A trajectory correction method

Abstract

The present application relates to the field of data processing technology, and in particular to a trajectory correction method and device. The method includes: obtaining each abnormal trajectory segment of a capture device; taking the abnormal trajectory segment that meets the second set condition as an independent trajectory segment, and determining that the number of each independent trajectory segment is greater than a quantity threshold; for each independent trajectory segment, determining the shortest path of the independent trajectory segment; and determining the path point that meets the third set condition from each path point included in each shortest path as the correction point of the abnormal trajectory point corresponding to the capture device. In the above manner, multiple shortest paths are obtained according to multiple abnormal trajectory segments, and correction points are selected from the shortest paths, which can effectively improve the accuracy of the selection of correction points for the capture device; and multiple capture trajectories of multiple capture devices can also be corrected, which effectively improves the efficiency of trajectory correction.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a trajectory correction method and device. Background Art

[0002] The data in modern traffic data systems are mainly obtained by capturing vehicles or pedestrians with camera equipment. Due to the merger of new and old data systems and cross-platform data interaction in recent years, the captured data in the data system contains a large amount of invalid location information, resulting in deviations in the trajectory of vehicles or pedestrians.

[0003] In the prior art, the invalid location information is checked mainly manually. The captured information of the captured object is visualized. After the wrong capture point is observed manually, the capture device corresponding to the wrong capture point is found in the data system, and the capture device is corrected. After the correction, the captured data is corrected. However, in a city road network, the captured data obtained every day is massive, and the work in the above method is mainly completed manually, which will consume a lot of labor costs and time costs, and the accuracy of correcting the trajectory of vehicles or pedestrians is very low.

[0004] Based on this, there is an urgent need for a trajectory correction method and device to improve the efficiency and accuracy of trajectory correction. Summary of the invention

[0005] The present application provides a trajectory correction method and device for improving the efficiency and accuracy of trajectory correction.

[0006] In a first aspect, the present application provides a trajectory correction method, the method comprising: obtaining each abnormal trajectory segment of a capture device; any abnormal trajectory segment is composed of each trajectory point in the capture trajectory of the captured object that meets a first set condition; each trajectory point includes an abnormal trajectory point corresponding to the capture device; abnormal trajectory segments that meet a second set condition are determined from the abnormal trajectory segments as independent trajectory segments, and it is determined that the number of the independent trajectory segments is greater than a quantity threshold; the second set condition is that the capture device sequences corresponding to the trajectory points in any two abnormal trajectory segments are not exactly the same; for each of the independent trajectory segments, based on the starting trajectory point of the independent trajectory segment and the ending trajectory point of the independent trajectory segment, the shortest path of the independent trajectory segment is determined; from each path point included in each shortest path, a path point that meets a third set condition is determined as a correction point for the abnormal trajectory point corresponding to the capture device.

[0007] Through the above method, by obtaining abnormal trajectory segments for the capture device from the capture trajectory of each capture object, the abnormal trajectory segments are summarized based on the capture device; then multiple shortest paths are obtained based on multiple abnormal trajectory segments, and correction points are selected based on multiple shortest paths. By performing a comprehensive analysis on multiple different shortest paths for the same capture device, the accuracy of selecting correction points for the capture device can be effectively improved, and multiple capture trajectories of multiple capture devices can also be corrected, effectively improving the efficiency of trajectory correction.

[0008] In one possible implementation, any abnormal trajectory segment is obtained from the capture trajectory of the captured object and is a set of trajectory points that meet the set conditions, including: for any abnormal trajectory point in the capture trajectory of the captured object for the capture device, determining the first normal trajectory point before the abnormal trajectory point as the first trajectory point and determining the first normal trajectory point after the abnormal trajectory point as the second trajectory point, and taking each trajectory point from the first trajectory point to the second trajectory point as the abnormal trajectory segment corresponding to the abnormal trajectory point.

[0009] In the above manner, since the captured trajectory contains many trajectory points, the accuracy of trajectory correction can be effectively guaranteed by obtaining abnormal trajectory segments in a precise manner.

[0010] In a possible implementation, the abnormal trajectory point is determined in the following manner, including: for any trajectory point Pi in the captured trajectory of the captured object, if the first speed Vi from the Pi-1 trajectory point to the Pi trajectory point is greater than the speed threshold, and the second speed Vi+1 from the Pi trajectory point to the Pi+1 trajectory point is greater than the speed threshold, then the trajectory point Pi is determined to be an abnormal trajectory point.

[0011] In the above method, the trajectory points with abnormal velocities in both sections are regarded as abnormal trajectory points, so that the trajectory points deviating from the normal trajectory points can be accurately found.

[0012] A possible implementation method is to determine the shortest path of the independent trajectory segment based on the starting trajectory point of the independent trajectory segment and the ending trajectory point of the independent trajectory segment, including: performing road network fitting based on the starting trajectory point of the independent trajectory segment and the ending trajectory point of the independent trajectory segment to obtain each path point between the starting trajectory point and the ending trajectory point; and obtaining the shortest path of the independent trajectory segment based on the each path point.

[0013] In the above method, the shortest path of the abnormal trajectory segment is simulated based on the road network, and the shortest path is used as the possible trajectory in the abnormal trajectory segment, which improves the reliability of obtaining the real trajectory and further improves the accuracy of trajectory correction.

[0014] A possible implementation method is to determine the correction points for the abnormal trajectory points of the capture device based on the path points in the shortest paths corresponding to the independent trajectory segments, including: determining the path points that appear most frequently in the shortest paths corresponding to the independent trajectory segments as the correction points; and for any abnormal trajectory segment, correcting the abnormal trajectory points for the capture device in the abnormal trajectory segment based on the correction points.

[0015] In the above manner, the path point that appears most frequently in the shortest path is used as the correction point, which is obtained based on the most likely real driving trajectory, and can effectively improve the accuracy of trajectory correction.

[0016] A possible implementation method, after determining the shortest path of the independent trajectory segment, further includes: for any shortest path, taking the road segment between adjacent path points in the shortest path as the minimum road segment unit; taking the minimum road segment unit with the largest number of occurrences in each shortest path as the correction unit; and merging the correction units with common path points in each correction unit into one correction unit.

[0017] The correction unit can be obtained in the above manner, and the obtained correction points can be checked by the correction unit.

[0018] A possible implementation method, before obtaining each abnormal trajectory segment of the capture device, also includes: obtaining the capture data of each capture object from the capture data within a set time period; for any capture object, splitting the capture data of the capture object into multiple capture trajectories; wherein the capture time difference between adjacent trajectory points in any capture trajectory is less than a time threshold; if any capture trajectory includes an abnormal trajectory point for the capture device, determining the abnormal trajectory segment of the capture device from the capture trajectory.

[0019] By dividing the captured data and obtaining the captured trajectories in the above manner, it is possible to correct many captured trajectories at the same time, which improves the correction efficiency and facilitates the subsequent verification of the correction results.

[0020] A possible implementation method, after determining the correction point for the abnormal trajectory point of the capture device, also includes: according to the correction point, correcting the abnormal trajectory segment having the abnormal trajectory point for the capture device in another capture device; the number of independent trajectory segments possessed by the other capture device is not greater than the quantity threshold; after the correction, returning to the step of obtaining each abnormal trajectory segment of the capture device, and continuing to perform the correction for the abnormal trajectory point of the other capture device.

[0021] The above method can realize multiple rounds of trajectory correction, which effectively improves the accuracy of trajectory correction.

[0022] In a possible implementation, the method further includes: outputting at least one of the following: device information of each capture device having abnormal trajectory segments; each abnormal trajectory segment corresponding to each capture device and each abnormal trajectory segment after correction; each correction unit corresponding to each capture device.

[0023] By storing the various results output during the processing, the correction process can be verified and the accuracy of trajectory correction can be further improved.

[0024] In a second aspect, the present application provides a trajectory correction device, including an acquisition unit and a determination unit.

[0025] The acquisition unit is used to acquire each abnormal trajectory segment of the capture device; any abnormal trajectory segment is each trajectory point that meets the set conditions and is obtained from the capture trajectory of the capture object; and each trajectory point includes at least one abnormal trajectory point for the capture device.

[0026] A determination unit is used to take abnormal trajectory segments that meet set conditions as independent trajectory segments, and determine that the number of the independent trajectory segments is greater than a quantity threshold; the set condition is: there is no inclusion relationship between a first capture device sequence corresponding to each trajectory point in a first independent trajectory segment of any two independent trajectory segments and a second capture device sequence corresponding to each trajectory point in a second independent trajectory segment.

[0027] The determination unit is also used to determine, for any independent trajectory segment, the shortest path of the independent trajectory segment based on the starting trajectory point of the independent trajectory segment and the ending trajectory point of the independent trajectory segment, and to determine the correction point for the abnormal trajectory point of the capture device based on each path point in each shortest path corresponding to each independent trajectory segment.

[0028] In a third aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is run, any one of the methods in the first aspect is executed.

[0029] In a fourth aspect, the present application provides a computing device, comprising: a memory for storing program instructions; a processor for calling the program instructions stored in the memory, and executing the method in any one of the designs in the above-mentioned first aspect according to the obtained program.

[0030] In a fifth aspect, the present application provides a computer program product, which, when executed on a processor, implements a method as in any one of the designs of the first aspect.

[0031] The beneficial effects of the second to fifth aspects mentioned above can be specifically referred to the beneficial effects that can be achieved by any design of the first aspect mentioned above, and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present application is exemplified;

[0033] Figure 2 A schematic diagram of a vehicle driving trajectory provided by an embodiment of the present application is exemplarily shown;

[0034] Figure 3 A schematic diagram of an abnormal driving trajectory of a vehicle provided in an embodiment of the present application is exemplarily shown;

[0035] Figure 4 A schematic diagram of a trajectory correction method provided by an embodiment of the present application is exemplarily shown;

[0036] Figure 5 A schematic diagram exemplarily showing an abnormal trajectory segment provided in an embodiment of the present application;

[0037] Figure 6 A schematic diagram exemplarily illustrates a method for obtaining an abnormal trajectory segment provided in an embodiment of the present application;

[0038] Figure 7 A schematic diagram exemplarily showing a type of captured data provided by an embodiment of the present application;

[0039] Figure 8 A schematic diagram of splitting captured data provided by an embodiment of the present application is exemplified;

[0040] Fig. 9 A schematic diagram exemplarily shows another method of splitting captured data provided in an embodiment of the present application;

[0041] Fig.10 A schematic diagram exemplarily showing an abnormal trajectory point provided by an embodiment of the present application;

[0042] Fig.11 A schematic diagram of a snapshot trajectory sequence provided by an embodiment of the present application is exemplarily shown;

[0043] Fig.12 Another snapshot trajectory sequence diagram provided by an embodiment of the present application is exemplarily shown;

[0044] Fig.13 A schematic diagram exemplarily showing an abnormal trajectory segment provided in an embodiment of the present application;

[0045] Fig.14 A schematic diagram exemplarily showing another abnormal trajectory segment provided in an embodiment of the present application;

[0046] Fig.15A schematic diagram exemplarily showing an independent trajectory segment provided in an embodiment of the present application;

[0047] Fig.16 A schematic diagram of the shortest path of an independent trajectory segment provided by an embodiment of the present application is exemplarily shown;

[0048] Fig.17 Another shortest path schematic diagram of an independent trajectory segment provided in an embodiment of the present application is exemplarily shown;

[0049] Fig.18 A schematic diagram of the shortest path of another independent trajectory segment provided in an embodiment of the present application is exemplarily shown;

[0050] Fig.19 A schematic diagram of the shortest path of another independent trajectory segment provided in an embodiment of the present application is exemplarily shown;

[0051] Fig. 20 Another snapshot trajectory sequence diagram provided by an embodiment of the present application is exemplarily shown;

[0052] Fig.21 A schematic diagram of a trajectory correction device provided in an embodiment of the present application is exemplarily shown. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Figure 1 The following is a schematic diagram of an application scenario provided by an embodiment of the present application. Figure 1 As shown, the application scenario of the present application can be an urban road scenario. There are many crisscrossing roads 103 in the city, pedestrians 102 walk on the roads 103, and vehicles 101 drive on the roads 103. A capture device 104 will be installed on the road 103 to capture pedestrians and vehicles. Taking vehicle 101 as an example, the vehicle 101 will generate a driving trajectory when driving on the road 103. After the capture device 104 captures the vehicle, a capture point will be generated on the driving trajectory. After the capture device 104 captures the vehicle 101, the ID of the capture device 104, the coordinates of the capture device 104, and the capture time are recorded and stored in the database.

[0055] Figure 2 A schematic diagram of a vehicle driving trajectory provided by an embodiment of the present application is exemplarily shown. Figure 2As shown in the figure, there are some snapshot points on the vehicle's driving trajectory, which are generated when the vehicle is captured by the snapshot device during driving. The snapshot points are stored in the data system in the form of longitude and latitude, for example, Figure 2 The coordinates of point A in the example are (E123°36′, N40°28′). In the embodiment of the present application, the vehicle driving trajectory extracted from the database may be the vehicle driving trajectory within a period of time, such as a month, and the vehicle driving trajectory within this month is analyzed and corrected. Figure 2 It only shows a part of the vehicle's driving trajectory within one month.

[0056] When obtaining the vehicle's driving trajectory from the system, the system may integrate data from multiple platforms, or there may be data migration between the new system and the old system, or there may be abnormalities in the capture device, which may cause errors in the capture data of the capture point on the vehicle's driving trajectory. For example, when entering the capture device information, the longitude and latitude coordinates of the capture device are written in reverse, which is reflected in the vehicle's driving trajectory as an offset of the capture point. Figure 3 The following is a schematic diagram of an abnormal driving trajectory of a vehicle provided in an embodiment of the present application. Figure 3 As shown, there is a snapshot point B with a lot of offset in the vehicle's driving trajectory. This snapshot point is captured by the snapshot device b. From the map, it can be seen that the snapshot point B is very far away from the previous snapshot point and the next snapshot point, which may be caused by an error in the snapshot device b.

[0057] For the capture point B, one of the existing methods is to directly remove the capture point B from the vehicle's trajectory, but this will lose some useful information. Another method is to manually correct the capture data of the capture point B. The main method is to find the information of the capture device b in the database after determining that the capture point B has a deviation, and correct the information of the capture device b. One of the important verification items is whether the device coordinates of the capture device b are filled in incorrectly, which is an important factor affecting the position of the capture point B. However, the coordinates of the capture device b are entered when the system is established. It will be very difficult to find the original data at this time. Therefore, it will take a lot of time to obtain the correct coordinates of the capture device b.

[0058] Therefore, the present application provides a trajectory correction method, which can correct the deviated capture points, thereby improving the efficiency of the entire trajectory correction.

[0059] Figure 4 A schematic diagram of a trajectory correction method provided in an embodiment of the present application is shown as an example. Figure 4 As shown, the method comprises the following steps:

[0060] Step 401, obtaining each abnormal trajectory segment of the capture device; any abnormal trajectory segment is composed of each trajectory point in the capture trajectory of the capture object that meets the first set condition; the each trajectory point includes the abnormal trajectory point corresponding to the capture device.

[0061] It should be noted that the abnormal trajectory segment is composed of trajectory points, and at least one of the trajectory points that constitute the abnormal trajectory segment is an abnormal trajectory point. Figure 5 The following is a schematic diagram showing an abnormal trajectory segment provided by an embodiment of the present application. Figure 5 As shown, the starting point A and the end point G of an abnormal trajectory segment are normal trajectory points, and there are 5 trajectory points between the starting point and the end point, among which the first trajectory point B, the third trajectory point D and the fourth trajectory point E are abnormal trajectory points, and the second trajectory point C and the fifth trajectory point F are normal trajectory points.

[0062] Figure 6 A schematic diagram exemplarily illustrates a method for obtaining abnormal trajectory segments provided in an embodiment of the present application. Figure 6 As shown, the method for obtaining the abnormal trajectory fragment includes:

[0063] Step 601, acquiring the captured data of each captured object from the captured data within a set time period.

[0064] Exemplarily, the set period can be set to one month, and the trajectory correction is performed on the captured object within this month. In the following steps, the captured object is a vehicle as an example for introduction. The captured data of the vehicle obtained includes: the identification of the capture device, the coordinates of the capture device and the capture time.

[0065] Figure 7 A schematic diagram of a captured data provided by an embodiment of the present application is exemplarily shown. Figure 7 As shown, assuming that the captured objects are vehicle 1 and vehicle 2, the trajectories of vehicle 1 and vehicle 2 in March 2022 are as follows Figure 7 As shown, there is a track point A on the trajectory of vehicle 1. The data of this track point was captured by device 1 at 15:38:55 on March 24, 2022. The coordinates of this track point are 115.25 degrees east longitude and 34.26 degrees north latitude.

[0066] Step 602: for any captured object, split the captured data of the captured object into multiple captured tracks. If any captured track includes an abnormal track point for the captured device, determine the abnormal track segment of the captured device from the captured track.

[0067] In a possible implementation, the capture time difference between adjacent track points in any capture track is less than a time threshold.

[0068] Figure 8 The following is a schematic diagram of splitting snapshot data provided by an embodiment of the present application. Figure 8 As shown in the figure, assuming that the time threshold is set to 8 hours, there is a gap of 9 hours between track point B and track point C, which means that no capture device captured vehicle 1 within these 9 hours. The capture track AB, capture track BC and the track after track point C are obtained by splitting with track point B and track point C as the dividing points. After track point C, there is a gap of 10 hours between track point E and track point F. Although the distance between track point E and track point F is very small, it may contain the time when vehicle 1 was parked in the garage, so the capture track CE and the capture track after track point F are still obtained with track point E and track point F as the dividing points. It should be noted that if it can be determined that the vehicle has a long period of stagnation between two track points, the segment between the two track points can be filtered out.

[0069] In another possible implementation, the captured data may be segmented according to time intervals to obtain the captured trajectory. The time interval may be set based on the general driving time or usage cycle of the vehicle. Fig. 9 Another schematic diagram of splitting captured data provided by an embodiment of the present application is exemplarily shown. Fig. 9 As shown in , assuming that the time interval is set to 24 hours, for example, 7 am on the first day to 7 am on the second day is a snapshot track. Fig. 9 As shown, in the first captured trajectory, trajectory points AH are included, while in the second captured trajectory, only trajectory point I is included. This may be because the vehicle traveled a shorter distance on this day.

[0070] By dividing the captured data and obtaining the captured trajectories in the above manner, it is possible to correct many captured trajectories at the same time, which improves the correction efficiency and facilitates the subsequent verification of the correction results.

[0071] Step 603, determine an abnormal trajectory point for the captured trajectory of the captured object. For any trajectory point Pi, if the first speed Vi from the Pi-1 trajectory point to the Pi trajectory point is greater than the speed threshold, and the second speed Vi+1 from the Pi trajectory point to the Pi+1 trajectory point is greater than the speed threshold, then determine that the trajectory point Pi is an abnormal trajectory point.

[0072] Fig.10 The following is a schematic diagram showing an abnormal trajectory point provided by an embodiment of the present application. Fig.10 The captured trajectory shown can be Fig. 9The captured trajectory AH in the figure. The following takes the trajectory point P2 as an example to illustrate, and calculates the first speed between the trajectory point P1 and the trajectory point P2, and the second speed between the trajectory point P2 and the trajectory point P3. If the first speed and the second speed are both greater than the speed threshold, the trajectory point P2 is taken as an abnormal trajectory point. Based on the capture position and capture time in the capture data corresponding to each trajectory point, the above-mentioned first speed and second speed can be obtained. Of course, the speed of the capture point can also be directly determined based on the speed detection function of the capture device. At this time, it can also be directly determined whether it is an abnormal trajectory point based on the speed of point P2.

[0073] After determining whether a track point in a captured track is an abnormal track point or a normal track point, the abnormal track point is marked as 1, the normal track point is marked as 0, and the two endpoints in a captured track are marked as 3, and multiple captured track sequences can be obtained.

[0074] Fig.11 A schematic diagram of a snapshot trajectory sequence provided by an embodiment of the present application is exemplarily shown. Fig.11 As shown, a total of N capture trajectory sequences are obtained. The N capture trajectories may be capture trajectories of the same vehicle in different time periods, capture trajectories of multiple vehicles in the same time period, or capture trajectories of multiple vehicles in multiple time periods.

[0075] Fig.12 Another snapshot trajectory sequence diagram provided by an embodiment of the present application is exemplarily shown. Fig.12 As shown, the continuously appearing abnormal trajectory points can be marked as 2, and the captured trajectories can be classified and stored after the correction is completed to facilitate subsequent verification.

[0076] Step 604, determining an abnormal trajectory segment according to the abnormal trajectory point in the captured trajectory of the captured object. For any abnormal trajectory point for the captured device in the captured trajectory of the captured object, determine the first normal trajectory point before the abnormal trajectory point as the first trajectory point and determine the first normal trajectory point after the abnormal trajectory point as the second trajectory point, and use each trajectory point from the first trajectory point to the second trajectory point as the abnormal trajectory segment corresponding to the abnormal trajectory point.

[0077] Exemplarily, an abnormal trajectory segment can be extracted according to the captured trajectory series in step 603, and the abnormal trajectory segment can be divided into the following two forms according to whether the abnormal trajectory points in the abnormal trajectory segment are continuous:

[0078] Fig.13 The following is a schematic diagram showing an abnormal trajectory segment provided by an embodiment of the present application. Fig.13As shown, the track point P2 is a discontinuous abnormal track point, so the normal track point P1 before the track point P2 is used as the starting point of the abnormal track segment, and the normal track point P3 after the track point P2 is used as the end point of the abnormal track segment to obtain the first abnormal track segment.

[0079] Fig.14 The following is a schematic diagram showing another abnormal trajectory segment provided by an embodiment of the present application. Fig.14 As shown, the abnormal trajectory point P5 and the abnormal trajectory point P6 are consecutive abnormal trajectory points, so the normal trajectory point P4 before the abnormal trajectory point P5 is used as the starting point of the abnormal trajectory segment, and the normal trajectory point P7 after the abnormal trajectory point P6 is used as the end point of the abnormal trajectory segment to obtain the second abnormal trajectory segment.

[0080] Through the above method, the obtained first abnormal trajectory segment and the second abnormal trajectory segment can be classified and processed, which can effectively improve the correction efficiency, and can also be classified and stored to facilitate the verification of the correction result.

[0081] Step 402: determine the abnormal trajectory segments that meet the second setting condition from the abnormal trajectory segments as independent trajectory segments, and determine that the number of the independent trajectory segments is greater than the number threshold. The second setting condition is that the capture device sequences corresponding to the trajectory points in any two abnormal trajectory segments are not completely the same.

[0082] In the above step 401, since the same vehicle may repeatedly pass through a section of road or different vehicles may pass through the same section of road, the acquired abnormal track segments may be repeated. Before correcting the abnormal track segments, it is necessary to remove duplicates.

[0083] Fig.15 The following is a schematic diagram showing an independent trajectory segment provided by an embodiment of the present application. Fig.15 As shown, when obtaining the abnormal trajectory segment of the captured trajectory 1, the abnormal trajectory segment XYZ is obtained, and when obtaining the abnormal trajectory segment of the captured trajectory 2, the abnormal trajectory segment XYZ is also obtained. The capture devices that capture the trajectory points X, Y, and Z are exactly the same, so one of the abnormal trajectory segments XYZ is removed. There is no abnormal trajectory segment ZWU that repeats it, so the abnormal trajectory segment ZWU is an independent abnormal trajectory segment.

[0084] Step 403 : for each independent trajectory segment, based on the starting trajectory point of the independent trajectory segment and the ending trajectory point of the independent trajectory segment, determine the shortest path of the independent trajectory segment.

[0085] A possible implementation method is to perform road network fitting based on the starting trajectory point of the independent trajectory segment and the ending trajectory point of the independent trajectory segment, obtain each path point between the starting trajectory point and the ending trajectory point; and obtain the shortest path of the independent trajectory segment based on each path point.

[0086] Fig.16 The shortest path schematic diagram of an independent trajectory segment provided by an embodiment of the present application is exemplarily shown. Fig.16 As shown, the normal track point P1 is the starting point of the abnormal track segment where the abnormal track point P2 is located, and the normal track point P3 is the end point of the abnormal track segment where the abnormal track point P2 is located. Then, the path points from p1 to P3 are combined in combination with the road network simulation, and these path points are connected to obtain the shortest path 1. In the same way, the shortest path 2 corresponding to the abnormal track segments where the abnormal track points P5 and P6 are located is obtained.

[0087] Step 404: determine, from among the path points included in each shortest path, a path point that satisfies a third set condition as a correction point for the abnormal trajectory point corresponding to the capture device.

[0088] Exemplarily, the third setting condition may be: determining the path point with the largest number of occurrences in each shortest path corresponding to each independent trajectory segment as the correction point; for any abnormal trajectory segment, correcting the abnormal trajectory point for the capture device in the abnormal trajectory segment based on the correction point.

[0089] Still taking the abnormal trajectory point P2 as an example, the captured data of the abnormal trajectory point P2 is obtained by capturing the device two. Therefore, it is possible that the abnormal trajectory point P2 is caused by an error in the device two. Therefore, there are multiple abnormal trajectory segments corresponding to the device two. Therefore, in step 401, multiple abnormal trajectory segments including the abnormal trajectory point P2 will be obtained, and in step 404, multiple shortest paths can be obtained.

[0090] Fig.17 Another shortest path schematic diagram of an independent trajectory segment provided in an embodiment of the present application is exemplarily shown, such as Fig.17 As shown, there are three shortest paths related to the abnormal trajectory point P2. The shortest paths are connected by path points. The path points appearing in these three shortest paths are counted and sorted according to the number of times they appear. It is found that P2' appears the most times, so the path point P2' is used as the correction point of the abnormal trajectory point P2.

[0091] Exemplarily, for any shortest path, the road segment between adjacent path points in the shortest path can be used as the minimum road segment unit. Fig.18 A schematic diagram of the shortest path of another independent trajectory segment provided in an embodiment of the present application is exemplarily shown, such as Fig.18In the shortest path shown, there are 7 path points. The section between path point A and path point B can be regarded as a minimum path section unit (AB), the section between path point B and path point C can be regarded as a minimum path section unit (BC), and the section between path point C and path point D can be regarded as a minimum path section unit (CD).

[0092] For all the shortest paths of an abnormal trajectory point, after obtaining all the minimum road segment units on these shortest paths, count the minimum road segment units that appear the most times among these minimum road segment units, and output the minimum road segment units that appear the most times. Generally speaking, there are multiple minimum road segment units that appear the most times. At this time, the correction units with common path points in each correction unit can be merged into one correction unit. If the corresponding minimum road segment units in another shortest path include minimum road segment units (AB), (BC) and (CF), the minimum road segment units that appear the most times are (AB) and (BC) as correction units. Since correction units (AB) and (BC) have a common path point B, they are merged into correction unit (AC).

[0093] Fig.19 A schematic diagram of the shortest path of another independent trajectory segment provided in an embodiment of the present application is exemplarily shown, such as Fig.19 As shown, there are multiple minimum road section units between the path point H and the path point Y. These minimum road section units appear three times, and these minimum road section units have common points. These minimum road section units can be merged to obtain the correction unit HY.

[0094] The correction unit can be obtained in the above manner, and the obtained correction points can be checked by the correction unit.

[0095] After determining the correction point for the abnormal trajectory point of the capture device, the abnormal trajectory segment having the abnormal trajectory point for the capture device in another capture device can also be corrected according to the correction point; the number of independent trajectory segments possessed by the other capture device is not greater than the quantity threshold; after the correction, return to the step of obtaining the abnormal trajectory segments of the capture device, and continue to perform the correction for the abnormal trajectory point of the other capture device.

[0096] Taking the above-mentioned capture trajectory 3 as an example, Fig. 20 Another snapshot trajectory sequence diagram provided by an embodiment of the present application is exemplarily shown. Fig. 20As shown, in the process of correcting the abnormal trajectory segment (0220) in the above-mentioned captured trajectory three, the abnormal trajectory segments corresponding to device two and device three are both (0220). Assume that the number of independent trajectory segments corresponding to device two is greater than the number threshold, and the number of independent trajectory segments corresponding to device three is not greater than the number threshold. Then in the first round of correction, the abnormal trajectory points of device two are corrected successfully, and the abnormal trajectory points of device three fail to be corrected. After correcting the abnormal trajectory points corresponding to device two through the above-mentioned trajectory correction process, the abnormal trajectory points corresponding to device three are corrected. At this time, the abnormal trajectory segment corresponding to device three becomes 010, and then the abnormal trajectory points corresponding to device three are corrected in combination with other abnormal trajectory segments corresponding to device three.

[0097] The processing results obtained in the above correction process can be output, such as storage or display, including: device information of each capture device with abnormal trajectory segments, each abnormal trajectory segment corresponding to each capture device and each abnormal trajectory segment after correction, each correction unit corresponding to each capture device, etc.

[0098] Based on the same technical concept as in the above method processes, an embodiment of the present invention further provides a trajectory correction device.

[0099] Fig.21 The following is a schematic diagram of a trajectory correction device provided by an embodiment of the present application. The trajectory correction device includes an acquisition unit 2101 and a determination unit 2102.

[0100] The acquisition unit 2101 captures abnormal trajectory segments of the device; any abnormal trajectory segment is composed of trajectory points in the captured trajectory of the captured object that meet the first set condition; and the trajectory points include the abnormal trajectory points corresponding to the captured device.

[0101] The determination unit 2102 determines, from the abnormal trajectory segments, abnormal trajectory segments that meet a second set condition as independent trajectory segments, and determines that the number of the independent trajectory segments is greater than a quantity threshold; the second set condition is that the capture device sequences corresponding to the trajectory points in any two abnormal trajectory segments are not completely the same.

[0102] The determination unit 2102 is also used to determine, for any independent trajectory segment, the shortest path of the independent trajectory segment based on the starting trajectory point of each independent trajectory segment and the ending trajectory point of the independent trajectory segment, and to determine, from the path points included in each shortest path, a path point that meets the third set condition as a correction point for the abnormal trajectory point corresponding to the capture device.

[0103] Based on the same technical concept, an embodiment of the present invention further provides a computing device, including: a memory for storing program instructions;

[0104] The processor is used to call the program instructions stored in the memory and execute the methods shown in the above method flow according to the obtained program.

[0105] Based on the same technical concept, an embodiment of the present invention further provides a computer-readable storage medium, which implements the methods shown in the above method flow when the computer program product runs on a processor.

[0106] Based on the same technical concept, an embodiment of the present invention further provides a computer program product, which, when executed on a processor, implements the following Figure 4 or Figure 6 The method indicated.

[0107] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0108] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0111] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A trajectory correction method, characterized in that: The method comprises: Acquire each abnormal trajectory segment of the capture device; any abnormal trajectory segment is composed of each trajectory point in the capture trajectory of the captured object that meets the first set condition; each trajectory point includes the abnormal trajectory point corresponding to the capture device; the first set condition is to determine the first normal trajectory point before the abnormal trajectory point, and to determine the first normal trajectory point after the abnormal trajectory point; Determine, from the abnormal trajectory segments, abnormal trajectory segments that meet a second setting condition as independent trajectory segments, and determine that the number of the independent trajectory segments is greater than a number threshold; the second setting condition is that the capture device sequences corresponding to the trajectory points in any two abnormal trajectory segments are not completely the same; For each of the independent trajectory segments, determining the shortest path of the independent trajectory segment based on a starting trajectory point of the independent trajectory segment and an ending trajectory point of the independent trajectory segment; A path point satisfying a third setting condition is determined from each path point included in each shortest path as a correction point for the abnormal trajectory point corresponding to the capture device; wherein the third setting condition is the path point that appears most frequently in each shortest path corresponding to each independent trajectory segment.

2. The method according to claim 1, characterized in that Any abnormal trajectory segment is composed of each trajectory point in the captured trajectory of the captured object that meets the first set condition, including: For any abnormal trajectory point of the capture device in the capture trajectory of the captured object, the first normal trajectory point before the abnormal trajectory point is determined as the first trajectory point and the first normal trajectory point after the abnormal trajectory point is determined as the second trajectory point, and each trajectory point between the first trajectory point and the second trajectory point is used as the abnormal trajectory segment corresponding to the abnormal trajectory point.

3. The method according to claim 1, characterized in that The abnormal trajectory points are determined by the following methods, including: For any track point Pi in the captured track of the captured object, if the first speed Vi from the Pi-1 track point to the Pi track point is greater than the speed threshold, and the second speed Vi+1 from the Pi track point to the Pi+1 track point is greater than the speed threshold, then the track point Pi is determined to be an abnormal track point.

4. The method according to claim 1, characterized in that Determining the shortest path of the independent trajectory segment based on the starting trajectory point of the independent trajectory segment and the ending trajectory point of the independent trajectory segment includes: Performing road network fitting based on the starting trajectory point of the independent trajectory segment and the ending trajectory point of the independent trajectory segment to obtain each path point between the starting trajectory point and the ending trajectory point; The shortest path of the independent trajectory segment is obtained based on the path points.

5. The method according to claim 1, characterized in that Determining, from each path point included in each shortest path, a path point that meets a third setting condition as a correction point of the abnormal trajectory point corresponding to the capture device, comprising: Determine the path point with the largest number of occurrences in each shortest path corresponding to each independent trajectory segment as a correction point; For any abnormal trajectory segment, the abnormal trajectory points for the capture device in the abnormal trajectory segment are corrected based on the correction points.

6. The method according to claim 1, characterized in that After determining the shortest path of the independent trajectory segment, the method further includes: For any shortest path, the road segment between adjacent path points in the shortest path is used as the minimum road segment unit; The smallest road segment unit that appears most times in each shortest path is used as the correction unit; The correction units having common path points among the correction units are merged into one correction unit.

7. The method according to any one of claims 1 to 6, characterized in that: Before obtaining each abnormal trajectory fragment of the capture device, it also includes: Obtaining the captured data of each captured object from the captured data within a set time period; For any captured object, the captured data of the captured object is split into multiple captured trajectories; wherein the captured time difference between adjacent trajectory points in any captured trajectory is less than a time threshold; if any captured trajectory includes abnormal trajectory points for the captured device, the abnormal trajectory segment of the captured device is determined from the captured trajectory.

8. The method according to claim 7, characterized in that After determining the correction point of the abnormal trajectory point corresponding to the capture device, the method further includes: According to the correction point, correcting the abnormal trajectory segment having the abnormal trajectory point for the capture device in another capture device; the number of independent trajectory segments of the another capture device is not greater than the number threshold; After the correction, the process returns to the step of obtaining each abnormal trajectory segment of the capture device, and continues to perform the correction for the abnormal trajectory points of the other capture device.

9. The method according to claim 7, characterized in that The method further includes: outputting at least one of the following: Device information of each capture device with abnormal trajectory segments; Each abnormal trajectory segment corresponding to each capture device and each abnormal trajectory segment after correction; Each correction unit corresponds to each capture device.

10. A trajectory correction device, characterized in that: The device comprises an acquisition unit and a determination unit; The acquisition unit is used to capture each abnormal trajectory segment of the capture device; any abnormal trajectory segment is composed of each trajectory point in the capture trajectory of the captured object that meets the first set condition; each trajectory point includes the abnormal trajectory point corresponding to the capture device; the first set condition is to determine the first normal trajectory point before the abnormal trajectory point, and to determine the first normal trajectory point after the abnormal trajectory point; The determining unit determines, from the abnormal trajectory segments, abnormal trajectory segments that meet a second setting condition as independent trajectory segments, and determines that the number of the independent trajectory segments is greater than a number threshold; the second setting condition is that the capture device sequences corresponding to the trajectory points in any two abnormal trajectory segments are not completely the same; The determination unit is also used to determine, for any independent trajectory segment, the shortest path of the independent trajectory segment based on the starting trajectory point of each independent trajectory segment and the ending trajectory point of the independent trajectory segment, and to determine, from the path points included in each shortest path, a path point that meets a third setting condition as a correction point for the abnormal trajectory point corresponding to the capture device; wherein the third setting condition is the path point that appears the most times in each shortest path corresponding to each independent trajectory segment.

Images