Muck truck activity area analysis method and system based on trajectory data

Abstract

The invention provides a slag car activity area analysis method and system based on trajectory data, and relates to the technical field of traffic trajectories, and the method comprises the following steps: S1, obtaining a resident clustering point area with a resident point location as a central point; s2, judging whether the distance difference value of the central points between the resident clustering point areas exceeds a threshold value or not, if not, performing area updating on the resident clustering point areas, and turning to the step S3; s3, slag car track points located in the resident clustering point area are obtained; and S4, carrying out average speed segmentation curve fitting on the slag car track points in the resident clustering point area, judging the scene type of the resident clustering point area according to curve characteristics of an average speed trend curve, and detecting whether a slag car moving area such as a newly added construction site or a dumping yard exists in the current area or not. Therefore, the activity area of the muck truck is supervised.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic trajectories, and in particular to a method and system for analyzing an activity area of ​​a muck truck based on trajectory data. Background Art

[0002] In order to ensure the safety of muck trucks in construction sites, dumping sites and other muck truck activity areas, it is necessary to supervise the muck truck activity areas. The current muck truck activity areas are registered so that the staff can clearly understand the scene type of the area. However, the registration records are usually manually inspected at locations suspected of being muck truck activity areas to count the current muck truck activity areas. This method consumes a lot of manpower costs, and when the area to be inspected is large, the efficiency of manual counting will be very low. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for analyzing the activity area of ​​a dump truck based on trajectory data. The residence clustering point area where the dump truck often resides is obtained by clustering the residence points, and the scene type of the current residence clustering point area can be determined according to the average speed change of the dump truck in the residence clustering point area. It can be used to detect whether there are new construction sites or dumping sites and other dump truck activity areas in the current area, so as to realize the role of supervising the activity area of ​​the dump truck through the trajectory data of the dump truck.

[0004] In order to solve the above technical problems, the present invention adopts the following solutions: A method for analyzing the activity area of ​​a muck truck based on trajectory data comprises the following steps: S1, obtaining multiple resident point groups screened out through the trajectory data of the muck truck, and matching the resident points in the resident point group to the divided grids, clustering each resident point group according to the adjacent grids, and obtaining a resident cluster point area with the resident point as the center point; S2, judging whether the distance difference between the center points of the resident cluster point areas exceeds a threshold value, if not, performing regional update on the resident cluster point areas, and going to step S3; S3, matching the track data of the muck truck corresponding to the resident point group to the resident cluster point area, and screening the track points of the muck truck in the current track data of the muck truck to obtain the track points of the muck truck located in the resident cluster point area; S4. Perform average speed segmented curve fitting on the trajectory points of the muck truck in the resident cluster point area to obtain a corresponding average speed trend curve, and determine the scene type of the resident cluster point area according to the curve characteristics of the average speed trend curve.

[0005] Further, in S1, the plurality of stationary point groups screened out through the trajectory data of the muck truck refers to grouping the stationary points whose travel distance within a preset time does not exceed a preset value screened out through the matrix method and the adaptive jump method according to time; The matrix method can be used to remove inactive track points of the muck truck from the track data of the muck truck; The adaptive jumping method can be used to identify whether a muck truck trajectory point surrounded by multiple muck truck trajectory points in the muck truck trajectory data is a stationary point. If so, the stationary point is matched to the divided grid.

[0006] Furthermore, in S1, the process of clustering each resident point group according to adjacent grids is as follows: Connecting the resident points located in adjacent grids to obtain a plurality of resident points connected in sequence; Calculate the distance difference between the dwelling points; The sum of the distance differences between each residence point and other residence points is counted respectively, and the sums are compared. The residence point with the smallest sum is taken as the center point, and the maximum distance difference of the center point is used as the radius to form the residence cluster point area.

[0007] Furthermore, in S2, the process of updating the resident cluster point area includes the following steps: SA1, take the median value of the distance difference between the center points of the two resident cluster point areas, take the point where the median value is located as the new center point, and determine whether the two resident cluster point areas are overlapping. If so, go to step SA2; if not, go to step SA3; SA2, according to the overlapping relationship and area size between the two resident cluster point areas, select the radius value of a resident cluster point area and add it to the middle value, use it as the current radius value, form a new resident cluster point area based on the new center point with the current radius value, and delete the corresponding two resident cluster point areas; SA3. Based on the new center point, a new resident cluster point area is formed with a preset radius value as the radius, and the corresponding two resident cluster point areas are deleted.

[0008] Further, in SA2, the process of selecting a radius value of a resident cluster point area and adding the intermediate value according to the overlapping relationship and area size between the two resident cluster point areas is: The overlapping relationship includes intersection and inclusion; When the overlapping relationship between two resident cluster point areas is intersection, the radius value of the resident cluster point area with a smaller area is selected and added to the middle value, and the value is used as the current radius value; When the overlapping relationship between two resident cluster point areas is inclusive, the radius value of the resident cluster point area with a larger area is selected and added to the middle value, which is used as the current radius value.

[0009] Furthermore, the step S4 includes the following steps: S41, connecting the track points of the muck trucks in the resident cluster point area in chronological order, obtaining the average speed values ​​between the track points of the muck trucks in the resident cluster point area in chronological order, and sorting the multiple average speed values ​​in chronological order; S42, judging in chronological order whether the change values ​​between the average speed values ​​are continuously less than the minimum value, if so, screening is performed based on the change values ​​that are continuously less than the minimum value, screening the average speed value at the center position as the segmentation point, and going to step S43; S43, splitting the multiple average speed values ​​into two segments according to the segmentation points, and performing linear fitting on the average speed values ​​of the two segments to obtain a corresponding average speed trend curve; S44: Determine the scene type of the resident cluster point area according to the slope of the average speed trend curves of the previous and next two sections.

[0010] Further, in S41, the process of obtaining the average speed values ​​between the track points of the muck truck in the resident cluster point area in sequence according to the time sequence is as follows: The distance difference and time difference between the track points of the muck trucks in the resident cluster point area are calculated in chronological order. The average speed value between the two track points of the muck trucks can be obtained by calculating the distance difference and time difference.

[0011] Further, in S44, the process of determining the scene type of the resident cluster point area according to the slope of the average speed trend curves of the previous and next two sections is as follows: If the slope of the average speed trend curve in the front section is greater than the slope of the average speed trend curve in the rear section, the scene type of the resident cluster point area is determined to be a dumping site; if the slope of the average speed trend curve in the front section is less than the slope of the average speed trend curve in the rear section, the scene type of the resident cluster point area is determined to be a construction site.

[0012] A system for analyzing the activity area of ​​a muck truck based on trajectory data, using a method for analyzing the activity area of ​​a muck truck based on trajectory data, comprising: The module for dividing the resident clustering points area is used to obtain multiple resident point groups filtered out by the trajectory data of the muck truck, and the resident points in the resident point group are matched to the divided grids. Each resident point group is clustered according to the adjacent grids to obtain the resident clustering point area with the resident point as the center point. Resident cluster point area update module: determines whether the distance difference between the center points of the resident cluster point areas exceeds a threshold, if not, updates the resident cluster point areas; Muck truck trajectory data matching module: matches the muck truck trajectory data corresponding to the resident point group to the resident cluster point area, and filters the muck truck trajectory points in the current muck truck trajectory data to obtain the muck truck trajectory points located in the resident cluster point area; Resident cluster point area determination module: perform average speed segmented curve fitting on the trajectory points of the muck truck in the resident cluster point area to obtain the corresponding average speed trend curve, and determine the scene type of the resident cluster point area according to the curve characteristics of the average speed trend curve.

[0013] Beneficial effects of the present invention: The present invention provides a method and system for analyzing the activity area of ​​a muck truck based on trajectory data. The method for analyzing the activity area of ​​a muck truck mainly analyzes the resident cluster point area through the trajectory data of the muck truck, and can determine the scene type of the resident cluster point area. It is not necessary to count the activity area of ​​the muck truck through manual inspection, which can effectively improve the efficiency of counting the activity area of ​​the muck truck and reduce labor costs.

[0014] In addition, the present invention filters the trajectory data to obtain the residence points, obtains the residence cluster point area where the dump truck often resides by clustering the residence points, and at the same time, updates and judges the area size of the residence cluster point area, which can improve the accuracy of the analysis of the dump truck activity area when confirming the size of the dump truck activity area. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Schematic diagram of the process of analyzing the activity area of ​​a muck truck in Example 1 of the present invention; Figure 2 Schematic diagram of the resident cluster point area 1 in Example 1 of the present invention; Figure 3 Schematic diagram of the resident cluster point area 2 in Example 1 of the present invention; Figure 4 It is a schematic diagram of the intersecting resident cluster point area 1 and resident cluster point area 2 in embodiment 1 of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. 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.

[0017] The relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0018] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0019] Additionally, descriptions of well-known structures, functions, and configurations may be omitted for clarity and conciseness.One of ordinary skill in the art will recognize that various changes and modifications may be made to the examples described herein without departing from the spirit and scope of the present disclosure.

[0020] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0021] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0022] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments: Example 1 In this embodiment, if Figure 1 As shown, a scene type analysis method based on the resident cluster point area is proposed, and the scene type analysis method includes the following steps: S1, obtaining multiple resident point groups screened out through the trajectory data of the muck truck, and matching the resident points in the resident point group to the divided grids, clustering each resident point group according to the adjacent grids, and obtaining a resident cluster point area with the resident point as the center point; S2, judging whether the distance difference between the center points of the resident cluster point areas exceeds a threshold value, if not, performing regional update on the resident cluster point areas, and going to step S3; S3, matching the track data of the muck truck corresponding to the resident point group to the resident cluster point area, and screening the track points of the muck truck in the current track data of the muck truck to obtain the track points of the muck truck located in the resident cluster point area; S4. Perform average speed segmented curve fitting on the trajectory points of the muck truck in the resident cluster point area to obtain a corresponding average speed trend curve, and determine the scene type of the resident cluster point area according to the curve characteristics of the average speed trend curve.

[0023] Based on the above-mentioned scene type analysis method, it can be seen that the present invention mainly uses the trajectory data generated by the dump truck in the resident clustering point area to analyze the scene type of the resident clustering point area. The resident clustering point area is an area obtained by clustering the resident points. This area can be expressed as an area where the dump truck often resides or an area where the dump truck often wanders. The location of the suspected dump truck activity area can be obtained through the resident clustering point area. There is no need for manual inspection, so the dump truck activity area can be supervised and the labor cost can be reduced.

[0024] Preferably, in S1, the plurality of stationary point groups screened out through the trajectory data of the muck truck refers to grouping the stationary points whose travel distance within a preset time does not exceed a preset value screened out through the matrix method and the adaptive jump method according to time; The matrix method can be used to remove inactive track points of the muck truck from the track data of the muck truck; The adaptive jumping method can be used to identify whether a muck truck trajectory point surrounded by multiple muck truck trajectory points in the muck truck trajectory data is a stationary point. If so, the stationary point is matched to the divided grid.

[0025] The above-mentioned screening by the matrix method and the adaptive jump method to obtain the stay points whose travel distance within the preset time does not exceed the preset value is a conventional technical means and will not be repeated here.

[0026] Preferably, in S1, the process of clustering each resident point group according to adjacent grids is: Connecting the resident points located in adjacent grids to obtain a plurality of resident points connected in sequence; Calculate the distance difference between the dwelling points; The sum of the distance differences between each residence point and other residence points is counted respectively, and the sums are compared. The residence point with the smallest sum is taken as the center point, and the maximum distance difference of the center point is used as the radius to form the residence cluster point area.

[0027] Preferably, in S2, the process of performing regional update on the resident cluster point region comprises the following steps: SA1, take the median value of the distance difference between the center points of the two resident cluster point areas, take the point where the median value is located as the new center point, and determine whether the two resident cluster point areas are overlapping. If so, go to step SA2; if not, go to step SA3; SA2, according to the overlapping relationship and area size between the two resident cluster point areas, select the radius value of a resident cluster point area and add it to the middle value, use it as the current radius value, form a new resident cluster point area based on the new center point with the current radius value, and delete the corresponding two resident cluster point areas; In SA2, the process of selecting a radius value of a resident cluster point area and adding the median value according to the overlap relationship and area size between the two resident cluster point areas is as follows: The overlapping relationship includes intersection and inclusion; When the overlapping relationship between two resident cluster point areas is intersection, the radius value of the resident cluster point area with a smaller area is selected and added to the middle value, and the value is used as the current radius value; When the overlapping relationship between two resident cluster point areas is inclusive, the radius value of the resident cluster point area with a larger area is selected and added to the middle value, which is used as the current radius value; SA3. Based on the new center point, a new resident cluster point area is formed with a preset radius value as the radius, and the corresponding two resident cluster point areas are deleted.

[0028] Specifically, through the above steps S1-S2, when the stationary points filtered out by the current muck truck trajectory data within the preset time are obtained, the stationary points separated by a long time are divided into two stationary point groups A and B according to the time sequence, and the time of the stationary point group A is earlier than that of the stationary point group B. The stationary point group A is composed of a plurality of stationary points sorted in time sequence, represented by A1, A2, A3, A4, A5, A6, and A7; the stationary point B is also composed of a plurality of stationary points sorted in time sequence, represented by B1, B2, B3, B4, B5, B6, and B7, and the two groups of stationary points are matched to the divided grids, and then the stationary points are matched in turn according to the adjacent grids. Point group A and resident point group B are clustered, and the resident points in adjacent grids are connected to obtain a plurality of resident points connected in sequence. If A3-A4-A5-A6-A7 is currently obtained, the distance difference between the resident points is calculated, and the judgment can be made according to the grid area passed by the connecting line between the resident points. The sum of the distance difference between each resident point and other resident points is counted respectively. At this time, the resident point with the smallest sum is A5, and the resident point with the largest distance difference with A5 is A7. A5 is used as the center point, and the distance difference r1 between A5 and A7 is used as the radius to form a resident cluster point area 1. The resident cluster point area 1 is as follows: Figure 2As shown above, by clustering the resident point group B, a resident cluster point area 2 can be obtained with B4 as the center point and the distance difference r2 between B4 and B6 as the radius. The resident cluster point area 2 is as shown in FIG. Figure 3 As shown, the locations of suspected muck truck activity areas can be obtained by clustering the stationary points. At this time, the suspected muck truck activity areas can be analyzed and judged.

[0029] In the present invention, in order to more accurately obtain the area size of the suspected dump truck activity area, the multiple resident cluster point areas formed by the multiple groups of resident points are further processed to determine whether the distance difference between the center points of the resident cluster point areas exceeds the threshold. If the distance difference between the center point of the current resident cluster point area 1 and the center point of the resident cluster point area 2 does not exceed the threshold, the center point of the resident cluster point area 1 and the resident cluster point area 2 need to be updated.

[0030] If the distance difference between the center points of the two current resident cluster point regions exceeds a threshold, there is no need to perform region update on the two current resident cluster point regions.

[0031] The fact that the distance difference between the center point of the resident cluster point area 1 and the center point of the resident cluster point area 2 does not exceed the threshold value may indicate that the two areas where the dump truck has stayed or lingered for many times are relatively close. Correcting the size of the resident cluster point area according to the behavior of the dump truck staying or lingering in different time periods can effectively improve the accuracy of subsequent analysis of the resident cluster point area through the dump truck trajectory data.

[0032] The above-mentioned resident cluster point area 1 and resident cluster point area 2 are updated. If the overlapping relationship between the current resident cluster point area 1 and the resident cluster point area 2 is an intersection, the intersecting resident cluster point area 1 and the resident cluster point area 2 are as follows: Figure 4 As shown, the middle value d / 2 of the distance difference d between the center point of the resident cluster point area 1 and the center point of the resident cluster point area 2 is taken, and the point where the middle value is located is used as the new center point, and the radius value r1 of the resident cluster point area 1 with a smaller area is selected and added to the middle value d / 2, and r1+d / 2 is used as the current radius value. Based on the new center point, a new resident cluster point area 3 is formed with the current radius value, and the center point of the resident cluster point area 1 and the resident cluster point area 2 are deleted. The purpose is to obtain a more accurate suspected dump truck activity area.

[0033] Preferably, the step S4 includes the following steps: S41, connecting the track points of the muck trucks in the resident cluster point area in chronological order, obtaining the average speed values ​​between the track points of the muck trucks in the resident cluster point area in chronological order, and sorting the multiple average speed values ​​in chronological order; In S41, the process of obtaining the average speed values ​​between the track points of the muck truck in the resident cluster point area in sequence according to the time sequence is as follows: The distance difference and time difference between the track points of the muck trucks in the resident cluster point area are calculated in chronological order. The average speed value between the two track points of the muck trucks can be obtained by calculating the distance difference and time difference. S42, judging in chronological order whether the change values ​​between the average speed values ​​are continuously less than the minimum value, if so, screening is performed based on the change values ​​that are continuously less than the minimum value, screening the average speed value at the center position as the segmentation point, and going to step S43; S43, splitting the multiple average speed values ​​into two segments according to the segmentation points, and performing linear fitting on the average speed values ​​of the two segments to obtain a corresponding average speed trend curve; S44, determining the scene type of the resident cluster point area according to the slope of the average speed trend curves of the previous and next two sections; In S44, the process of determining the scene type of the resident cluster point area according to the slope of the average speed trend curves of the previous and next two sections is as follows: If the slope of the average speed trend curve in the front section is greater than the slope of the average speed trend curve in the rear section, the scene type of the resident cluster point area is determined to be a dumping site; if the slope of the average speed trend curve in the front section is less than the slope of the average speed trend curve in the rear section, the scene type of the resident cluster point area is determined to be a construction site.

[0034] Specifically, after obtaining the suspected dump truck activity area, the scene type of the dump truck activity area can be judged according to the speed changes between the dump truck trajectory points in the dump truck trajectory data, and the suspected dump truck activity area refers to the newly generated resident cluster point area after the area update or the resident cluster point area that has not been updated. At this time, the suspected dump truck activity area refers to the resident cluster point area 3.

[0035] After obtaining the resident cluster point area, a section of dump truck trajectory data corresponding to a resident point group can be optionally or separately matched to the resident cluster point area, and the dump truck trajectory points in the dump truck trajectory data are screened to obtain multiple dump truck trajectory points located in the resident cluster point area, and the multiple dump truck trajectory points are connected in chronological order. Since the dump truck trajectory points are uploaded by the GPS device carried by the dump truck itself, the dump truck trajectory points have time information and coordinate information. The time difference between two dump truck trajectory points can be calculated based on the time information of the dump truck trajectory points, and the distance difference between the two dump truck trajectory points can be calculated based on the coordinate information of the dump truck trajectory points. The distance difference can be calculated using the Haversine formula, and the average speed value between the two dump truck trajectory points can be obtained based on the distance difference and time difference between the two dump truck trajectory points.

[0036] Since the time interval between two GPS data of a muck truck is generally less than 30 seconds, that is, the time difference between two muck truck track points is generally less than 30 seconds, the time interval between two muck truck track points is short, and the current average speed value can be regarded as the instantaneous speed at a time point. The driving behavior of the muck truck in the trajectory data can be analyzed according to the change value of the average speed, and combined with the behavioral characteristics of the muck truck performing different activities in the muck truck activity areas of different scene types, the scene type of the current resident cluster point area can be judged.

[0037] In this embodiment, the scene type judgment of the current resident cluster point area is mainly to judge whether the current resident cluster point area is a dumping site or a construction site. The dumping site and the construction site are the two most common activity areas of the dump truck. In these two activity areas, the dump truck needs to take certain measures, such as loading and unloading. This behavior needs to be supervised, so that the inspectors need to patrol these two activity areas.

[0038] For the construction site, when the dump truck enters the construction site, its front end speed is faster because it is generally empty; when the dump truck is within the construction site, it maintains a low driving speed according to the needs of the construction site or stops due to loading earth and stone, resulting in a low or zero middle speed; when the dump truck leaves the construction site, it is generally fully loaded with earth and stone, resulting in a slower rear end speed compared to the front end speed.

[0039] For the dumping site, when the dump truck enters the dumping site, its front-end speed is slow because it is generally fully loaded; when the dump truck is inside the dumping site, it will maintain a low driving speed or stop for dumping according to the demand in the dumping site, resulting in a low or zero middle speed; when the dump truck leaves the dumping site, it is generally empty, resulting in a faster rear-end speed than the front-end speed.

[0040] In combination with the above situation, the present invention chooses to split the average speed value into two sections, front and back, based on the lowest change value of the average speed value, and linearly fits the average speed values ​​of the front and back sections respectively to obtain the corresponding average speed trend curve. If the slope of the average speed trend curve of the front section is greater than the slope of the average speed trend curve of the rear section, the scene type of the resident clustering point area is determined to be a dumping site; if the slope of the average speed trend curve of the front section is less than the slope of the average speed trend curve of the rear section, the scene type of the resident clustering point area is determined to be a construction site. The scene type of the current resident clustering point area can be accurately analyzed. In actual situations, the current resident clustering point area is compared with the registered construction site or dumping site, so that whether there are new construction sites or dumping sites and other muck truck activity areas in the current area can be detected, so as to realize the role of supervising the muck truck activity area through the muck truck trajectory data, and there is no need to count the muck truck activity area through manual inspection, which can effectively improve the efficiency of counting the muck truck activity area and reduce labor costs.

[0041] Example 2 A system for analyzing the activity area of ​​a muck truck based on trajectory data, using a method for analyzing the activity area of ​​a muck truck based on trajectory data, comprising: The module for dividing the resident clustering points area is used to obtain multiple resident point groups filtered out by the trajectory data of the muck truck, and the resident points in the resident point group are matched to the divided grids. Each resident point group is clustered according to the adjacent grids to obtain the resident clustering point area with the resident point as the center point. Resident cluster point area update module: determines whether the distance difference between the center points of the resident cluster point areas exceeds a threshold, if not, updates the resident cluster point areas; Muck truck trajectory data matching module: matches the muck truck trajectory data corresponding to the resident point group to the resident cluster point area, and filters the muck truck trajectory points in the current muck truck trajectory data to obtain the muck truck trajectory points located in the resident cluster point area; Resident cluster point area determination module: perform average speed segmented curve fitting on the trajectory points of the muck truck in the resident cluster point area to obtain the corresponding average speed trend curve, and determine the scene type of the resident cluster point area according to the curve characteristics of the average speed trend curve.

[0042] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. According to the technical essence of the present invention, within the spirit and principles of the present invention, any simple modification, equivalent replacement and improvement made to the above embodiment still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for analyzing the activity area of ​​a muck truck based on trajectory data, characterized in that: The method for analyzing the activity area of ​​a muck truck comprises the following steps: S1, obtaining multiple resident point groups screened out through the trajectory data of the muck truck, and matching the resident points in the resident point group to the divided grids, clustering each resident point group according to the adjacent grids, and obtaining a resident cluster point area with the resident point as the center point; S2, judging whether the distance difference between the center points of the resident cluster point areas exceeds a threshold value, if not, performing regional update on the resident cluster point areas, and going to step S3; S3, matching the track data of the muck truck corresponding to the resident point group to the resident cluster point area, and screening the track points of the muck truck in the current track data of the muck truck to obtain the track points of the muck truck located in the resident cluster point area; S4. Perform average speed segmented curve fitting on the trajectory points of the muck truck in the resident cluster point area to obtain a corresponding average speed trend curve, and determine the scene type of the resident cluster point area according to the curve characteristics of the average speed trend curve.

2. The method for analyzing the activity area of ​​a muck truck based on trajectory data according to claim 1 is characterized in that: In S1, the plurality of stay point groups selected by the trajectory data of the muck truck refers to grouping the stay points whose travel distance does not exceed a preset value within a preset time selected by the matrix method and the adaptive jump method according to time; Inactive track points of the muck truck are removed from the track data of the muck truck by using the matrix method; The adaptive jumping method is used to identify whether the muck truck trajectory point surrounded by multiple muck truck trajectory points in the muck truck trajectory data is a stationary point. If so, the stationary point is matched to the divided grid.

3. The method for analyzing the activity area of ​​a muck truck based on trajectory data according to claim 1 is characterized in that: In S1, the process of clustering each resident point group according to the adjacent grids is: Connecting the resident points located in adjacent grids to obtain a plurality of resident points connected in sequence; Calculate the distance difference between the dwelling points; The sum of the distance differences between each residence point and other residence points is counted respectively, and the sums are compared. The residence point with the smallest sum is taken as the center point, and the maximum distance difference of the center point is used as the radius to form the residence cluster point area.

4. The method for analyzing the activity area of ​​a muck truck based on trajectory data according to claim 3 is characterized in that: In S2, the process of updating the region of the resident cluster point region includes the following steps: SA1, take the median value of the distance difference between the center points of the two resident cluster point areas, take the point where the median value is located as the new center point, and determine whether the two resident cluster point areas are overlapping. If so, go to step SA2; if not, go to step SA3; SA2, according to the overlapping relationship and area size between the two resident cluster point areas, select the radius value of a resident cluster point area and add it to the middle value, use it as the current radius value, form a new resident cluster point area based on the new center point with the current radius value, and delete the corresponding two resident cluster point areas; SA3. Based on the new center point, a new resident cluster point area is formed with a preset radius value as the radius, and the corresponding two resident cluster point areas are deleted.

5. The method for analyzing the activity area of ​​a muck truck based on trajectory data according to claim 4 is characterized in that: In SA2, the process of selecting a radius value of a resident cluster point area and adding the median value according to the overlap relationship and area size between the two resident cluster point areas is as follows: The overlapping relationship includes intersection and inclusion; When the overlapping relationship between two resident cluster point areas is intersection, the radius value of the resident cluster point area with a smaller area is selected and added to the middle value, and the value is used as the current radius value; When the overlapping relationship between two resident cluster point areas is inclusive, the radius value of the resident cluster point area with a larger area is selected and added to the middle value, which is used as the current radius value.

6. The method for analyzing the activity area of ​​a muck truck based on trajectory data according to claim 1 is characterized in that: The step S4 includes the following steps: S41, connecting the track points of the muck trucks in the resident cluster point area in chronological order, obtaining the average speed values ​​between the track points of the muck trucks in the resident cluster point area in chronological order, and sorting the multiple average speed values ​​in chronological order; S42, judging in chronological order whether the change values ​​between the average speed values ​​are continuously less than the minimum value, if so, screening is performed based on the change values ​​that are continuously less than the minimum value, screening the average speed value at the center position as the segmentation point, and going to step S43; S43, splitting the multiple average speed values ​​into two segments according to the segmentation points, and performing linear fitting on the average speed values ​​of the two segments to obtain a corresponding average speed trend curve; S44: Determine the scene type of the resident cluster point area according to the slope of the average speed trend curves of the previous and next two sections.

7. The method for analyzing the activity area of ​​a muck truck based on trajectory data according to claim 6 is characterized in that: In S41, the process of obtaining the average speed values ​​between the track points of the muck truck in the resident cluster point area in sequence according to the time sequence is as follows: The distance difference and time difference between the track points of the muck trucks in the resident cluster point area are calculated in chronological order, and the average speed value between the two track points of the muck trucks is obtained by calculating the distance difference and the time difference.

8. The method for analyzing the activity area of ​​a muck truck based on trajectory data according to claim 6 is characterized in that: In S44, the process of determining the scene type of the resident cluster point area according to the slope of the average speed trend curves of the previous and next two sections is as follows: If the slope of the average speed trend curve in the front section is greater than the slope of the average speed trend curve in the rear section, the scene type of the resident cluster point area is determined to be a dumping site; if the slope of the average speed trend curve in the front section is less than the slope of the average speed trend curve in the rear section, the scene type of the resident cluster point area is determined to be a construction site.

9. A system for analyzing the activity area of ​​a muck truck based on trajectory data, characterized in that: A method for analyzing the activity area of ​​a muck truck based on trajectory data as described in any one of claims 1 to 8 is applied, comprising: The module for dividing the resident clustering points area is used to obtain multiple resident point groups filtered out by the trajectory data of the muck truck, and the resident points in the resident point group are matched to the divided grids. Each resident point group is clustered according to the adjacent grids to obtain the resident clustering point area with the resident point as the center point. Resident cluster point area update module: determines whether the distance difference between the center points of the resident cluster point areas exceeds a threshold, if not, updates the resident cluster point areas; Muck truck trajectory data matching module: matches the muck truck trajectory data corresponding to the resident point group to the resident cluster point area, and filters the muck truck trajectory points in the current muck truck trajectory data to obtain the muck truck trajectory points located in the resident cluster point area; Resident cluster point area determination module: perform average speed segmented curve fitting on the trajectory points of the muck truck in the resident cluster point area to obtain the corresponding average speed trend curve, and determine the scene type of the resident cluster point area according to the curve characteristics of the average speed trend curve.

Images