Large-curvature road electric bicycle retrograde motion behavior identification method based on trajectory data

Abstract

The invention provides a large-curvature road electric bicycle converse motion behavior identification method based on trajectory data. The method comprises the following steps: 1) trajectory data acquisition and cleaning: collecting trajectory data and cleaning missing and drifting data; 2) map matching: accurately matching the trajectory data to an urban road network; 3) retrograde motion behavior identification: calibrating retrograde motion points on a one-way road and a two-way road by using a geometry and road topological relation principle under the condition of considering a large-curvature road, and further identifying a retrograde motion behavior; and 4) road network risk level division: based on the shared electric bicycle track data, counting the occurrence frequency of the retrograde behavior of each road section in one day, performing risk level division on the road sections according to the occurrence frequency, and displaying the road network risk level on a GIS map platform. According to the method, the retrograde behavior under the road with the great curvature is recognized through the topology relation between geometry and the road, and compared with a previous method, the robustness and accuracy of retrograde detection are remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent traffic information processing, and more particularly relates to a method for identifying the reverse-travel behavior of electric bicycles on large-curvature roads based on trajectory data. Background Art

[0002] In recent years, electric bicycles have become a popular choice for short-distance commuting due to their speed, convenience, and affordability. However, this surge in usage has also brought safety concerns. Most electric bicycle accidents are related to high-risk riding behaviors, making accurate identification of these behaviors crucial for strengthening electric bicycle traffic safety management.

[0003] Among the many risky cycling behaviors, driving against traffic is the most frequently occurring risky cycling behavior except for running red lights. Depending on the type of road, driving against traffic can be divided into driving against traffic on one-way roads and driving against traffic on two-way roads. At present, the identification of driving against traffic based on the trajectory data of electric bicycles has been widely used. For example, patent CN201910865192.5 proposed "a method for identifying driving against traffic based on bicycle trajectory data", which realizes the identification of driving against traffic on one-way and two-way roads and is widely adopted by the industry. However, the method for identifying driving against traffic provided by this patent is only applicable to situations where the road section is a straight line or the curvature of the road section is small, and it has high requirements on the trajectory quality. As shown in the attached Figure 2 As shown, on one-way roads, when poor trajectory quality causes position drift, the azimuth difference can easily exceed the threshold, resulting in recognition failure. On two-way roads, when the road curvature is too large, the reverse trajectory chain will be located to the right of the temporary direction, causing recognition failure. In these situations, existing algorithms are no longer applicable. Therefore, finding a method for identifying reverse behavior based on e-bike trajectory data that is adaptable to roads with large curvature and low trajectory quality is an urgent problem for those skilled in the art. Summary of the Invention

[0004] The technical problem to be solved by the present invention is that, in response to the above-mentioned shortcomings of the existing technology, a method for identifying wrong-way behavior on large-curvature roads based on electric bicycle trajectory data is proposed. The method solves the problem that the existing technology cannot effectively identify wrong-way behavior on roads with excessive curvature. Through the integrated technical solution of "data cleaning-map matching-behavior identification-risk quantification", wrong-way behavior can be quickly and accurately identified. At the same time, with the help of emerging data platforms such as shared electric bicycles and food delivery electric bicycles, city-level, all-weather wrong-way behavior detection can be achieved, road risk levels can be quantified, and technical support can be provided for traffic safety management.

[0005] In order to achieve the above objectives, the present invention adopts the following technical solutions:

[0006] Step 1: Acquire and clean the trajectory data of electric bicycles, mainly cleaning the trajectory data with missing data and drift;

[0007] Step 2: Obtain road network data, sort the trajectory subchains and the trajectory points in the subchains in ascending time order, perform map matching, and accurately match the trajectory chains to the urban road network data;

[0008] Step 3: Use trajectory data to identify retrograde behavior;

[0009] Step 4: Classify road network risk levels.

[0010] According to a method for identifying wrong-way driving on a large curvature road based on electric bicycle trajectory data provided by the present invention, the step 1 of acquiring and cleaning the electric bicycle trajectory data includes:

[0011] Step 1.1: The electric bicycle trajectory data comes from the anonymized data of the shared electric bicycle operator, including the order number, trajectory timestamp, and latitude and longitude coordinates.

[0012] Step 1.2: Clean up missing and drifting points in the trajectory data. These points include trajectory data anomalies caused by reasons such as e-bike GPS sensor failure or obstruction by tall buildings in cities. They appear as points that deviate significantly from their true location (drifting points) or are lost (missing points).

[0013] According to a method for identifying wrong-way driving on a large curvature road based on electric bicycle trajectory data provided by the present invention, the map matching in step 2 includes:

[0014] Step 2.1: Road network data preparation.

[0015] Step 2.2: Implement map matching. After map matching, each trajectory point will have three additional attributes: road segment ID, one-way and two-way identification, and road direction angle.

[0016] According to a method for identifying wrong-way traffic on a large curvature road based on electric bicycle trajectory data provided by the present invention, the wrong-way traffic identification step 3 includes:

[0017] Step 3.1: Arrange the trajectory points P in the trajectory chain T in ascending time order i , i is the time sequence identifier of the trajectory point.

[0018] Step 3.2: P i 、P i+1 Project to matching road segment E j , get the projection point P′ i , P′ i+1 , j is the road section code identifier.

[0019] Step 3.3: For the identification of reverse points on one-way roads, when P′i , P′ i+1 Belong to the same road section sub-segment e jk , and P′ i , P′ i+1 With e jk Starting point v jl The distance d i,jl <d i+1,jl When P i is a retrograde point, otherwise it is a direct point. i , P′ i+1 Not belonging to the same road section sub-segment e jk When comparing P′ i Belongs to jk2 The position labels k2 and P′ i+1 Belongs to jk1 The relative size of the position label k1, if P′ i The k2 number is larger, marked P i is a retrograde point, otherwise it is a direct point. jk is the road segment where the projection point is located, v jl is the starting point of the road sub-segment, k and l are coding identifiers.

[0020] Step 3.4: For the identification of the reverse point on a two-way road, use the projection point P′ i , P′ i+1 Constructing a temporary direction vector make Represents the trajectory point P i The riding direction. When a×b i =a x b y -a y b x >0, P i is a retrograde point, otherwise it is a direct point.

[0021] Step 3.5: Calculate the number of all retrograde points NW in the trajectory chain T T and the number of trajectory points N T , when NW T / N T When >0.5, the trajectory chain T is a retrograde trajectory chain, otherwise it is an anterograde trajectory chain.

[0022] According to a method for identifying wrong-way driving on a large curvature road based on electric bicycle trajectory data provided by the present invention, the road network risk level division in step 4 includes:

[0023] Step 4.1: Based on the shared e-bike trajectory data, count the frequency of wrong-way traffic on each road section throughout the day, divide the severity of wrong-way traffic using appropriate frequency panes, and display the road network risk level based on the GIS map platform.

[0024] The present invention provides a method for identifying wrong-way driving on a high-curvature road based on electric bicycle trajectory data. Compared with the prior art, the method has at least the following advantages:

[0025] (1) Strong adaptability to road conditions. The method proposed in the present invention can adapt to the identification of wrong-way traffic under different curvature road conditions and has higher accuracy.

[0026] (2) Strong data robustness. The retrograde behavior recognition method proposed in this invention can adapt to the situation where the trajectory data accuracy is low and has better robustness.

[0027] (3) Integrated technical solution. Through the integrated technical solution of "data cleaning - map matching - behavior identification - risk quantification", the present invention realizes the automation of the entire process from data acquisition to risk assessment, which helps to improve the efficiency and effectiveness of traffic safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a flowchart of a method for identifying wrong-way behavior based on electric bicycle trajectory data;

[0029] Figure 2 Identify errors for retrograde behavior schematics;

[0030] Figure 3 A schematic diagram for identifying reverse traffic points on a one-way road;

[0031] Figure 4 This is a schematic diagram for identifying reverse traffic points on a two-way road;

[0032] Figure 5 A schematic diagram of an embodiment for identifying wrong-way traffic on a one-way road;

[0033] Figure 6 A schematic diagram of an embodiment for identifying wrong-way traffic on a two-way road;

[0034] Figure 7 Schematic diagram of the frequency distribution of wrong-way behavior in the road network. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of the present invention more clear and distinct, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0036] Please see the attached Figure 1 The present invention provides a method for identifying wrong-way-on-curve behavior based on electric bicycle trajectory data, comprising the following steps:

[0037] Step 1: Acquisition and cleaning of electric bicycle trajectory data;

[0038] Step 2: Map matching;

[0039] Step 3: Use trajectory data to identify wrong-way behavior on one-way and two-way roads;

[0040] Step 4: Classify road network risk levels.

[0041] The specific implementation steps are as follows:

[0042] (1) Electric bicycle trajectory data acquisition and cleaning

[0043] The electric bicycle trajectory data comes from the desensitized data of the shared electric bicycle operator, and the drift points and missing points in the trajectory are cleaned. For the drift point, when d i,i+1 >v thr t i,i+1 Delete the trajectory point P i For missing points, when t i,i+1 >t thr When , the original trajectory chain is cut off and a new trajectory subchain is generated. i represents the i-th trajectory point, e ,i+1 is the trajectory point P i With P i+1 The Euclidean distance, t i,i+1 is the trajectory point P i With P i+1 The time interval, v thr is the upper limit of the permissible speed, t thr The upper limit of the allowed time.

[0044] (2) Map matching

[0045] 1) Road network preparation: The road network data is obtained through the open source map platform OSM (OpenStreet Map). j Contains four elements, E j =(rid,roneway,rdirection), where rid represents the road segment ID, roneway represents the one-way / two-way identification, and rdirection represents the road segment direction. j is a set of directed acyclic line segments, E j =(v j ,e j ). where e j ={e j1 ,e j2 ,…,e jk ,…,e jm} represents the sub-segment set of the road segment, v j ={v j1 ,v j2 ,…,vjl ,…,v jq} represents the set of road segment nodes, 1≤k≤m, 1≤l≤q. Where k and l are the road segment nodes E j The sub-segment and node codes of road segment E are respectively j The total number of sub-segments and nodes.

[0046] Subsequently, the main roads of highways and expressways where electric bicycles are not accessible will be deleted.

[0047] 2) Map matching: The present invention adopts an interactive voting-based map matching (IVMM) algorithm and improves the algorithm by taking into account the operating characteristics of electric bicycles. First, electric bicycles will cross the road at any position on a two-way road or at a one-way road crossing facility. Two-way road matching will not affect the subsequent behavior recognition results, while one-way road matching will interfere with the driving recognition results after crossing the road (such as whether it is driving in the opposite direction). Because the topological relationship of the one-way road crossing facilities is not marked in the original OSM road network, the road section at the crossing facility is truncated and connected through a new road section to ensure the accuracy of behavior recognition. Secondly, considering that electric bicycles often drive in the opposite direction and speeding in the opposite direction is particularly dangerous, the road topology is changed from a directed graph to an undirected graph to avoid situations where the reverse trajectory chain cannot be matched or is incorrectly matched to the opposite lane, thereby ensuring that the reverse behavior trajectory chain is correctly matched. Finally, after map matching, three attributes will be added to each trajectory point, namely, the road section ID, one-way and two-way identification, and road direction angle.

[0048] (3) Identification of retrograde behavior

[0049] 1) Identification of wrong-way traffic on one-way roads

[0050] One-way roads are digraph vectors with correct direction marks in OSM maps, and their direction is the same as the normal driving direction of the vehicle. i With road section sub-segment e jk The relationship between the identification of retrograde behavior. Figure 3 As shown, the identification steps are as follows:

[0051] a) Data index: Sort the n trajectory points in the trajectory chain T in ascending time order, and define the current trajectory point and the next trajectory point as P respectively. i 、P i+1 .

[0052] b) Road section sub-segment identification: P i 、P i+1 Projected to the matched road segment E j The resulting projection point is P′ i , P′ i+1 .

[0053] c) Retrograde point identification: When P′ i, P′ i+1 Belong to the same e jk When P′ i , P′ i+1 With e jk Starting point v jl The distance d i,jl d i+1,jl ; When d i+1,jl <d i,jl , marked P i is a retrograde point, otherwise it is a direct point. i , P′ i+1 Not belonging to the same jk When P′ i ∈e jk2 , P′ i+1 ∈e jk1 , compare the label size of k1 and k2; if P′ i The k2 number is larger, marked P i is a retrograde point, otherwise it is a direct point;

[0054] d) Retrograde behavior identification: Calculate the number of all retrograde points NW in the trajectory chain T T and the number of trajectory points N T , when NW T / N T When >0.5, the trajectory chain T is a retrograde trajectory chain, otherwise it is an anterograde trajectory chain.

[0055] 2) Identification of wrong-way traffic on two-way roads

[0056] Two-way roads are digraph vectors with incorrect direction markings in OSM maps, so the one-way road identification method cannot be used.

[0057] Therefore, the geometric method can be used to identify the wrong-way behavior on a two-way road. Figure 4 As shown, the identification steps are as follows:

[0058] a) Data index: Sort the n trajectory points in the trajectory chain T in ascending time order, and define the current trajectory point and the next trajectory point as P respectively. i 、P i+1 .

[0059] b) Road section sub-segment identification: P i 、P i+1 Projected to the matched road segment E j The resulting projection point is P′ i , P′ i+1 .

[0060] c) Retrograde point identification: Construct a temporary direction vector and let the projection point P′ i , P′ i+1is the endpoint of the temporary direction vector, then the vector make Represents the trajectory point P i The riding direction is reverse, and the trajectory point P i On the left side of a, that is, when a×b i =a x b y -a y b x >0, mark P i is a retrograde point, otherwise it is a direct point.

[0061] d) Retrograde behavior identification: Calculate the number of all retrograde points NW in the trajectory chain T T and the number of trajectory points N T , when NW T / N T When >0.5, the trajectory chain T is a retrograde trajectory chain, otherwise it is an anterograde trajectory chain.

[0062] (4) Road network risk level classification

[0063] 1) Based on the shared electric bicycle trajectory data, the frequency of wrong-way behavior on each road section in a certain area of ​​Changsha City within a day was counted, and three levels were divided with appropriate frequency panes. Road sections were marked with green, red, and black colors on the GIS map platform to indicate the severity of wrong-way behavior, so as to observe the risk level at the road network level, as shown in the attached figure. Figure 7 shown.

[0064] The following are application examples of the present invention.

[0065] Xinyao Road and Linda Road in Changsha City, Hunan Province are used as one-way roads and two-way roads respectively to identify wrong-way driving behavior on curves.

[0066] (1) Obtain the riding trajectory of shared electric bicycles and complete data cleaning.

[0067] (2) Perform map matching on the cycling trajectory and add three elements to each trajectory point: road segment ID, one-way and two-way identification, and road direction angle.

[0068] (3) Identification of retrograde behavior

[0069] 1) Identification of wrong-way traffic on one-way roads

[0070] Attachment Figure 5 The road topology of Xinyao Road (blue mark) is shown. Let this road section be E j , the matching trajectory chain is T. First, the one-way road reverse behavior recognition algorithm provided by patent CN201910865192.5 is used for judgment. With the north direction as 0° and the clockwise direction as the positive direction, E jThe direction angle is 238°. i The direction angles of the road section E j Comparing the direction angles, except for P4 and P6, the rest of the trajectory points were correctly identified as retrograde points. After checking, the direction angle of P4 was 347°, the direction angle difference was 109°, and the direction angle of P6 was 332°, the direction angle difference was 94°, both of which reached the retrograde judgment standard of direction angle [135°, 225°]. Then the curve retrograde recognition algorithm proposed by the present invention was used for judgment. After judgment, P1 to P 11 All are correctly identified as retrograde points. For trajectory points P4 and P5, their projection points P′4 and P′5 are both located at e j3 , calculate P′4, P′5 and v j3 The distances between P′4 and v are 90m and 80m respectively. j3 The distance is further, and P4 is marked as a retrograde point. Similarly, for trajectory points P6 and P7, their projection points P′6 and P′7 are both located at e j3 , calculate P′6, P′7 and v j3 The distances between P′6 and v are 77m and 75m respectively. j3 Further away, P6 is marked as a retrograde point.

[0071] In summary, both patent CN201910865192.5 and the present invention can identify trajectory chain T as a wrong-way behavior in terms of wrong-way behavior. However, because patent CN201910865192.5 sets the azimuth angle difference hyperparameter during recognition, trajectory points outside the hyperparameter range are invalid. The one-way road wrong-way behavior recognition algorithm proposed in the present invention relies on road topology, avoiding the problems caused by defining hyperparameters and achieving greater robustness.

[0072] 2) Identification of wrong-way traffic on two-way roads

[0073] Attachment Figure 6 The road topology of Linda Road (blue mark) is shown. Let this road section be E j , the matching trajectory chain is T. First, the bidirectional road reverse behavior recognition algorithm provided by patent CN201910865192.5 is used for judgment. i Determine a×b with the temporary direction vector of the road i Is it greater than 0? Finally, P1 and P2 are identified as retrograde points, and the rest are misjudged as direct points. Figure 4 It can be seen that P1 to P 12All of them are reverse points, P1 and P2 are located on the left side of the road temporary direction vector, and the rest of the trajectory points are on the right side of the road temporary direction vector. Therefore, the reverse behavior is misjudged. It can be seen that due to the large curvature of the road section, the road temporary direction vector cannot be used as a reference vector for reverse behavior identification, resulting in the failure of reverse behavior determination. Then the curve reverse identification algorithm proposed by the present invention is used for determination. After determination, P1 to P 12 All are correctly identified as retrograde points. Taking trajectory point P6 as an example, the projection point of trajectory point P6 is located at e j4 , P′6=(112.984239,28.139520), the projection point of trajectory point P7 is located at e j5 , P7 ′ =(112.983685,28.139678). As the temporary direction vector of the road, Calculation can be obtained as a×b i =1.505×10 -7 > 0. Therefore, P6 is marked as a retrograde point. Finally, the entire trajectory chain T is correctly identified as a retrograde trajectory chain.

[0074] In summary, patent CN201910865192.5 failed to correctly identify the reverse trajectory chain T when identifying wrong-way traffic on a two-way road, while the present invention correctly identified it. When the road curvature is too large, using the start and end points of the road segment as the temporary road direction vector is no longer applicable. The proposed two-way wrong-way traffic identification algorithm uses the projection of the trajectory points as the temporary road direction vector, avoiding mismatches caused by excessive road curvature and achieving higher accuracy.

[0075] Matters not covered by the present invention are known technologies.

[0076] The above embodiments are intended only to illustrate the technical concepts and features of the present invention. Their purpose is to enable those skilled in the art to understand the contents of the present invention and implement them accordingly. They are not intended to limit the scope of protection of the present invention. Any equivalent changes or modifications made in accordance with the spirit of the present invention are intended to be covered by the scope of protection of the present invention.

Claims

1. A method for identifying the reverse behavior of electric bicycles on large curvature roads based on trajectory data, characterized in that: Through the geometric and road topological relationship, the reverse driving behavior under the condition of large road curvature is identified. The identification method includes the following steps: Step S1: acquiring and cleaning electric bicycle trajectory data; Step S2: Obtain road network data, arrange the trajectory subchains and the trajectory points in the subchains in ascending time order, perform map matching, and accurately map the trajectory chains to the urban road network data; Step S3: using the trajectory data to identify the wrong-way behavior on the road with large curvature; Step S4: Based on the electric bicycle trajectory data, the road network risk level is divided.

2. The method for identifying the reverse behavior of an electric bicycle on a large curvature road based on trajectory data according to claim 1 is characterized in that: The process of acquiring and cleaning the trajectory data in step S1 is as follows: Step S11: The electric bicycle trajectory data comes from the desensitized data of the shared electric bicycle operator, including the order number, trajectory timestamp, and longitude and latitude coordinates; Step S12: cleaning the track data of drift points and missing points caused by the failure of the electric bicycle GPS sensor device or the occlusion of high-rise buildings in the city.

3. The method for identifying the reverse behavior of an electric bicycle on a large curvature road based on trajectory data according to claim 1 is characterized in that: The map matching process in step S2 is as follows: Step S21: road network data preparation; Step S22: After map matching, three attributes will be added to each trajectory point, namely, the road section ID, one-way and two-way identification, and road direction angle.

4. The method for identifying the reverse behavior of an electric bicycle on a large curvature road based on trajectory data according to claim 1 is characterized in that: The step S3 retrograde behavior identification process is as follows: Step S31: Arrange the trajectory points P in the trajectory subchain in ascending order of time i , where i is the time sorting identifier of the trajectory point; Step S32: P i , P i+1 Project to matching segment E j , get the projection point P′ i , P′ i+1 , j is the road section code identifier; Step S33: The method for identifying the reverse point on a one-way road is as follows: i , P′ i+1 Belong to the same road section sub-segment e jk , and P′ i , P′ i+1 With e jk Starting point jl The distance d i,jl <d i+1,jl When P i is a retrograde point, otherwise it is a direct point; when P′ i , P′ i+1 Not belonging to the same road segment jk When comparing P′ i Belongs to jk2 The position label k2 and P′ i+1 Belongs to jk1 The relative size of the position label k1, if P′ i The k2 number is larger, marked P i is a retrograde point, otherwise it is a direct point; where e jk is the road segment where the projection point is located, v jl is the starting point of the road section sub-segment, k and l are coding identifiers; Step S34: The method for identifying the reverse point on a two-way road is to use the projection point P′ i , P′ i+1 Constructing a temporary direction vector make Represents the trajectory point P i Riding direction; when a×b i =a x b y -a y b x >0, P i is a retrograde point, otherwise it is a direct point; Step S35: Calculate the number NW of all retrograde points in the trajectory chain T T and the number of trajectory points N T , when NW T / N T When >0.5, the trajectory chain T is a retrograde trajectory chain, otherwise it is an anterograde trajectory chain.

5. The method for identifying the reverse behavior of an electric bicycle on a large curvature road based on trajectory data according to claim 1 is characterized in that: The process of dividing the road network risk level in step S4 is as follows: Based on the trajectory data of shared electric bicycles, the frequency of wrong-moving behavior on each road section within a day is counted, and the severity of wrong-moving behavior is divided by appropriate frequency panes, and the road network risk level is displayed based on the GIS map platform.

6. The method for identifying the reverse behavior of an electric bicycle on a large curvature road based on trajectory data according to claim 2 is characterized in that: For the drift point, when d i,i+1 >v thr t i,i+1 When , delete the trajectory point P i ;for Missing point, when t i,i+1 >t thr When , the original trajectory chain is truncated to generate a new trajectory subchain; where P i represents the i-th trajectory point, d i,i+1 is the trajectory point P i With P i+1 The Euclidean distance, t i,i+1 is the trajectory point P i With P i+1 The time interval, v thr is the upper limit of the permissible speed, t thr The upper limit of the allowed time.

Images