Real-time Online Multi-Object Tracking in Compressed Domain

TL;DR

This paper introduces a real-time online multi-object tracking method that operates in the compressed domain, significantly increasing speed while maintaining comparable accuracy by dividing frames into key and non-key categories and using specialized CNNs.

Contribution

The paper proposes a novel framework that tracks objects efficiently in compressed video, combining detection on key frames with motion-based propagation on non-key frames, achieving a 6x speedup.

Findings

About 6 times faster than state-of-the-art methods

Maintains comparable tracking accuracy

Effective in real-time online multi-object tracking

Abstract

Recent online Multi-Object Tracking (MOT) methods have achieved desirable tracking performance. However, the tracking speed of most existing methods is rather slow. Inspired from the fact that the adjacent frames are highly relevant and redundant, we divide the frames into key and non-key frames respectively and track objects in the compressed domain. For the key frames, the RGB images are restored for detection and data association. To make data association more reliable, an appearance Convolutional Neural Network (CNN) which can be jointly trained with the detector is proposed. For the non-key frames, the objects are directly propagated by a tracking CNN based on the motion information provided in the compressed domain. Compared with the state-of-the-art online MOT methods,our tracker is about 6x faster while maintaining a comparable tracking performance.