Traffic Video Object Detection using Motion Prior

TL;DR

This paper introduces novel methods leveraging motion priors in traffic videos to significantly improve object detection accuracy, outperforming existing approaches in both fully-supervised and semi-supervised settings.

Contribution

It proposes two innovative techniques that utilize motion priors to enhance traffic video object detection, including a self-attention module and a pseudo-labeling mechanism.

Findings

Outperforms state-of-the-art methods by 2% mAP

Effective in both fully-supervised and semi-supervised scenarios

Demonstrates the value of motion priors in traffic video detection

Abstract

Traffic videos inherently differ from generic videos in their stationary camera setup, thus providing a strong motion prior where objects often move in a specific direction over a short time interval. Existing works predominantly employ generic video object detection framework for traffic video object detection, which yield certain advantages such as broad applicability and robustness to diverse scenarios. However, they fail to harness the strength of motion prior to enhance detection accuracy. In this work, we propose two innovative methods to exploit the motion prior and boost the performance of both fully-supervised and semi-supervised traffic video object detection. Firstly, we introduce a new self-attention module that leverages the motion prior to guide temporal information integration in the fully-supervised setting. Secondly, we utilise the motion prior to develop a pseudo-labelling mechanism to eliminate noisy pseudo labels for the semi-supervised setting. Both of our motion-prior-centred methods consistently demonstrates superior performance, outperforming existing state-of-the-art approaches by a margin of 2% in terms of mAP.