to each video point in each sub-time period is obtained from the highway gantry data; the difference ratio of each period is calculated based on the video traffic and the gantry traffic of each sub-time period; and the sub-time periods with a difference ratio less than a preset ratio threshold are designated as high-value time periods.

[0057] For example, the difference ratio If flow_pro is greater than a given percentage threshold, the time period is considered unavailable; otherwise, it is considered a high-value time period.

[0058] Artificial intelligence technology is used to extract vehicle targets from highway roadside videos, and the number of passing vehicles is counted at 5-minute intervals as usable traffic flow data. For example, identifying vehicles in each sub-time period of highway roadside videos can be done using a pre-trained neural network model. This model can identify target vehicles in the video, and it can be an existing trained model capable of identifying target objects; the relevant training process will not be elaborated here.

[0059] S105: Acquire floating car data on highway sections within the key monitoring area, and generate abnormal clues based on traffic flow data or floating car data during high-value periods. Abnormal clues include abnormal traffic flow clues or abnormal speed clues.

[0060] Among them, traffic flow data during high-value periods includes video traffic and gantry traffic.

[0061] Among these, the high-value time periods of video location data are the extracted usable time periods, while the usable time periods for ETC gantries are all day. Using these two data sources together can significantly improve coverage and increase detection speed. Traffic anomaly characteristics refer to significant differences between traffic flow and normal traffic flow, such as abnormally zero traffic flow or abnormally sudden drops in traffic flow. Traffic anomaly clues refer to clues containing information such as time and spatial location extracted based on the traffic anomaly characteristics of traffic monitoring facilities.

[0062] Specifically, the process of generating anomaly clues based on the traffic flow data during the high-value period includes: unifying the video traffic and gantry traffic during the high-value period as facilities; identifying high-value facilities, which are facilities in the road network whose traffic flow exceeds a preset traffic threshold within a preset time period; selecting high-value facilities in key monitoring areas from all high-value facilities as facilities to be analyzed; and generating traffic anomaly clues based on the gantry data and the facilities to be analyzed.

[0063] For example, when identifying high-value facilities, a fixed time interval is used as the statistical interval to count the total daily flow of facilities nationwide. Given a flow threshold σ, if the flow of a facility reaches σ in a certain time period, then this facility is a high-value facility in that time period; otherwise, it is a low-value facility in that time period.

[0064] Specifically, the process of generating traffic anomaly clues based on gantry data and the facilities to be analyzed includes: determining the maximum and minimum traffic flow, and the corresponding times of the maximum and minimum traffic flow for the facilities to be analyzed within a preset period based on the gantry data; determining whether the facilities to be analyzed meet preset traffic drop conditions based on the maximum and minimum traffic flow, and the corresponding times of the maximum and minimum traffic flow; designating the facilities to be analyzed that meet the preset traffic drop conditions as traffic anomaly facilities; and designating the traffic anomaly facilities and their associated abnormal road sections as traffic anomaly clues; wherein, the preset traffic drop conditions are: flow max and flow min The maximum and minimum flow rates within a preset period t, t max and t min These represent the times corresponding to the maximum and minimum flow rates, respectively.

[0065] S106, Based on floating car data, generate speed anomaly clues;

[0066] Floating car data includes floating car trajectories. Floating car data is collected through devices installed on moving vehicles (such as GPS trackers and speed sensors), and includes information such as the vehicle's position, speed, and direction of travel. Speed ​​anomaly cues refer to indications found through analysis of floating car data that significantly deviate from normal driving speeds.

[0067] In some embodiments of this application, the specific process of generating speed anomaly clues based on floating car data includes: identifying vehicles that decelerate rapidly and stop based on the floating car data; and generating speed anomaly clues based on the vehicles that decelerate rapidly and stop. The floating car data includes floating car trajectories.

[0068] Specifically, the process of determining vehicles that decelerate rapidly and stop based on floating car data includes: calculating the floating car speed based on the floating car trajectory; calculating the floating car deceleration based on the floating car speed; and identifying vehicles whose deceleration exceeds a preset threshold to obtain the vehicles that decelerate rapidly and stop.

[0069] For example, given a rapid deceleration threshold of a max_acc Calculate the deceleration 'a' of the floating car. 减 If a is satisfied 减 >a max_acc If the floating car decelerates rapidly, then the floating car will stop. Calculate the current speed v of the floating car. If v = 0, then the floating car will stop.

[0070] Specifically, the process of generating speed anomaly clues based on vehicles that decelerate suddenly and stop includes: matching the road segments to which the vehicles that decelerate suddenly and stop belong as abnormal road segments from the road network; counting the number of vehicles that decelerate suddenly and stop within a preset single statistical period; and when the number of vehicles exceeds a preset threshold, using the matched abnormal road segments and their associated key monitoring areas as speed anomaly clues.

[0071] For example, the number n of vehicles exhibiting sudden deceleration or stopping behavior on abnormal road sections within a preset single statistical period is counted. If n is greater than or equal to a given threshold n, the result is considered. abnormal If so, the road segment is considered an abnormal road segment, and the abnormal road segment and its associated key monitoring objects are considered clues to speed anomalies.

[0072] S107, send traffic anomaly clues and speed anomaly clues to the client used for emergency investigation to determine whether there is an emergency in the abnormal road segment.

[0073] For example, abnormal traffic and speed clues can be quickly sent to the client applications of relevant responsible units and individuals via SMS.

[0074] In some embodiments of this application, the process by which the client determines whether there is a sudden event in an abnormal road segment is as follows: receiving traffic anomaly clues and speed anomaly clues sent by the server; determining whether there is a high-speed video with a clarity greater than a preset threshold in the road segment indicated by the traffic anomaly clues and speed anomaly clues; if there is, retrieving the high-speed video for display; if not, generating on-site verification indication information for display.

[0075] For example, if there is clear and usable highway video of the abnormal road section, relevant personnel will retrieve the relevant real-time video for video inspection; if there is no usable highway video of the clue road section, the relevant unit and responsible person will conduct on-site verification. Clues that are verified correctly by manual verification will be manually marked and fed back to the server.

[0076] In some embodiments, the server receives investigation results from the client; when the investigation results indicate that there is a sudden event in the traffic flow abnormality clues and speed abnormality clues, the server determines the upstream gantries, downstream gantries, and service areas existing on the target road segment in the investigation results; and the server counts the vehicle information entering the upstream gantries within the target time period to obtain the first set of vehicles entering the target road segment. By collecting information on vehicles leaving the downstream gantry within the target time period, a second set of vehicles leaving the target road segment is obtained. By statistically analyzing the vehicle information entering the service area within the target time period, a third set of vehicles entering the service area is obtained. By collecting information on vehicles leaving the service area within the target time period, a fourth set of vehicles leaving the service area is obtained. Based on the first vehicle set, the second vehicle set, the third vehicle set, and the fourth vehicle set, count the number of vehicles affected by the emergency. Among them, the collection of disaster-stricken vehicles The calculation method is as follows:

[0077] For example, as shown in Figure 3, the abnormal road segment corresponds to the upstream gantry, the downstream gantry, and the service area.

[0078] In other embodiments, the server receives the investigation results from the client; when the investigation results indicate that there is a sudden event in the clues of abnormal traffic flow and abnormal speed, the server publishes relevant information about the sudden event in a preset manner; wherein, the preset manner is any one of ETC publishing software, WeChat official account, operating platform and roadside terminal.

[0079] Furthermore, this information on emergencies and affected vehicles can be promptly shared with traffic management departments and other relevant departments to provide data support for emergency relief and disaster relief.

[0080] For example, as shown in Figure 4, which is a schematic flowchart of a highway emergency analysis process provided in this application, key monitoring areas can be identified first based on meteorological data, key facility data, and disaster risk data on the highway. Alternatively, key monitoring areas can be identified through manual screening. For key monitoring areas, AI-based traffic flow recognition of highway video data, combined with highway gantry data, can be used to discover abnormal traffic flow clues. Floating car data can be used to discover abnormal speed clues. Finally, based on these abnormal traffic flow and speed clues, multi-source data monitoring and verification, investigation of affected vehicles, and dissemination of emergency information can be conducted.

[0081] In this embodiment, on the one hand, traffic flow anomaly clues are generated based on highway roadside video and highway gantry data. This process not only utilizes video surveillance data but also combines it with gantry data to form a three-dimensional monitoring network. This combination enables the system to capture abnormal changes in traffic flow from multiple angles, thereby more accurately identifying emergencies. On the other hand, speed anomaly clues are generated based on floating car data. This process uses floating car data to provide real-time speed and location information, which is crucial for identifying speed changes caused by traffic accidents or other events. By combining this data with traffic flow anomaly clues, the system can more accurately monitor high-risk areas, promptly detect and respond to possible emergencies. This differentiated and targeted monitoring strategy not only improves monitoring efficiency but also enhances the response speed and processing capability for emergencies.

[0082] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0083] Please refer to Figure 5, which shows a schematic diagram of the structure of a highway emergency analysis device provided in an exemplary embodiment of this application. This highway emergency analysis device can be implemented as all or part of an electronic device through software, hardware, or a combination of both. The device 1 includes an extraction module 10, an acquisition module 20, a determination module 30, a generation module 40, and a transmission module 50.

[0084] Extraction module 10 is used to determine key monitoring areas and, based on key monitoring areas, establish the adjacency relationship between each video point and its corresponding adjacent gantry.

[0085] The acquisition module 20 is used to acquire highway roadside videos of each video point within a historical time period, and to acquire highway gantry data of adjacent gantries corresponding to each video point through adjacency relationships.

[0086] Module 30 is used to determine high-value time periods based on highway roadside video and highway gantry data;

[0087] The generation module 40 is used to acquire floating car data on highway sections within the key monitoring area, and generate abnormal clues based on traffic flow data during the high-value period or the floating car data. The abnormal clues include traffic flow abnormal clues or speed abnormal clues.

[0088] The sending module 50 is used to send traffic anomaly clues and speed anomaly clues to the client used for emergency investigation in order to determine whether there is an emergency in the abnormal road segment.

[0089] It should be noted that the highway emergency analysis device provided in the above embodiments is only illustrated by the division of the above functional modules when executing the highway emergency analysis method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the highway emergency analysis device and the highway emergency analysis method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0090] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0091] In this embodiment, on the one hand, traffic flow anomaly clues are generated based on highway roadside video and highway gantry data. This process not only utilizes video surveillance data but also combines it with gantry data to form a three-dimensional monitoring network. This combination enables the system to capture abnormal changes in traffic flow from multiple angles, thereby more accurately identifying emergencies. On the other hand, speed anomaly clues are generated based on floating car data. This process uses floating car data to provide real-time speed and location information, which is crucial for identifying speed changes caused by traffic accidents or other events. By combining this data with traffic flow anomaly clues, the system can more accurately monitor high-risk areas, promptly detect and respond to possible emergencies. This differentiated and targeted monitoring strategy not only improves monitoring efficiency but also enhances the response speed and processing capability for emergencies.

[0092] This application also provides a computer-readable medium having program instructions stored thereon, which, when executed by a processor, implement the highway emergency event analysis method provided in the above-described method embodiments.

[0093] This application also provides a computer program product containing instructions that, when run on a computer, causes the computer to execute the highway emergency analysis method of the various method embodiments described above.

[0094] Please refer to Figure 6, which is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. As shown in Figure 6, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0095] The communication bus 1002 is used to realize the connection and communication between these components.

[0096] The user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0097] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0098] The processor 1001 may include one or more processing cores. The processor 1001 connects to various parts within the electronic device 1000 using various interfaces and lines. It executes various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005. Optionally, the processor 1001 may be implemented using at least one hardware form selected from Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1001 may integrate one or more of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip, without being integrated into the processor 1001.

[0099] The memory 1005 may include random access memory (RAM) or read-only memory. Optionally, the memory 1005 may include a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), instructions for implementing the various method embodiments described above, etc.; the data storage area may store data involved in the various method embodiments described above, etc. Optionally, the memory 1005 may also be at least one storage system located remotely from the aforementioned processor 1001. As shown in FIG6, the memory 1005, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a highway emergency analysis application.

[0100] In the electronic device 1000 shown in Figure 6, the user interface 1003 is mainly used to provide an input interface for the user and to obtain the user's input data; while the processor 1001 can be used to call the highway emergency analysis application stored in the memory 1005 and specifically perform the following operations:

[0101] Identify key monitoring areas, and based on these areas, establish the adjacency relationships between each video point and its corresponding adjacent gantries.

[0102] Acquire highway roadside videos for each video point within a historical time period, and obtain highway gantry data for adjacent gantries corresponding to each video point through adjacency relationships;

[0103] High-value time periods are determined based on highway roadside video and highway gantry data;

[0104] Acquire floating car data on highway sections within key monitoring areas, and generate anomaly clues based on traffic flow data during high-value periods or the floating car data. The anomaly clues include traffic flow anomaly clues or other anomaly clues.

[0105] Send traffic anomaly and speed anomaly clues to the client used for emergency investigation to determine whether there is an emergency in the abnormal road segment.

[0106] In one embodiment, the processor 1001, when determining high-value time periods based on highway roadside video and highway gantry data, specifically performs the following operations:

[0107] Divide the historical period into multiple sub-periods;

[0108] Identify and count the number of vehicles in each sub-time period of highway roadside video to obtain the video traffic for each sub-time period;

[0109] From the highway gantry data, obtain the gantry traffic of the adjacent gantries corresponding to each video point in each sub-time period;

[0110] Calculate the difference ratio for each period based on the video traffic and gantry traffic for each sub-period;

[0111] Sub-periods with a difference ratio less than a preset ratio threshold are designated as high-value periods.

[0112] In one embodiment, when the processor 1001 generates anomaly clues based on the traffic flow data during the high-value period, it specifically performs the following operations:

[0113] The video traffic and gantry traffic during the high-value periods will be treated as a unified facility.

[0114] High-value facilities are identified as those in the road network whose traffic flow is greater than a preset traffic flow threshold within a preset time period.

[0115] From all high-value facilities, high-value facilities within the key monitoring area were selected as the facilities to be analyzed;

[0116] Based on the gantry data and the facility to be analyzed, anomaly clues are generated.

[0117] In one embodiment, when the processor 1001 generates traffic anomaly clues based on the gantry data and the facility to be analyzed, it specifically performs the following operations:

[0118] Based on the gantry data, determine the maximum and minimum flow rates of the facility to be analyzed within a preset period, and the time corresponding to the maximum and minimum flow rates;

[0119] Based on the maximum and minimum flow rates and the times corresponding to the maximum and minimum flow rates, it is determined whether the facility to be analyzed meets the preset flow drop condition;

[0120] Facilities to be analyzed that meet the preset conditions for a sudden drop in flow are classified as flow anomaly facilities.

[0121] The aforementioned traffic anomaly facilities and their associated abnormal road sections are considered as clues to traffic anomalies; wherein,

[0122] The preset traffic drop condition is: flow max and flow min The maximum and minimum flow rates within a preset period t, t max and t min These represent the times corresponding to the maximum and minimum flow rates, respectively.

[0123] In one embodiment, when processor 1001 generates speed anomaly clues based on floating car data, it specifically performs the following operations:

[0124] Based on the floating car data, determine vehicles that decelerate rapidly and stop.

[0125] Based on the sudden deceleration and stopping of the vehicle, generate speed anomaly clues;

[0126] From the road network, the road segments to which the vehicles that suddenly decelerated and stopped belong are identified as abnormal road segments;

[0127] The number of vehicles that rapidly decelerate and stop within a preset single statistical period is counted;

[0128] When the number of vehicles exceeds a preset threshold, the matched abnormal road segments and their associated key monitoring areas will be used as speed anomaly clues.

[0129] In one embodiment, when the processor 1001 generates speed anomaly clues based on sudden deceleration and stopping of the vehicle, it specifically performs the following operations:

[0130] From the road network, identify the road segments where vehicles that decelerate suddenly or stop as abnormal road segments;

[0131] The number of vehicles that decelerate rapidly and stop within a preset single statistical period is counted.

[0132] When the number of vehicles exceeds a preset threshold, the matched abnormal road segments and their associated key monitoring areas will be used as clues to speed anomalies.

[0133] In one embodiment, the processor 1001 also performs the following operations:

[0134] Receive the investigation results from the client;

[0135] When the investigation results indicate that there is a sudden event due to abnormal traffic flow or abnormal speed, identify the upstream gantries, downstream gantries, and service areas on the target road segment in the investigation results.

[0136] By collecting information on vehicles entering the upstream gantry within the target time period, the first set of vehicles entering the target road segment is obtained.

[0137] By collecting information on vehicles leaving the downstream gantry within the target time period, a second set of vehicles leaving the target road segment is obtained.

[0138] By statistically analyzing the vehicle information entering the service area within the target time period, a third set of vehicles entering the service area is obtained.

[0139] By collecting information on vehicles leaving the service area within the target time period, a fourth set of vehicles leaving the service area is obtained.

[0140] Based on the first vehicle set, the second vehicle set, the third vehicle set, and the fourth vehicle set, count the number of vehicles affected by the emergency. in,

[0141] Collection of disaster-stricken vehicles The calculation method is as follows:

[0142] In one embodiment, the processor 1001 also performs the following operations:

[0143] Receive the investigation results from the client;

[0144] When the investigation results indicate that abnormal traffic flow or speed suggests an emergency, relevant information about the emergency will be released through pre-defined methods; among them,

[0145] The default method is any one of the following: ETC publishing software, WeChat official account, operating platform, and roadside terminal.

[0146] In this embodiment, on the one hand, traffic flow anomaly clues are generated based on highway roadside video and highway gantry data. This process not only utilizes video surveillance data but also combines it with gantry data to form a three-dimensional monitoring network. This combination enables the system to capture abnormal changes in traffic flow from multiple angles, thereby more accurately identifying emergencies. On the other hand, speed anomaly clues are generated based on floating car data. This process uses floating car data to provide real-time speed and location information, which is crucial for identifying speed changes caused by traffic accidents or other events. By combining this data with traffic flow anomaly clues, the system can more accurately monitor high-risk areas, promptly detect and respond to possible emergencies. This differentiated and targeted monitoring strategy not only improves monitoring efficiency but also enhances the response speed and processing capability for emergencies.

[0147] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program for analyzing highway emergencies can be stored in a computer-readable storage medium. When executed, the program can include the processes of the embodiments of the above methods. The storage medium for the highway emergency analysis program can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.

[0148] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A method for analyzing emergencies on highways, characterized in that, Applied to the server side, the method includes: determining key monitoring areas; establishing adjacency relationships between each video point and its corresponding adjacent gantries based on the key monitoring areas; acquiring highway roadside videos of each video point within a historical time period, and obtaining highway gantry data of the adjacent gantries corresponding to each video point through the adjacency relationships; dividing the historical time period into multiple sub-time periods; identifying and counting the number of vehicles in each sub-time period of the highway roadside videos to obtain the video traffic of each sub-time period; and obtaining the adjacent gantries corresponding to each video point from the highway gantry data. The system measures the gantry traffic flow in each sub-time period; calculates the difference ratio between the video traffic flow and the gantry traffic flow in each sub-time period; designates sub-time periods with a difference ratio less than a preset threshold as high-value time periods; acquires floating car data on highway sections within the key monitoring area, and generates anomaly clues based on the traffic flow data or the floating car data in the high-value time periods, including traffic flow anomaly clues or speed anomaly clues; and sends the traffic flow anomaly clues and the speed anomaly clues to a client for investigating emergencies to determine whether an emergency exists in the abnormal road section.

2. The method according to claim 1, characterized in that, The traffic flow data during the high-value period includes video traffic and gantry traffic; generating anomaly clues based on the traffic flow data during the high-value period includes: identifying high-value facilities, which are facilities in the road network whose traffic flow data for each traffic monitoring facility exceeds a preset traffic threshold within a preset time period; selecting high-value facilities in the key monitoring area from all high-value facilities as facilities to be analyzed; and generating traffic anomaly clues based on the gantry data and the facilities to be analyzed.

3. The method according to claim 2, characterized in that, The step of generating traffic anomaly clues based on the gantry data and the facility to be analyzed includes: determining, based on the gantry data, the maximum and minimum traffic flows of the facility to be analyzed within a preset period, and the times corresponding to the maximum and minimum traffic flows; determining, based on the maximum and minimum traffic flows and the times corresponding to the maximum and minimum traffic flows, whether the facility to be analyzed meets a preset traffic drop condition; designating the facility to be analyzed that meets the preset traffic drop condition as a traffic anomaly facility; and designating the traffic anomaly facility and its associated abnormal road segment as traffic anomaly clues; wherein, the preset traffic drop condition is: ， and The maximum and minimum flow rates within a preset period t. and These represent the times corresponding to the maximum and minimum flow rates, respectively.

4. The method according to claim 1, characterized in that, The step of generating speed anomaly clues based on the floating car data includes: identifying vehicles that decelerate rapidly and stop based on the floating car data; generating speed anomaly clues based on the vehicles that decelerate rapidly and stop; matching the road segments to which the vehicles that decelerate rapidly and stop belong from the road network as abnormal road segments; counting the number of vehicles that decelerate rapidly and stop within a preset single statistical period; and when the number of vehicles exceeds a preset threshold, using the matched abnormal road segments and their associated key monitoring areas as speed anomaly clues.

5. The method according to claim 1, characterized in that, The determination of key monitoring areas includes: analyzing real-time meteorological data of the road network to identify areas in the road network where severe weather is likely to occur as screening areas; overlaying the screening areas with preset facility data and geological disaster data to extract high-risk key facilities and disaster-risk road sections as key monitoring areas, and starting a countdown to continue the step of analyzing real-time meteorological data of the road network after the preset countdown ends, so as to update the key monitoring areas in real time; or, in response to the user's key monitoring area selection command, determining the key monitoring areas.

6. The method according to any one of claims 1-5, characterized in that, After sending the traffic anomaly clues and speed anomaly clues to the client for emergency investigation, the method further includes: receiving investigation results from the client; when the investigation results indicate that there is an emergency related to the traffic anomaly clues and speed anomaly clues, determining the upstream gantries, downstream gantries, and service areas existing on the target road segment in the investigation results; and statistically analyzing the vehicle information entering the upstream gantries within the target time period to obtain a first set of vehicles entering the target road segment. ; Collect information on vehicles leaving the downstream gantry within the target time period to obtain a second set of vehicles leaving the target road segment. ; Collect vehicle information entering the service area within the target time period to obtain a third set of vehicles entering the service area. ; Collect information on vehicles leaving the service area within the target time period to obtain a fourth set of vehicles leaving the service area. Based on the first vehicle set, the second vehicle set, the third vehicle set, and the fourth vehicle set, calculate the set of vehicles affected by the emergency. Among them, the affected vehicles were gathered. The calculation method is as follows: 。 7. The method according to any one of claims 1-5, characterized in that, After sending the traffic anomaly clues and the speed anomaly clues to the client for emergency investigation, the method further includes: receiving the investigation results from the client; when the investigation results indicate that there is an emergency related to the traffic anomaly clues and the speed anomaly clues, publishing relevant information about the emergency in a preset manner; wherein, the preset manner is any one of ETC publishing software, WeChat official account, operating platform, and roadside terminal.

8. A method for analyzing highway emergencies implemented according to any one of claims 1-5, characterized in that, Applied to the client, the method includes: receiving traffic anomaly clues and speed anomaly clues sent by the server; determining whether there is a high-speed video with a clarity greater than a preset threshold in the road segment indicated by the traffic anomaly clues and speed anomaly clues; if there is, retrieving the high-speed video and displaying it; if not, generating on-site verification indication information and displaying it.

9. A highway emergency analysis device, characterized in that, The device includes: an extraction module for determining key monitoring areas and establishing an adjacency relationship between each video point and its corresponding adjacent gantries based on the key monitoring areas; an acquisition module for acquiring highway roadside videos of each video point within a historical time period and acquiring highway gantry data of the adjacent gantries corresponding to each video point through the adjacency relationship; and a determination module for determining high-value time periods based on the highway roadside videos and the highway gantry data. Determining high-value time periods based on the highway roadside videos and highway gantry data includes: dividing the historical time period into multiple sub-time periods; identifying and counting the number of vehicles in each sub-time period from the highway roadside videos, and obtaining the video data for each sub-time period. The system includes: a video traffic flow rate; obtaining the gantry traffic flow of adjacent gantries corresponding to each video point in each sub-time period from the highway gantry data; calculating the difference ratio between the video traffic flow and the gantry traffic flow in each sub-time period; designating sub-time periods with a difference ratio less than a preset threshold as high-value time periods; a generation module for obtaining floating car data on highway sections within the key monitoring area, and generating abnormal clues based on the traffic flow data or floating car data in the high-value time periods, the abnormal clues including traffic flow abnormal clues or speed abnormal clues; and a sending module for sending the traffic flow abnormal clues and the speed abnormal clues to a client for investigating emergencies to determine whether there are emergencies in the abnormal road sections.

Images