Method for identifying violation of traffic light indication behavior of electric bicycle in monitoring blind area
By acquiring the location data of electric bicycles, and based on confidence assessment and road models, combined with spatiotemporal feature fusion and adaptive smoothing technology, the problem of electric bicycles violating traffic signals in blind spots has been solved, achieving more accurate trajectory reconstruction and identification of illegal behavior.
Patent Information
- Application Number
- CN202511280042.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-09
- Publication Date
- 2026-01-20
AI Technical Summary
Existing technologies are insufficient to effectively identify electric bicycles violating traffic signals in blind spots at intersections, leading to traffic chaos and safety hazards.
By acquiring the location data of electric bicycles, based on confidence assessment and road models, and combining spatiotemporal feature fusion and adaptive smoothing technology, the driving trajectory of electric bicycles is identified and matched with traffic lights to determine whether there is any violation of traffic light instructions.
It improves the accuracy of trajectory reconstruction and traffic light matching in complex road conditions, effectively identifies illegal behaviors in blind spots, and reduces misjudgments and omissions.
Smart Images
Figure CN121366487A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present disclosure belongs to the technical field of intelligent traffic management and illegal behavior identification, and relates to a method for identifying the behavior of an electric bicycle in a blind area violating the indication of a traffic signal light. BACKGROUND
[0002] Electric bicycles are the main means of transportation for short-distance travel and transportation. However, some electric bicycle drivers violate traffic laws such as running red lights at traffic intersections in pursuit of efficiency, which not only disrupts traffic order but also poses a huge road traffic safety hazard.
[0003] Currently, the handling of electric bicycle red light violations mainly relies on electric bicycle illegal snapshot devices deployed at key intersections. Such devices usually use video monitoring technology to detect and track vehicles entering the intersection through image recognition algorithms, and combine the signal light state to determine whether there is illegal behavior. SUMMARY
[0004] In order to overcome the above problems, the present disclosure provides a method for identifying the behavior of an electric bicycle in a blind area violating the indication of a traffic signal light.
[0005] The technical solution of the present disclosure is as follows: A method for identifying the behavior of an electric bicycle in a blind area violating the indication of a traffic signal light, comprising: obtaining electric bicycle positioning data; assigning a confidence level to each electric bicycle positioning data through confidence positioning point evaluation; restoring the driving trajectory of the electric bicycle according to the electric bicycle positioning data; obtaining road data and traffic signal light data, generating a road model according to the road data and traffic signal light data, the road model including road structure, intersection and traffic signal light; matching the driving trajectory of the electric bicycle with the road model to obtain the traffic signal light of the intersection passed by the electric bicycle; matching the driving trajectory of the electric bicycle with the indication of the traffic signal light to determine whether there is a violation of the indication of the traffic signal light.
[0006] Further, the electric bicycle positioning data includes a timestamp, a longitude coordinate and a latitude coordinate; The confidence level assigned to each electric bicycle positioning data through confidence evaluation is specifically: obtaining adjacent electric bicycle positioning data according to the timestamp; obtaining electric bicycle segment speed according to adjacent electric bicycle positioning data; obtaining electric bicycle segment acceleration according to electric bicycle segment speed; decrease the confidence of the electric bicycle positioning data corresponding to the electric bicycle segment speed greater than the preset value; decrease the confidence of the electric bicycle positioning data corresponding to the electric bicycle segment acceleration greater than the preset value; decrease the confidence of the adjacent electric bicycle positioning data with a time interval greater than the preset value; discard the electric bicycle positioning data with a confidence lower than the preset value.
[0007] Further, the distance between the two electric bicycle positioning data is obtained by the following method : ; ; wherein, the radius of the earth, and the difference between the latitude coordinates and the difference between the longitude coordinates of the two electric bicycle positioning data, and the latitude coordinates of the two electric bicycle positioning data.
[0008] Further, the electric bicycle driving trajectory is restored according to the electric bicycle positioning data, specifically: obtain adjacent electric bicycle positioning data according to the time stamp; obtain electric bicycle segment directions according to the adjacent electric bicycle positioning data; the electric bicycle segment directions include a first direction and a second direction, and the starting point of the second direction is the end point of the first direction; obtain electric bicycle segment direction changes according to the first direction and the second direction; set the electric bicycle positioning data corresponding to the starting point of the second direction with an electric bicycle segment direction change greater than the preset value as a road segment split point; divide the electric bicycle positioning data into at least one group according to the road segment split point, and each group of electric bicycle positioning data belongs to the same road segment.
[0009] Further, according to the electric bicycle positioning data, the electric bicycle driving trajectory is restored, and further comprising: assign weights to the electric bicycle positioning data according to the confidence of the electric bicycle positioning data; perform adaptive dynamic interpolation for the electric bicycle, specifically: adjust the interpolation point density according to the time interval of the adjacent electric bicycle positioning data and the road segment length; determine the interpolation point data according to the weight of the electric bicycle positioning data.
[0010] Further, the electric bicycle positioning data is used to restore the electric bicycle driving track, and the method further comprises: The electric bicycle driving track is smoothed according to the curvature of the electric bicycle driving track.
[0011] Further, the method further comprises cleaning of the electric bicycle positioning data, and specifically comprises: The DBSCAN clustering is used to identify and remove isolated noise points in the electric bicycle positioning data.
[0012] Further, the method further comprises generating a road model according to road data and traffic signal lamp data, and specifically comprises: The road intersection data is used to determine whether the roads intersect, and the intersection is set as an intersection; The road data and the intersection are used to obtain the intersection center and the intersection range; The traffic signal lamp and the intersection are matched according to the distance between the traffic signal lamp and the intersection.
[0013] Further, the traffic signal lamp and the intersection are matched according to the distance between the traffic signal lamp and the intersection, and specifically comprises: The traffic signal lamp semantic information and the distance between the traffic signal lamp and the intersection are obtained; The traffic signal lamp and the intersection are matched according to the traffic signal lamp semantic information and the distance between the traffic signal lamp and the intersection, and the weights of the traffic signal lamp semantic information and the distance between the traffic signal lamp and the intersection are dynamically adjusted during the matching.
[0014] Further, the traffic signal lamp semantic information comprises a signal lamp type and road type matching degree, a direction consistency, and an accessory facility correlation.
[0015] The present disclosure has the following beneficial effects: The present disclosure uses an algorithm based on spatiotemporal feature fusion and segmented dynamic optimization when restoring the electric bicycle driving track. The algorithm introduces road segment feature recognition and adaptive smoothing technology, and can better handle track restoration under complex road conditions.
[0016] The electric bicycle track restoration algorithm based on spatiotemporal features, compared with the traditional track restoration method, uses confidence-based positioning point evaluation: not only filters abnormal points, but also assigns a confidence weight to each positioning point, dynamically adjusts its influence in subsequent processing, and more reasonably utilizes the original data.
[0017] Road segment segmentation and segmented optimization: automatically identify road segments according to driving direction changes, and optimize each road segment separately to retain the true turning characteristics and avoid excessive smoothing that causes track distortion.
[0018] Curvature adaptive smoothing: dynamically adjust smoothing parameters according to trajectory curvature, use stronger smoothing on straight segments and weaker smoothing on curved segments, better balance smoothing and trajectory authenticity.
[0019] Space-time feature fusion: combine time interval, speed change, direction change and other multi-dimensional features for trajectory optimization, rather than simply based on spatial distance interpolation.
[0020] The present disclosure also proposes to dynamically adjust the weights of spatial features and semantic features according to the distance between the signal light and the candidate point, relying more on spatial information at close range and more on semantic information at long range.
[0021] By identifying intersections and constructing road network topology, the signal light position is associated with road network features, improving matching accuracy, especially in dense urban areas.
[0022] When matching signal lights and roads, not only latitude and longitude information is considered, but also signal light type and road type matching degree, direction consistency, and related semantic features of ancillary facilities, solving the limitations of simply relying on distance. BRIEF DESCRIPTION OF DRAWINGS
[0023] Figure 1 The flowchart of the method of the present disclosure. DETAILED DESCRIPTION
[0024] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme of the embodiments of the present disclosure will be described clearly and completely below in combination with the drawings of the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present disclosure.
[0025] Unless otherwise defined, technical terms or scientific terms used in the present disclosure shall have the meanings as generally understood by one of ordinary skill in the art to which the present disclosure belongs. The terms "first", "second", and similar terms are used herein to distinguish one element from another, and are not necessarily used in a sequence or to denote importance or quantity. The terms "comprise", "comprising", "include", "including", and the like are used herein to mean including but not limited to. The terms "connected", "coupled", and the like are used herein to mean either a direct connection or an indirect connection through one or more intervening elements, unless otherwise specified. The terms "above", "below", "upper", "lower", and the like are used herein to denote relative positions for the purpose of illustration and the relative positions can change accordingly when the absolute positions of the described objects change. In order to keep the following description of the embodiments of the present disclosure clear and concise, the detailed description of some known functions and known components is omitted.
[0026] The present disclosure will be described in detail below with reference to the accompanying drawings and specific embodiments.
[0027] Reference Figure 1 A method for identifying the behavior of electric bicycles violating traffic signal indications in a blind area, comprising: obtaining electric bicycle positioning data; assigning a confidence level to each electric bicycle positioning data through confidence positioning point evaluation; restoring the driving trajectory of the electric bicycle according to the electric bicycle positioning data; obtaining road data and traffic signal data, generating a road model according to the road data and the traffic signal data, the road model including road structure, intersections, and traffic signals; matching the driving trajectory of the electric bicycle with the road model to obtain the traffic signal of the intersection passed by the electric bicycle; matching the driving trajectory of the electric bicycle with the traffic signal indication to determine whether there is a behavior of violating the traffic signal indication.
[0028] In an embodiment of the present disclosure, the electric bicycle positioning data includes a timestamp, a longitude coordinate, and a latitude coordinate; The confidence level is assigned to each electric bicycle positioning data through confidence evaluation, specifically: obtaining adjacent electric bicycle positioning data according to the timestamp; obtaining electric bicycle segment speed according to the adjacent electric bicycle positioning data; obtaining electric bicycle segment acceleration according to the electric bicycle segment speed; decrease the confidence of the electric bicycle positioning data corresponding to the electric bicycle segment speed greater than the preset value; decrease the confidence of the electric bicycle positioning data corresponding to the electric bicycle segment acceleration greater than the preset value; decrease the confidence of the adjacent electric bicycle positioning data with a time interval greater than the preset value; discard the electric bicycle positioning data with a confidence lower than the preset value.
[0029] In an embodiment of the present disclosure, the distance between the two electric bicycle positioning data is obtained by the following method : ; ; wherein, is the radius of the earth, and is the difference between the latitude coordinates and the difference between the longitude coordinates of the two electric bicycle positioning data, and is the latitude coordinate of the two electric bicycle positioning data.
[0030] In an embodiment of the present disclosure, the electric bicycle driving trajectory is restored according to the electric bicycle positioning data, specifically: obtain adjacent electric bicycle positioning data according to the time stamp; obtain electric bicycle segment direction according to the adjacent electric bicycle positioning data; the electric bicycle segment direction includes a first direction and a second direction, and the starting point of the second direction is the end point of the first direction; obtain electric bicycle segment direction change according to the first direction and the second direction; set the electric bicycle positioning data corresponding to the starting point of the second direction with the electric bicycle segment direction change greater than the preset value as a road segment split point; divide the electric bicycle positioning data into at least one group according to the road segment split point, and each group of electric bicycle positioning data belongs to the same road segment.
[0031] For example, the first direction is obtained according to points A and B, and the second direction is obtained according to points B and C. If the direction change of the second direction relative to the first direction is greater than the preset value, then point B is set as a road segment split point, and the points before B form one road segment and the points after B form another road segment. If it is not greater than the preset value, then the points before and after B form the same road segment.
[0032] In an embodiment of the present disclosure, the electric bicycle driving trajectory is restored according to the electric bicycle positioning data, and further comprises: According to the confidence of the electric bicycle positioning data, the electric bicycle positioning data is weighted; Adaptive dynamic interpolation is performed for the electric bicycle, specifically: According to the time interval of the adjacent electric bicycle positioning data and the length of the road section, the density of the interpolation points is adjusted; According to the weight of the electric bicycle positioning data, the interpolation point data is determined.
[0033] When the time interval is too long, the interpolation point density can be increased, and when the road section length is relatively long, it indicates that the electric bicycle trajectory is relatively flat, and the interpolation point density can be reduced.
[0034] The interpolation point data is obtained according to the electric bicycle positioning data of other points on the road section, and the influence of each data on the interpolation point value is adjusted through the weight of the electric bicycle positioning data.
[0035] In an embodiment of the present disclosure, the electric bicycle trajectory is restored according to the electric bicycle positioning data, and further comprises: According to the curvature of the electric bicycle trajectory, the electric bicycle trajectory is smoothed.
[0036] Specifically, B-spline can be used for smoothing.
[0037] In an embodiment of the present disclosure, the electric bicycle positioning data is cleaned, specifically: DBSCAN clustering is used to identify and remove isolated noise points in the electric bicycle positioning data.
[0038] The present disclosure can effectively process errors and missing problems in most positioning data, and is particularly suitable for the trajectory restoration requirements of electric bicycles in urban environments. The algorithm retains key feature points (such as turning points) and reasonably processes data loss (interpolation), while ensuring trajectory smoothness, and maximizes the restoration of the true driving path.
[0039] In an embodiment of the present disclosure, a road model is generated according to road data and traffic signal data, specifically: According to the road intersection data, it is judged whether the roads intersect, and the intersection is set as an intersection; According to the road data and the intersection, the intersection center and the intersection range are obtained; According to the distance between the traffic signal and the intersection, the traffic signal and the intersection are matched.
[0040] In an embodiment of the present disclosure, the traffic signal and the intersection are matched according to the distance between the traffic signal and the intersection, specifically: The semantic information of the traffic signal and the distance between the traffic signal and the intersection are obtained; The traffic signal and the intersection are matched according to the traffic signal semantic information and the distance between the traffic signal and the intersection, wherein the weights of the traffic signal semantic information and the distance between the traffic signal and the intersection are dynamically adjusted according to the distance between the traffic signal and the intersection.
[0041] When matching the traffic signal and the intersection, the spatial feature can be trusted more for the case of close spatial distance, and thus the weight of the distance between the traffic signal and the intersection can be increased. For the case of far spatial distance, the semantic feature can be trusted more, and thus the weight of the semantic feature can be increased.
[0042] In an embodiment of the present disclosure, the traffic signal semantic information includes a signal lamp type and road type matching degree, a direction consistency, and an accessory facility correlation.
[0043] Specifically, the road type matching degree matrix is as follows: 'motor vehicle signal lamp': {'main road': 1.0,'secondary road': 0.9, 'branch road': 0.7, 'pedestrian street': 0.2}, 'pedestrian signal lamp': {'main road': 0.7,'secondary road': 0.8, 'branch road': 0.9, 'pedestrian street': 1.0}, 'non-motor vehicle signal lamp': {'main road': 0.8,'secondary road': 0.9, 'branch road': 0.8, 'pedestrian street': 0.6}, 'comprehensive signal lamp': {'main road': 0.9,'secondary road': 0.9, 'branch road': 0.8, 'pedestrian street': 0.5} The direction consistency is the indication direction of the traffic signal and the traffic direction of the road.
[0044] The accessory facility is a highway accessory facility, including a photo, a communication, a boundary post, a safety facility, and the like.
[0045] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions of the flow diagrams and / or block diagrams as computer processes. In this context, a "computer" apparatus can be a general purpose computing device, a special purpose computing device, a computing cloud, or any other computing system or processing device.
[0046] The units described in the embodiments of the present disclosure can be implemented by hardware, software, or a combination of hardware and software. In some cases, the names of the units do not constitute a limitation on the units themselves.
[0047] The functions described in this specification can be performed by one or more hardware logic components. For example, non-limiting examples of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SOCs), complex programmable logic devices (CPLDs), etc.
[0048] The above description is merely illustrative of the exemplary embodiments of the present disclosure and the principles of the technology involved. It should be understood by those skilled in the art that the scope of the disclosure involved is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by the combinations of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the technical solutions formed by the mutual replacement of the above features and the technical features disclosed in the present disclosure (but not limited to) having similar functions.
[0049] Moreover, while operations are depicted in a particular, chronological sequence in this disclosure, this should not be understood as requiring such order unless otherwise specified. In some cases, the activities can be performed in different order, or concurrently, or in different ways. Additionally, while specific implementation details are discussed in the context of certain implementations, other implementations can also be implemented consistent with the scope of the disclosure. Certain features described in the context of separate embodiments can also be implemented together in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented separately or in any suitable subcombination. Moreover, although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
[0050] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
[0051] For the disclosure, there are the following points to note: (1) The drawings of the embodiments of the disclosure only involve the structures involved in the embodiments of the disclosure, and other structures can refer to the general design.
[0052] (2) In the case of no conflict, the embodiments of the disclosure and the features in the embodiments can be combined to obtain new embodiments.
[0053] The above only describes the embodiments of the disclosure, and does not limit the patent scope of the disclosure, and any equivalent structure made by using the disclosure specification and drawings, or directly or indirectly applied to other related technical fields, are also included in the patent protection scope of the disclosure.
Claims
1. A method for identifying the behavior of an electric bicycle in a blind area violating the indication of a traffic signal lamp, characterized in that, The method comprises the following steps: acquiring electric bicycle positioning data; assigning a confidence level to each electric bicycle positioning data through a confidence positioning point evaluation; restoring an electric bicycle travel trajectory according to the electric bicycle positioning data; acquiring road data and traffic signal data, and generating a road model according to the road data and the traffic signal data, wherein the road model comprises road structures, intersections and traffic signals; matching the electric bicycle travel trajectory with the road model to obtain traffic signals of intersections passed by the electric bicycle; matching the electric bicycle travel trajectory with traffic signal indication conditions to determine whether there is a traffic signal indication violation behavior.
2. The method of claim 1, wherein the method further comprises: The electric bicycle positioning data comprises a timestamp, a longitude coordinate and a latitude coordinate; The confidence level assigned to each electric bicycle positioning data through the confidence evaluation is specifically: acquiring adjacent electric bicycle positioning data according to the timestamp; obtaining electric bicycle segment speeds according to the adjacent electric bicycle positioning data; obtaining electric bicycle segment accelerations according to the electric bicycle segment speeds; reducing the confidence level of the electric bicycle positioning data corresponding to the electric bicycle segment speed greater than a preset value; reducing the confidence level of the electric bicycle positioning data corresponding to the electric bicycle segment acceleration greater than a preset value; reducing the confidence level of the adjacent electric bicycle positioning data with a time interval greater than a preset value; removing the electric bicycle positioning data with a confidence level lower than a preset value.
3. The method of claim 2, wherein the method further comprises: The distance of the 2 e-bike positioning data is obtained by the following method : ； ； wherein, is the earth radius, and are the latitude and longitude coordinate differences of the 2 e-bike positioning data, and are the latitude coordinates of the 2 e-bike positioning data.
4. The method of claim 1, wherein the method further comprises: The electric bicycle travel trajectory is restored according to the electric bicycle positioning data, specifically: acquiring adjacent electric bicycle positioning data according to the timestamp; obtaining electric bicycle segment directions according to the adjacent electric bicycle positioning data; The electric bicycle segment direction comprises a first direction and a second direction, and the starting point of the second direction is the end point of the first direction; obtaining electric bicycle segment direction changes according to the first direction and the second direction; setting the electric bicycle positioning data corresponding to the starting point of the second direction with an electric bicycle segment direction change greater than a preset value as a road segment split point; dividing the electric bicycle positioning data into at least one group according to the road segment split point, and each group of electric bicycle positioning data belongs to the same road segment.
5. The method of claim 4, wherein the method further comprises: The electric bicycle travel trajectory is restored according to the electric bicycle positioning data, further comprising: assigning a weight to the electric bicycle positioning data according to the confidence level of the electric bicycle positioning data; performing adaptive dynamic interpolation for the electric bicycle, specifically: adjusting the interpolation point density according to the time interval of the adjacent electric bicycle positioning data and the road segment length; determining the interpolation point data according to the weight of the electric bicycle positioning data.
6. The method of claim 4, wherein the method further comprises: The electric bicycle travel trajectory is restored according to the electric bicycle positioning data, further comprising: performing smoothing processing on the electric bicycle travel trajectory according to the curvature of the electric bicycle travel trajectory.
7. The method of claim 1, wherein the method further comprises: Further comprising cleaning of the electric bicycle positioning data, specifically: using DBSCAN clustering to identify and remove isolated noise points in the electric bicycle positioning data.
8. The method of claim 1, wherein the method further comprises: The road model is generated according to the road data and the traffic signal data, specifically: determining whether roads intersect according to road intersection data, and setting the intersection as an intersection. According to the road data and the intersection, an intersection center and an intersection range are obtained; According to the distance between the traffic signal lamp and the intersection, the traffic signal lamp is matched with the intersection.
9. The method of claim 8, wherein the method further comprises: According to the distance between the traffic signal lamp and the intersection, the traffic signal lamp is matched with the intersection, specifically: Traffic signal lamp semantic information and the distance between the traffic signal lamp and the intersection are obtained; According to the traffic signal lamp semantic information and the distance between the traffic signal lamp and the intersection, the traffic signal lamp is matched with the intersection, wherein the weights of the traffic signal lamp semantic information and the distance between the traffic signal lamp and the intersection are dynamically adjusted according to the distance between the traffic signal lamp and the intersection.
10. The method of claim 8, wherein the method further comprises: The traffic signal lamp semantic information includes a signal lamp type and a road type matching degree, a direction consistency and an accessory facility correlation.