Depth Perspective-aware Multiple Object Tracking

TL;DR

This paper introduces a real-time depth perspective-aware approach for multiple object tracking that effectively addresses occlusions by estimating depth order, extending Kalman filtering, and enhancing data association.

Contribution

It proposes a novel unsupervised depth estimation method and an extended Kalman filter with high-order data association for improved MOT performance.

Findings

Achieves state-of-the-art results on standard benchmarks.

Effectively handles occlusions in real-time.

Improves object tracking accuracy with depth-aware techniques.

Abstract

This paper aims to tackle Multiple Object Tracking (MOT), an important problem in computer vision but remains challenging due to many practical issues, especially occlusions. Indeed, we propose a new real-time Depth Perspective-aware Multiple Object Tracking (DP-MOT) approach to tackle the occlusion problem in MOT. A simple yet efficient Subject-Ordered Depth Estimation (SODE) is first proposed to automatically order the depth positions of detected subjects in a 2D scene in an unsupervised manner. Using the output from SODE, a new Active pseudo-3D Kalman filter, a simple but effective extension of Kalman filter with dynamic control variables, is then proposed to dynamically update the movement of objects. In addition, a new high-order association approach is presented in the data association step to incorporate first-order and second-order relationships between the detected objects. The proposed approach consistently achieves state-of-the-art performance compared to recent MOT methods on standard MOT benchmarks.