Multi-Object Tracking in the Dark

TL;DR

This paper introduces a new low-light multi-object tracking dataset and a robust tracking method, LTrack, designed to improve performance in dark scenes by enhancing image features and learning invariant representations.

Contribution

The paper presents the first low-light multi-object tracking dataset, LMOT, and proposes LTrack, a novel method with adaptive filtering and degradation suppression for dark scene tracking.

Findings

LTrack outperforms existing methods in low-light conditions.

LMOT dataset provides high-quality annotations for dark scene tracking.

LTrack demonstrates robustness and competitiveness in real night scenes.

Abstract

Low-light scenes are prevalent in real-world applications (e.g. autonomous driving and surveillance at night). Recently, multi-object tracking in various practical use cases have received much attention, but multi-object tracking in dark scenes is rarely considered. In this paper, we focus on multi-object tracking in dark scenes. To address the lack of datasets, we first build a Low-light Multi-Object Tracking (LMOT) dataset. LMOT provides well-aligned low-light video pairs captured by our dual-camera system, and high-quality multi-object tracking annotations for all videos. Then, we propose a low-light multi-object tracking method, termed as LTrack. We introduce the adaptive low-pass downsample module to enhance low-frequency components of images outside the sensor noises. The degradation suppression learning strategy enables the model to learn invariant information under noise disturbance and image quality degradation. These components improve the robustness of multi-object tracking in dark scenes. We conducted a comprehensive analysis of our LMOT dataset and proposed LTrack. Experimental results demonstrate the superiority of the proposed method and its competitiveness in real night low-light scenes. Dataset and Code: https: //github.com/ying-fu/LMOT