行驶轨迹的处理方法、装置、车辆及存储介质
By grouping and calculating the similarity between the starting and ending points of the driving trajectory, and utilizing grayscale processing and grid partitioning techniques, the problem of excessive computational resource consumption during driving trajectory recognition is solved, achieving efficient trajectory merging and recognition.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA FAW CO LTD
- Filing Date
- 2023-08-23
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, the complex spatial variations of driving trajectories lead to excessive computational resource consumption during the driving trajectory recognition process, which existing methods such as dynamic time warping and similarity coefficient methods cannot effectively solve.
By obtaining the starting point and ending point of the target driving trajectory, the trajectory is grouped and clustered to form driving trajectory groups. The similarity of the trajectories in each group is calculated and merged. Gray-scale processing and grid partitioning techniques are used to compare the trajectory similarity.
It effectively reduces the consumption of computing resources, achieves efficient identification and merging of driving trajectories, and reduces computational complexity.
Smart Images
Figure CN117113099B_ABST