一种基于深度学习的渐进折返跑越线检测方法及系统
By using a deep learning-based video processing method, the system detects the position of the tester's toes and the position of their line, solving the problems of poor portability, low accuracy, and low efficiency of existing line crossing detection systems, and achieving more efficient line crossing detection.
CN117726649BActive Publication Date: 2026-07-17CHINA UNIV OF PETROLEUM (EAST CHINA)
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA UNIV OF PETROLEUM (EAST CHINA)
- Filing Date
- 2023-11-03
- Publication Date
- 2026-07-17
Smart Images
Figure CN117726649B_ABST
Abstract
一种基于深度学习的渐进折返跑越线检测方法及系统，它属于视频图像处理领域。本发明解决了现有越线检测系统存在的便携性差、检测准确性差以及检测效率低的问题。本发明对采集的测试人员视频进行处理得到图像序列，再分别提取出每帧图像中的左脚脚尖坐标及右脚脚尖坐标，进而得到左脚脚尖坐标及右脚脚尖坐标随时间的运动轨迹。对图像序列的第一帧图像中的直线进行检测得到每帧图像中的起点直线位置和终点直线位置；根据左脚脚尖坐标、右脚脚尖坐标随时间的运动轨迹及起点直线位置和终点直线位置进行越线检测。本发明方法可以应用于渐进折返跑过程中的越线检测。
Need to check novelty before this filing date? Find Prior Art