SOT for MOT

TL;DR

This paper introduces a robust multiple object tracking method that combines single object tracking with deep learning-based appearance models, significantly improving detection association and reducing false negatives in complex scenes.

Contribution

It innovatively integrates SOT algorithms with MOT, and employs a deep learning appearance model for efficient, accurate data association across diverse scenes.

Findings

Achieved state-of-the-art performance on MOT16 benchmark.

Effectively reduces false negatives regardless of detection quality.

Demonstrated robustness across various challenging scenes.

Abstract

In this paper we present a robust tracker to solve the multiple object tracking (MOT) problem, under the framework of tracking-by-detection. As the first contribution, we innovatively combine single object tracking (SOT) algorithms with multiple object tracking algorithms, and our results show that SOT is a general way to strongly reduce the number of false negatives, regardless of the quality of detection. Another contribution is that we show with a deep learning based appearance model, it is easy to associate detections of the same object efficiently and also with high accuracy. This appearance model plays an important role in our MOT algorithm to correctly associate detections into long trajectories, and also in our SOT algorithm to discover new detections mistakenly missed by the detector. The deep neural network based model ensures the robustness of our tracking algorithm, which can perform data association in a wide variety of scenes. We ran comprehensive experiments on a large-scale and challenging dataset, the MOT16 benchmark, and results showed that our tracker achieved state-of-the-art performance based on both public and private detections.