2021/01/21 by Jinhai Yang, Hua Yang, Yang, Jinhai +1
Computer Science · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Digital Media Forensic Detection #FOS: Computer and information sciences #Machine Learning (cs.LG) #Video Surveillance and Tracking Methods #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2101.08609
ICIP 2021 Camera Ready
openalex publication_date 2021/01/21 · openalex created_date 2021/02/01 · arxiv created 2021/06/02 · arxiv updated 2021/06/03 · openalex updated_date 2026/08/01
Crowd segmentation is a fundamental task serving as the basis of crowded scene analysis, and it is highly desirable to obtain refined pixel-level segmentation maps. However, it remains a challenging problem, as existing approaches either require dense pixel-level annotations to train deep learning models or merely produce rough segmentation maps from optical or particle flows with physical models. In this paper, we propose the Motion Prior-Aware Siamese Network (MPASNET) for unsupervised crowd semantic segmentation. This model not only eliminates the need for annotation but also yields high-quality segmentation maps. Specially, we first analyze the coherent motion patterns across the frames and then apply a circular region merging strategy on the collective particles to generate pseudo-labels. Moreover, we equip MPASNET with siamese branches for augmentation-invariant regularization and siamese feature aggregation. Experiments over benchmark datasets indicate that our model outperforms the state-of-the-arts by more than 12% in terms of mIoU.