Trajectory data processing method and device, and storage medium

Patent metadata

Field	Value
Publication number	US-12229968-B2
Application number	US-202117394389-A
Country	US
Kind code	B2
Filing date	Aug 4, 2021
Priority date	Jul 29, 2019
Publication date	Feb 18, 2025
Grant date	Feb 18, 2025

Abstract

A trajectory data processing method is provided to a trajectory data apparatus. The method includes: obtaining trajectory data in a target geographical range, the trajectory data including moving trajectories of a plurality of moving objects, generating a feature map layer of the trajectory data, the feature map layer at least including a trajectory flow map layer, a moving speed map layer, and a travel direction map layer, fusing map layers in the feature map layer to obtain a fused feature map layer; displaying the fused feature map layer; and in response to obtaining a selection instruction of any pixel position on the fused feature map layer, displaying a trajectory flow at the pixel position and a moving speed and a travel direction of a moving object at the pixel position.

First claim

What is claimed is:

1. A trajectory data processing method, applied to a trajectory data processing device, and the method comprising:
obtaining trajectory data in a target geographical range, the trajectory data including moving trajectories of a plurality of moving objects;
respectively scaling a plurality of grid regions into a trajectory image with a uniform size, wherein the grid regions are obtained by spatially splitting the target geographical range, and the moving trajectories are respectively divided according to the grid regions to which the moving trajectories belong;
for a grid region of the plurality of grid regions, obtaining pixel positions of sampling points on each moving trajectory in the trajectory image corresponding to the grid region;
generating a feature map layer of the trajectory data, the feature map layer at least including a trajectory flow map layer, a moving speed map layer, and a travel direction map layer;
fusing map layers in the feature map layer to obtain a fused feature map layer;
displaying the fused feature map layer; and
in response to obtaining a selection instruction of any pixel position on the fused feature map layer, displaying a trajectory flow at the pixel position and a moving speed and a travel direction of a moving object at the pixel position,
wherein generating the feature map layer comprises:
for a target pixel position in a trajectory image, based on the pixel positions of the sampling points on each moving trajectory included in a corresponding grid region in the trajectory image, detecting whether each of the moving trajectories is intersected with the target pixel position; and
in response to determining one of the moving trajectories being intersected with the target pixel position, determining at least one of a trajectory flow at the target pixel position, a moving speed of a target moving object at the target pixel position, or a vector direction of the target pixel position;
wherein the trajectory flow map layer comprises the trajectory flow of the target pixel position in the trajectory image, the moving speed map layer comprises the moving speed of the target moving object at the target pixel position in the trajectory image, and the travel direction map layer comprises the vector direction of the target pixel position in the trajectory image, the vector direction representing the travel direction of the target moving object.

2. The method according to claim 1 , wherein displaying the trajectory flow comprises:
superimposing and displaying a feature display map layer on the fused feature map layer; and
displaying, on the feature display map layer, the trajectory flow at the pixel position and the moving speed and the travel direction of the moving object at the pixel position.

3. The method according to claim 1 , wherein obtaining pixel positions of sampling points on each moving trajectory in the trajectory image corresponding to the grid region comprises:
performing coordinate system conversion on each moving trajectory comprised in the grid region, to obtain a pixel position of each sampling point on each moving trajectory in a corresponding trajectory image.

4. The method according to claim 1 , wherein performing the coordinate system conversion comprises:
obtaining longitude and latitude coordinates of a region boundary of the grid region;
obtaining a height value and a width value of a corresponding trajectory image;
for any sampling point, obtaining a horizontal axis coordinate of the sampling point in the corresponding trajectory image according to longitude and latitude coordinates of left and right boundaries of the grid region, the width value, and a longitude coordinate of the sampling point; and
obtaining a longitudinal axis coordinate of the sampling point in the corresponding trajectory image according to longitude and latitude coordinates of upper and lower boundaries of the grid region, the height value, and a latitude coordinate of the sampling point.

5. The method according to claim 1 , wherein generating the feature map layer of the trajectory data comprises:
in response to determining one of the moving trajectories is intersected with the target pixel position, adding one to a trajectory flow at the target pixel position.

6. The method according to claim 1 , wherein generating the feature map layer of the trajectory data comprises:
in response to determining one of the moving trajectories is intersected with the target pixel position, accumulating the moving speeds of the sampling points having the pixel position on the moving trajectory;
obtaining an average moving speed based on a total number of the accumulated sampling points and a sum of the accumulated moving speeds; and
in response to the average moving speed being smaller than a speed threshold, using the average moving speed as a moving speed of a moving object at the target pixel position.

7. The method according to claim 1 , wherein generating the feature map layer of the trajectory data comprises:
in response to determining one of the moving trajectories is intersected with the target pixel position, accumulating vector directions of the sampling points having the pixel position on the moving trajectory.

8. The method according to claim 1 , wherein fusing the map layers in the feature map layer to obtain the fused feature map layer comprises:
performing flow feature processing on the trajectory flow map layer, to obtain a first feature map layer;
projecting the moving speed of the moving speed map layer in a directional space based on the travel direction map layer, to obtain a second feature map layer; and
splicing and combining the first feature map layer and the second feature map layer to obtain the fused feature map layer;
wherein the first feature map layer and the second feature map layer have the same value space.

9. The method according to claim 8 , wherein performing the flow feature processing on the trajectory flow map layer comprises:
obtaining a flow value upper limit, a first smoothing factor, and a second smoothing factor;
obtaining a maximum trajectory flow in the trajectory flow map layer; and
for any pixel position in the trajectory flow map layer, obtaining the trajectory flow of the pixel position again based on the trajectory flow of the pixel position, the first smoothing factor, the second smoothing factor, the maximum trajectory flow, and the flow value upper limit.

10. The method according to claim 8 , wherein projecting the moving speed of the moving speed map layer comprises:
for any pixel position, obtaining, in the moving speed map layer, the moving speed of the moving object at the pixel position;
obtaining a vector direction of the moving object at the pixel position in the travel direction map layer; and
using a product of the moving speed and a sine value of the vector direction as a moving speed of the pixel position in a longitudinal axis direction; and using a product of the moving speed and a cosine value of the vector direction as a moving speed of the pixel position in a horizontal axis direction.

11. The method according to claim 1 , wherein displaying the trajectory flow comprises:
displaying a historical trajectory flow at a geographical position corresponding to the pixel position and a historical average moving speed and a historical travel direction of the moving object at the geographical position corresponding to the pixel position.

12. The method according to claim 1 , further comprising:
after obtaining the trajectory data, pre-processing the trajectory data;
wherein the pre-processing comprises one or more of:
filtering, according

Assignees

• Tencent Tech Shenzhen Co Ltd

Inventors

• Dong Hao
• Gao Shufeng

Classifications

• G06T2207/30241

  Trajectory · CPC title

• G06T2207/20221

  Image fusion; Image merging · CPC title

• G06T11/60

  Creating or editing images; Combining images with text · CPC title

• G06T17/05

  Geographic models · CPC title

• G01C21/3878

  Hierarchical structures, e.g. layering · CPC title