arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.01258cs.CVeess.IV
收藏

基于运动相似图谱分析的在线行人群体步行事件检测

Online Pedestrian Group Walking Event Detection Using Spectral Analysis of Motion Similarity Graph

University of Genoa(热那亚大学)

Vahid Bastani, Damian Campo, Lucio Marcenaro, Carlo S. Regazzoni

摘要:

提出了一种视频中运动目标群的在线识别方法。该方法利用运动相似性图的谱聚类,在每一帧中识别出具有相似局部瞬时运动模式的被跟踪对象组。然后,根据PETS 2015挑战的要求,使用算法的输出来检测两个以上物体一起移动的事件。在PETS 2015数据集上评估了算法的性能。

英文摘要:

A method for online identification of group of moving objects in the video is proposed in this paper. This method at each frame identifies group of tracked objects with similar local instantaneous motion pattern using spectral clustering on motion similarity graph. Then, the output of the algorithm is used to detect the event of more than two object moving together as required by PETS2015 challenge. The performance of the algorithm is evaluated on the PETS2015 dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑