Multi-View People Detection in Large Scenes via Supervised View-Wise Contribution Weighting

TL;DR

This paper introduces a supervised view-wise contribution weighting method for multi-view people detection in large scenes, utilizing synthetic data and domain adaptation to improve cross-scene performance in complex environments.

Contribution

The paper proposes a novel view-wise contribution weighting approach and uses a synthetic dataset with domain adaptation to enhance multi-view people detection in large, complex scenes.

Findings

Improved detection accuracy in large scenes with occlusions.

Effective generalization across different scenes.

Enhanced robustness with domain adaptation.

Abstract

Recent deep learning-based multi-view people detection (MVD) methods have shown promising results on existing datasets. However, current methods are mainly trained and evaluated on small, single scenes with a limited number of multi-view frames and fixed camera views. As a result, these methods may not be practical for detecting people in larger, more complex scenes with severe occlusions and camera calibration errors. This paper focuses on improving multi-view people detection by developing a supervised view-wise contribution weighting approach that better fuses multi-camera information under large scenes. Besides, a large synthetic dataset is adopted to enhance the model's generalization ability and enable more practical evaluation and comparison. The model's performance on new testing scenes is further improved with a simple domain adaptation technique. Experimental results demonstrate the effectiveness of our approach in achieving promising cross-scene multi-view people detection performance. See code here: https://vcc.tech/research/2024/MVD.