Spatio-temporal crowd density model in a human detection and tracking framework

作者：

Highlights：

• We model time-varying dynamics of the crowd density using feature tracks.

• We incorporate the crowd measure into the state-of-the-art detector.

• We extend the improved detections to tracking in a tracking-by-detection framework.

• We obtain better results compared to the baseline methods of detection and tracking.

摘要

Highlights•We model time-varying dynamics of the crowd density using feature tracks.•We incorporate the crowd measure into the state-of-the-art detector.•We extend the improved detections to tracking in a tracking-by-detection framework.•We obtain better results compared to the baseline methods of detection and tracking.

论文关键词：Crowd density,Local features,Human detection,Tracking,Crowded scenes

论文评审过程：Received 7 March 2014, Revised 25 October 2014, Accepted 21 November 2014, Available online 15 December 2014.

论文官网地址：https://doi.org/10.1016/j.image.2014.11.006