Video Individual Counting With Implicit One-to-Many Matching

TL;DR

This paper introduces OMAN, a novel VIC model that employs implicit one-to-many matching to better identify pedestrians across video frames, leveraging social behaviors for improved counting accuracy.

Contribution

The paper proposes a new VIC approach using implicit one-to-many matching, addressing limitations of previous one-to-one strategies and achieving state-of-the-art results.

Findings

OMAN outperforms existing VIC methods on benchmarks.

Implicit one-to-many matching improves pedestrian correspondence accuracy.

The model effectively leverages social grouping behavior.

Abstract

Video Individual Counting (VIC) is a recently introduced task that aims to estimate pedestrian flux from a video. It extends conventional Video Crowd Counting (VCC) beyond the per-frame pedestrian count. In contrast to VCC that only learns to count repeated pedestrian patterns across frames, the key problem of VIC is how to identify co-existent pedestrians between frames, which turns out to be a correspondence problem. Existing VIC approaches, however, mainly follow a one-to-one (O2O) matching strategy where the same pedestrian must be exactly matched between frames, leading to sensitivity to appearance variations or missing detections. In this work, we show that the O2O matching could be relaxed to a one-to-many (O2M) matching problem, which better fits the problem nature of VIC and can leverage the social grouping behavior of walking pedestrians. We therefore introduce OMAN, a simple but effective VIC model with implicit One-to-Many mAtchiNg, featuring an implicit context generator and a one-to-many pairwise matcher. Experiments on the SenseCrowd and CroHD benchmarks show that OMAN achieves the state-of-the-art performance. Code is available at \href{https://github.com/tiny-smart/OMAN}{OMAN}.