Traffic jam detection method, device, equipment and medium
By collecting road vibration signals through an optical fiber vibration sensor network and combining sliding window and spatiotemporal continuity judgment, the problem of all-weather accuracy and independence of existing traffic congestion detection has been solved, realizing all-weather and accurate traffic congestion detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-19
- Publication Date
- 2026-03-13
AI Technical Summary
Existing traffic congestion detection technologies cannot achieve accurate independent detection around the clock, as they are limited by lighting conditions, weather conditions, and reliance on external data.
By using fiber optic vibration sensor networks to collect road vibration signals, determining traffic flow levels by dividing and accumulating vibration values through sliding windows, and assessing traffic congestion risk by combining spatiotemporal continuity, a mapping relationship between traffic flow levels and intensity is constructed to achieve all-weather, independent traffic congestion detection.
It enables all-weather, accurate traffic congestion detection, reduces reliance on external data, improves the independence and reliability of detection, avoids false alarms, and enhances the accuracy and robustness of detection results.
Smart Images
Figure CN121661842A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent transportation technology, specifically to a traffic congestion detection method, device, equipment, and medium. Background Technology
[0002] Traffic congestion is a major challenge facing modern cities. It not only reduces road efficiency and increases travel time and costs, but also leads to energy waste, increased emissions, and a higher risk of traffic accidents. Therefore, real-time and accurate detection of traffic congestion is crucial for achieving intelligent traffic management and dynamic guidance.
[0003] Currently, common traffic congestion detection technologies mainly rely on the following methods: 1. Video image-based technologies: These capture traffic flow images using cameras and analyze vehicle density and speed using computer vision algorithms. However, this method is severely limited by lighting conditions (such as nighttime or backlighting) and weather factors (such as rain, snow, and fog), and also has limitations in installation angle and privacy concerns. 2. Fixed-point sensing technologies: Such as loop coils and geomagnetic sensors. While these technologies are relatively mature and accurate, they need to be buried under the road surface, resulting in high installation and maintenance costs. Construction can also disrupt traffic, and they only provide discrete point data, making it difficult to comprehensively reflect the overall continuous traffic status of a road segment. 3. Wireless signal-based technologies: Such as those using microwave radar or mobile communication signaling data. Radar is susceptible to multipath effects and interference from complex environments, while signaling data depends on user mobile phone penetration and operator cooperation, resulting in unstable data sources, user privacy protection, and limited positioning accuracy.
[0004] In recent years, fiber optic sensing technology has been introduced into the field of traffic monitoring due to its advantages such as resistance to electromagnetic interference, corrosion resistance, and the ability to achieve long-distance distributed measurement. Therefore, to address the technical problems of the aforementioned methods, some existing solutions attempt to use fiber optic vibration signals to sense vehicle traffic. However, these solutions mostly remain at the level of vehicle counting or speed estimation, or still rely on the fusion with external data such as vehicle GPS and mobile phone signaling to determine congestion, failing to fully leverage the inherent advantages of fiber optic sensing—achieving independent detection across all weather conditions and road sections solely based on roadside physical signals.
[0005] Therefore, there is an urgent need to provide a traffic congestion detection method, device, equipment, and medium that can achieve all-weather, highly reliable traffic congestion detection relying solely on fiber optic vibration sensor networks. Summary of the Invention
[0006] In view of this, it is necessary to provide a traffic congestion detection method, device, equipment and medium to solve the technical problem that existing technologies cannot achieve all-weather and accurate detection of traffic congestion through a single fiber optic vibration sensor network.
[0007] To address the aforementioned technical problems, in a first aspect, the present invention provides a traffic congestion detection method, comprising: The vibration signal matrix of multiple lanes within a preset time period is acquired, and the vibration signal matrix is preprocessed to obtain the traffic flow trajectory matrix; the vibration signal matrix is acquired based on the fiber optic vibration sensing network laid in the road. The traffic flow trajectory matrix is divided based on a sliding window to obtain multiple local trajectory matrices and the cumulative vibration value of each local trajectory matrix, and the traffic flow level of each local trajectory matrix is determined based on the cumulative vibration value. Determine whether the local trajectory matrix corresponding to a traffic flow level greater than a preset level is continuous in time and space. If it is continuous, then it is determined that the road has a risk of traffic congestion.
[0008] In one possible implementation, the traffic flow trajectory matrix is a two-dimensional matrix with two dimensions: time and distance. The sliding window has overlapping portions in both the time and distance dimensions.
[0009] In one possible implementation, determining the traffic flow level of each of the local trajectory matrices based on the accumulated vibration values includes: Establish a mapping relationship between traffic flow levels and traffic flow intensity ranges; The accumulated vibration value is used as the traffic flow intensity value, and the traffic flow level of the local trajectory matrix is determined based on the traffic flow intensity value and the mapping relationship.
[0010] In one possible implementation, after determining that the road has a risk of traffic congestion, the method further includes: Multiple local trajectory matrices that are continuous in time and space are identified as a congestion cluster; The local trajectory matrix at the downstream end of the traffic flow direction in the congestion cluster is taken as the current local trajectory matrix; Search in the opposite direction of the traffic flow direction of the road, and within a preset search range, find a target local trajectory matrix whose traffic flow level is greater than or equal to that of the current local trajectory matrix. If the target local trajectory matrix exists, and the spatiotemporal distance between the target local trajectory matrix and the current local trajectory matrix is greater than a preset distance, then the road segment between the current local trajectory matrix and the target local trajectory matrix is determined to be a congested road segment, and the start and end information of the congested road segment is output.
[0011] In one possible implementation, the spatiotemporal distance between the current local trajectory matrix and the target local trajectory matrix is a weighted sum of the temporal distance and the mileage distance between the current local trajectory matrix and the target local trajectory matrix.
[0012] In one possible implementation, when there is no traffic flow level greater than or equal to the current local trajectory matrix within the preset search range, the method further includes: Record the mileage and time corresponding to the current local trajectory matrix, and mark the current local trajectory matrix as a potential congestion endpoint; After a preset delay, the time length of the sliding window is increased, and the congested road segment is re-determined.
[0013] In one possible implementation, the vibration signal matrix is preprocessed to obtain a traffic flow trajectory matrix, including: The vibration signal matrix is filtered and binarized sequentially to obtain the traffic flow trajectory matrix.
[0014] Secondly, the present invention also provides a traffic congestion detection device, comprising: The vehicle trajectory matrix determination unit is used to acquire vibration signal matrices of multiple lanes within a preset time period, and preprocess the vibration signal matrices to obtain a traffic flow trajectory matrix; the vibration signal matrix is acquired based on an optical fiber vibration sensing network laid in the road. The traffic flow level determination unit is used to divide the traffic flow trajectory matrix based on a sliding window, obtain multiple local trajectory matrices and the cumulative vibration value of each local trajectory matrix, and determine the traffic flow level of each local trajectory matrix based on the cumulative vibration value. The traffic congestion determination unit is used to determine whether the local trajectory matrix corresponding to a traffic flow level greater than a preset level is continuous in time and space. If it is continuous, it is determined that there is a risk of traffic congestion on the road.
[0015] Thirdly, the present invention also provides a traffic congestion detection device, comprising an optical fiber sensor network, a memory, and a processor, wherein... The fiber optic sensing network is used to collect vibration signals from the road in real time. The memory is used to store programs; The processor, coupled to the memory and the fiber optic sensor network, is used to execute the program stored in the memory to implement the steps in the traffic congestion detection method described in any of the above possible implementations.
[0016] Fourthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps of the traffic congestion detection method described in any of the above possible implementations.
[0017] The beneficial effects of this invention are as follows: The traffic congestion detection method provided by this invention only needs to be based on the vibration signal matrix obtained by fiber optic vibration sensing to detect traffic congestion, completely independent of vehicle terminals (such as GPS), mobile communication networks, or user mobile phone data, achieving independent roadside detection. In other words, it reduces the dependence of the traffic congestion detection method on complex external data sources, improving the independence and reliability of traffic congestion detection. Simultaneously, because the fiber optic sensor network itself is insensitive to weather conditions such as illumination, rain, snow, and fog, this method can work stably in scenarios where traditional visual methods fail, such as at night or in severe weather, achieving all-weather congestion detection.
[0018] Furthermore, this invention employs a two-stage detection method to determine the risk of traffic congestion: a coarse detection based on traffic flow level and a fine detection based on spatiotemporal continuity. Traffic flow level is determined by accumulating vibration values, discretizing and standardizing continuous traffic conditions to provide a clear quantitative benchmark for judgment. Then, only when the local trajectory matrix meeting the coarse detection criteria exhibits continuity in both time and space is a congestion risk deemed to exist. This mechanism fundamentally distinguishes between instantaneous traffic density and continuous traffic congestion, avoiding frequent false alarms caused by temporary vehicle aggregation and instantaneous signal fluctuations, thus significantly improving the accuracy of the detection results. Attached Figure Description
[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0020] Figure 1 A schematic flowchart of an embodiment of the traffic congestion detection method provided by the present invention; Figure 2 A schematic diagram of an embodiment of the present invention for determining congested road sections; Figure 3 This is a schematic flowchart of an embodiment of the processing method provided by the present invention when the target local trajectory matrix cannot be found within a preset search range; Figure 4 A schematic diagram of an embodiment of the traffic congestion detection device provided by the present invention; Figure 5 This is a schematic diagram of an embodiment of the traffic congestion detection device provided by the present invention. Detailed Implementation
[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.
[0022] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this invention illustrate operations implemented according to some embodiments of the invention. It should be understood that the operations in the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed or performed simultaneously. Furthermore, those skilled in the art, guided by the content of this invention, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.
[0023] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0024] This invention provides a traffic congestion detection method, apparatus, equipment, and medium, which are described below.
[0025] Figure 1 This is a schematic flowchart of an embodiment of the traffic congestion detection method provided by the present invention, as shown below. Figure 1 As shown, traffic congestion detection methods include: S101. Obtain the vibration signal matrix of multiple lanes within a preset time period, and preprocess the vibration signal matrix to obtain the traffic flow trajectory matrix; the vibration signal matrix is obtained based on the fiber optic vibration sensing network laid in the road.
[0026] The preset time period can be set according to actual needs, and no specific limitation is made here.
[0027] Specifically, the traffic flow trajectory matrix is a two-dimensional matrix, with the two dimensions being the time dimension and the mileage dimension.
[0028] Furthermore, to improve the precision of congestion detection, in some embodiments of the present invention, the traffic flow trajectory matrix can also be a three-dimensional matrix, with the third dimension being the lane dimension, which records the vibration signal of each lane at different times and different distances.
[0029] S102. Divide the traffic flow trajectory matrix based on the sliding window to obtain multiple local trajectory matrices and the cumulative vibration value of each local trajectory matrix, and determine the traffic flow level of each local trajectory matrix based on the cumulative vibration value.
[0030] The cumulative vibration value is the sum of multiple vibration values within the sliding window.
[0031] S103. Determine whether the local trajectory matrix corresponding to the traffic flow level greater than the preset level is continuous in time and space. If it is continuous, determine that there is a risk of traffic congestion on the road.
[0032] The preset levels can be set or adjusted according to the actual application scenario, which will not be elaborated here.
[0033] It should be noted that the principle of congestion risk detection in this embodiment of the invention is as follows: when road congestion occurs, the traffic flow in the congested section increases significantly, and since vehicle movement has spatiotemporal continuity, congestion also has spatiotemporal continuity. Therefore, this embodiment of the invention detects the existence of traffic congestion risk by characterizing the traffic flow level and spatiotemporal continuity, so as to achieve accurate and reliable traffic congestion detection.
[0034] It should be understood that the traffic congestion detection method in this embodiment of the invention can be implemented in any device based on the traffic congestion detection method, such as electronic devices like decision-making devices or management devices based on traffic congestion detection results. Specifically, the traffic congestion detection method is stored in the aforementioned device as a pre-programmed program. When the device is started, the program is invoked, and the traffic congestion detection method is implemented.
[0035] Compared with existing technologies, the traffic congestion detection method provided in this invention only needs to acquire a vibration signal matrix based on fiber optic vibration sensing to detect traffic congestion. It is completely independent of vehicle terminals (such as GPS), mobile communication networks, or user mobile phone data, achieving independent roadside detection. In other words, it reduces the dependence of traffic congestion detection methods on complex external data sources, improving the independence and reliability of traffic congestion detection. Furthermore, since the fiber optic sensor network itself is insensitive to weather conditions such as illumination, rain, snow, and fog, this method can operate stably in scenarios where traditional visual methods fail, such as at night or in severe weather, achieving all-weather congestion detection.
[0036] Furthermore, this embodiment of the invention employs a two-stage detection method to determine whether traffic congestion exists on a road: coarse detection based on traffic flow level and fine detection based on spatiotemporal continuity. Traffic flow level is determined by accumulating vibration values, discretizing and standardizing continuous traffic conditions to provide a clear quantitative benchmark for judgment. Then, only when the local trajectory matrix meeting the coarse detection criteria exhibits continuity in both time and space is a congestion risk deemed to exist. This mechanism fundamentally distinguishes between instantaneous traffic density and continuous traffic congestion, avoiding frequent false alarms caused by temporary vehicle aggregation and instantaneous signal fluctuations, thus greatly improving the accuracy of the detection results.
[0037] To improve the continuity of the local trajectory matrix, in a specific embodiment of the present invention, the sliding window has overlapping portions in both the time and mileage dimensions.
[0038] By overlapping the time and mileage dimensions, the continuity of vehicle trajectories and traffic condition changes is fully preserved at the data level, thus providing a stable input for subsequent congestion criteria based on spatiotemporal continuity. Ultimately, this significantly improves the accuracy, robustness, and precision of congestion detection and origin / end point location.
[0039] In some embodiments of the present invention, the specific process of determining the traffic flow level in step S102 is as follows: Establish a mapping relationship between traffic flow levels and traffic flow intensity ranges; The accumulated vibration value is used as the traffic flow intensity value, and the traffic flow level of the local trajectory matrix is determined based on the traffic flow intensity value and the mapping relationship.
[0040] For example, if traffic flow levels are divided into high, medium and low, the traffic flow intensity range corresponding to the high traffic flow level is A1-A2. When the cumulative vibration value is between A1 and A2, the traffic flow level is determined to be high.
[0041] In practical engineering applications, after determining that traffic congestion exists on a road, it is necessary to identify the congested sections to provide a basis for subsequent driver decisions or upper-level management decision-making strategies. Therefore, in some embodiments of the present invention, such as... Figure 2 As shown, after determining that there is a risk of traffic congestion on the road, the following steps are also taken: S201. Multiple local trajectory matrices that are continuous in time and space are identified as a congestion cluster; S202. Take the downstream local trajectory matrix along the traffic flow direction in the congestion cluster as the current local trajectory matrix.
[0042] The reason for choosing the downstream local trajectory matrix along the traffic flow direction as the current local trajectory matrix is that, on a road, congestion propagates upstream, that is, in the opposite direction of traffic flow. Therefore, using the downstream local trajectory matrix along the traffic flow direction within the congestion cluster as the current local trajectory matrix can completely define the entire congested road segment.
[0043] S203. Search in the opposite direction of the traffic flow along the road. Within the preset search range, find the target local trajectory matrix whose traffic flow level is greater than or equal to the current local trajectory matrix.
[0044] For example, if the traffic flow direction is from the upper left to the lower right, then the opposite direction of the traffic flow is from the lower right to the upper left.
[0045] S204. If a target local trajectory matrix exists, and the spatiotemporal distance between the target local trajectory matrix and the current local trajectory matrix is greater than a preset distance, then the road segment between the current local trajectory matrix and the target local trajectory matrix is determined to be a congested road segment, and the start and end information of the congested road segment is output.
[0046] It should be noted that when searching in the opposite direction of traffic flow along the road, if there are multiple local trajectory matrices that meet the conditions, the local trajectory matrix that is closest in spatiotemporal distance to the current local trajectory matrix will be taken as the target local trajectory matrix.
[0047] From a traffic flow theory perspective, the spatial pattern of congestion propagating on roads is continuous and smooth over a short period. Therefore, among all upstream windows that also meet the traffic flow level conditions, the target local trajectory matrix with the smallest spatiotemporal distance is physically most likely to be a direct continuation of the current congested traffic flow and most likely to belong to the same congestion cluster as the current window. Secondly, in practical applications, multiple target local trajectory matrices may exist within the preset search range, making it impossible to determine which one is the true starting point of congestion, leading to unstable and non-unique output results. This embodiment of the invention introduces a rule based on the closest spatiotemporal distance to ensure the uniqueness and stability of the results, thereby accurately depicting the actual spatial range of congestion.
[0048] In this embodiment of the invention, a target local trajectory matrix with a traffic flow level greater than or equal to the current local trajectory matrix is selected. This ensures that the target local trajectory matrix is also in a congested state, rather than a point where traffic flow is normal or beginning to dissipate. If the traffic flow level of the searched target local trajectory matrix is less than that of the current local trajectory matrix, it indicates that the target local trajectory matrix has entered a smooth state. If the traffic flow level is greater than or equal to that of the current local trajectory matrix, it means that the congestion continues upstream, thus allowing for more reliable delineation of congested sections.
[0049] Furthermore, when the spatiotemporal distance between the target local trajectory matrix and the current local trajectory matrix is less than a preset distance, it indicates that the target local trajectory matrix and the current local trajectory matrix may belong to the same congestion cluster. There is no need to split them into two segments, thus avoiding misjudgment of congested road segments and improving the accuracy of the identified congested road segments.
[0050] In summary, the embodiments of the present invention can not only determine whether there is traffic congestion on the road, but also accurately define the congested road sections, providing directly usable structured information for traffic management departments to make precise guidance and decisions, and greatly improving the efficiency of traffic congestion handling.
[0051] In a specific embodiment of the present invention, the spatiotemporal distance between the current local trajectory matrix and the target local trajectory matrix is a weighted sum of the time distance and the mileage distance between the current local trajectory matrix and the target local trajectory matrix.
[0052] Specifically, spatiotemporal distance for:
[0053] In the formula, For time distance; This refers to the distance in kilometers; , The weights for time distance and mileage distance can be set or adjusted based on the actual application scenario or expert knowledge.
[0054] In practical applications, there may be scenarios where, within the preset search range, there is no traffic flow level equal to or greater than the current local trajectory matrix. This scenario is caused by the following actual situations: 1. Congestion is forming: The currently detected high-traffic area is a congestion that has just begun to accumulate. Because congestion takes time to form, the upstream traffic flow level has not yet reached the trigger threshold within the current short time window.
[0055] 2. Isolated incidents or misjudgments: The current high traffic flow window is just a temporary, localized traffic accumulation (such as the end of a queue at a red light at an intersection), not a real, widespread congestion.
[0056] 3. The observation window is too short: Traffic flow fluctuates. The upstream boundary of a real congestion may fall exactly in the gap between two preset time periods, or its formation process is relatively slow, and its characteristics are not obvious on a short time scale.
[0057] To achieve accurate detection of traffic congestion in this scenario, in some embodiments of the present invention, such as... Figure 3 As shown, traffic congestion detection methods also include: S301. Record the mileage and time corresponding to the current local trajectory matrix, and mark the current local trajectory matrix as a potential congestion endpoint; S302. After a preset delay, increase the duration of the sliding window and redetermine the congested road section.
[0058] This invention addresses situations where congestion has just formed or its boundaries are unclear. By marking potential congestion endpoints and triggering a delayed reanalysis mechanism, it can adaptively adjust the observation window, continuously track the evolution of traffic conditions, avoid hastily determining congestion due to instantaneous fluctuations, improve the ability to capture gradually changing congestion and occasional congestion, and further improve the detection rate and accuracy of traffic congestion.
[0059] In some embodiments of the present invention, the preprocessing of the vibration signal matrix in step S101 to obtain the traffic flow trajectory matrix includes: The vibration signal matrix is filtered and binarized sequentially to obtain the traffic flow trajectory matrix.
[0060] Specifically, the filtering method is Butterworth filtering.
[0061] This invention preprocesses the vibration signal matrix to suppress noise signals unrelated to vehicle trajectory, thereby enhancing the visibility of vehicle trajectory behavior and providing a reliable and accurate data foundation for subsequent traffic congestion detection. At the same time, it reduces the amount of subsequent data processing and improves congestion detection efficiency.
[0062] In summary, the traffic congestion detection method proposed in this invention can quickly and effectively detect traffic congestion in all times, all areas, and all weather conditions, providing convenience for traffic management. Specifically, it does not rely on vehicle-side information or mobile phone location information, but only on roadside information to achieve congestion detection. It has the technical advantages of simplified data sources and strong detection independence, effectively avoiding the limitation of dependence on external data from multiple terminals and improving the adaptability of congestion recognition scenarios. At the same time, it is not affected by weather, lighting, or other factors, and has excellent environmental adaptability. It can effectively avoid the impact of environmental interference on the detection results, significantly improving the stability and reliability of congestion recognition and broadening the applicable scenarios of the method proposed in this invention.
[0063] On the other hand, embodiments of the present invention also provide a traffic congestion detection device, such as... Figure 4 As shown, the traffic congestion detection device 400 includes: The vehicle trajectory matrix determination unit 401 is used to acquire the vibration signal matrix of multiple lanes within a preset time period, and preprocess the vibration signal matrix to obtain the traffic flow trajectory matrix; the vibration signal matrix is acquired based on the fiber optic vibration sensing network laid in the road. The traffic flow level determination unit 402 is used to divide the traffic flow trajectory matrix based on a sliding window, obtain multiple local trajectory matrices and the cumulative vibration value of each local trajectory matrix, and determine the traffic flow level of each local trajectory matrix based on the cumulative vibration value. The traffic congestion determination unit 403 is used to determine whether the local trajectory matrix corresponding to a traffic flow level greater than a preset level is continuous in time and space. If it is continuous, it is determined that there is a risk of traffic congestion on the road.
[0064] The traffic congestion detection device 400 provided in the above embodiments can realize the technical solutions described in the above traffic congestion detection method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above traffic congestion detection method embodiments, and will not be repeated here.
[0065] like Figure 5 As shown, the present invention also provides a traffic congestion detection device 500. The traffic congestion detection device 500 includes an optical fiber sensor network 501, a processor 502, a memory 503, and a display 504. Figure 5 Only some components of the traffic congestion detection device 500 are shown; however, it should be understood that implementation of all shown components is not required, and more or fewer components may be implemented instead.
[0066] The fiber optic sensor network 501 is used to collect vibration signals from roads in real time.
[0067] In some embodiments, processor 502 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in memory 503 or process data, such as the traffic congestion detection method of the present invention.
[0068] In some embodiments, memory 503 may be an internal storage unit of the traffic congestion detection device 500, such as a hard disk or memory of the traffic congestion detection device 500. In other embodiments, memory 503 may also be an external storage device of the traffic congestion detection device 500, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the traffic congestion detection device 500.
[0069] Furthermore, the memory 503 may include both internal storage units and external storage devices of the traffic congestion detection device 500. The memory 503 is used to store the application software and various types of data installed on the traffic congestion detection device 500.
[0070] In some embodiments, display 504 may be an LED display, a liquid crystal display, a touch-screen liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 504 is used to display information from the traffic congestion detection device 500 and to display a visual user interface. Components 501-504 of the traffic congestion detection device 500 communicate with each other via a device bus.
[0071] In some embodiments of the present invention, when the processor 502 executes the traffic congestion detection program in the memory 503, the following steps may be performed: The vibration signal matrix of multiple lanes within a preset time period is acquired, and the vibration signal matrix is preprocessed to obtain the traffic flow trajectory matrix; the vibration signal matrix is acquired based on the fiber optic vibration sensing network laid in the road. The traffic flow trajectory matrix is divided based on a sliding window to obtain multiple local trajectory matrices and the cumulative vibration value of each local trajectory matrix. The traffic flow level of each local trajectory matrix is then determined based on the cumulative vibration value. Determine whether the local trajectory matrix corresponding to a traffic flow level greater than a preset level is continuous in time and space. If it is continuous, then it is determined that there is a risk of traffic congestion on the road.
[0072] It should be understood that when the processor 502 executes the traffic congestion detection program in the memory 503, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.
[0073] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.
[0074] The present invention provides a detailed description of a traffic congestion detection method, apparatus, device, and medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.
Claims
1. A traffic congestion detection method, characterized in that, include: The vibration signal matrix of multiple lanes within a preset time period is acquired, and the vibration signal matrix is preprocessed to obtain the traffic flow trajectory matrix; the vibration signal matrix is acquired based on the fiber optic vibration sensing network laid in the road. The traffic flow trajectory matrix is divided based on a sliding window to obtain multiple local trajectory matrices and the cumulative vibration value of each local trajectory matrix, and the traffic flow level of each local trajectory matrix is determined based on the cumulative vibration value. Determine whether the local trajectory matrix corresponding to a traffic flow level greater than a preset level is continuous in time and space. If it is continuous, then it is determined that the road has a risk of traffic congestion.
2. The traffic congestion detection method according to claim 1, characterized in that, The traffic flow trajectory matrix is a two-dimensional matrix with time and mileage dimensions; the sliding window has overlapping portions in both the time and mileage dimensions.
3. The traffic congestion detection method according to claim 1, characterized in that, Determining the traffic flow level of each of the local trajectory matrices based on the accumulated vibration values includes: Establish a mapping relationship between traffic flow levels and traffic flow intensity ranges; The accumulated vibration value is used as the traffic flow intensity value, and the traffic flow level of the local trajectory matrix is determined based on the traffic flow intensity value and the mapping relationship.
4. The traffic congestion detection method according to claim 1, characterized in that, After determining that the road poses a risk of traffic congestion, the following is also included: Multiple local trajectory matrices that are continuous in time and space are identified as a congestion cluster; The local trajectory matrix at the downstream end of the traffic flow direction in the congestion cluster is taken as the current local trajectory matrix; Search in the opposite direction of the traffic flow direction of the road, and within a preset search range, find a target local trajectory matrix whose traffic flow level is greater than or equal to that of the current local trajectory matrix. If the target local trajectory matrix exists, and the spatiotemporal distance between the target local trajectory matrix and the current local trajectory matrix is greater than a preset distance, then the road segment between the current local trajectory matrix and the target local trajectory matrix is determined to be a congested road segment, and the start and end information of the congested road segment is output.
5. The traffic congestion detection method according to claim 4, characterized in that, The spatiotemporal distance between the current local trajectory matrix and the target local trajectory matrix is a weighted sum of the time distance and the mileage distance between the current local trajectory matrix and the target local trajectory matrix.
6. The traffic congestion detection method according to claim 4, characterized in that, When there is no traffic flow level greater than or equal to the current local trajectory matrix within the preset search range, the method further includes: Record the mileage and time corresponding to the current local trajectory matrix, and mark the current local trajectory matrix as a potential congestion endpoint; After a preset delay, the time length of the sliding window is increased, and the congested road segment is re-determined.
7. The traffic congestion detection method according to claim 1, characterized in that, The vibration signal matrix is preprocessed to obtain the traffic flow trajectory matrix, including: The vibration signal matrix is filtered and binarized sequentially to obtain the traffic flow trajectory matrix.
8. A traffic congestion detection device, characterized in that, include: The vehicle trajectory matrix determination unit is used to acquire vibration signal matrices of multiple lanes within a preset time period, and preprocess the vibration signal matrices to obtain a traffic flow trajectory matrix; the vibration signal matrix is acquired based on an optical fiber vibration sensing network laid in the road. The traffic flow level determination unit is used to divide the traffic flow trajectory matrix based on a sliding window, obtain multiple local trajectory matrices and the cumulative vibration value of each local trajectory matrix, and determine the traffic flow level of each local trajectory matrix based on the cumulative vibration value. The traffic congestion determination unit is used to determine whether the local trajectory matrix corresponding to a traffic flow level greater than a preset level is continuous in time and space. If it is continuous, it is determined that there is a risk of traffic congestion on the road.
9. A traffic congestion detection device, characterized in that, This includes fiber optic sensor networks, memory, and processors, among which... The fiber optic sensor network is used to collect vibration signals from the road in real time. The memory is used to store programs; The processor, coupled to the memory and the fiber optic sensor network, is used to execute the program stored in the memory to implement the steps in the traffic congestion detection method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the traffic congestion detection method according to any one of claims 1 to 7.