MPASNET: Motion Prior-Aware Siamese Network for Unsupervised Deep Crowd Segmentation in Video Scenes

TL;DR

MPASNET is an unsupervised deep learning model that leverages motion priors and siamese networks to produce high-quality crowd segmentation maps without requiring pixel-level annotations, outperforming existing methods.

Contribution

The paper introduces MPASNET, a novel unsupervised crowd segmentation model that uses motion priors and siamese networks to improve segmentation quality without annotations.

Findings

Outperforms state-of-the-art by over 12% mIoU.

Effectively generates high-quality segmentation maps without annotations.

Utilizes motion patterns and siamese regularization for improved accuracy.

Abstract

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.