Tracklets Predicting Based Adaptive Graph Tracking

TL;DR

This paper introduces TPAGT, an end-to-end multi-object tracking framework that re-extracts features based on motion prediction and uses an adaptive graph neural network to fuse appearance, location, and historical data, achieving state-of-the-art results.

Contribution

The paper presents a novel framework combining motion-based feature re-extraction and adaptive graph neural networks for improved multi-object tracking.

Findings

Achieves 76.5% MOTA on MOT16

Outperforms previous methods on MOT17

Introduces balanced MSE loss for training stability

Abstract

Most of the existing tracking methods link the detected boxes to the tracklets using a linear combination of feature cosine distances and box overlap. But the problem of inconsistent features of an object in two different frames still exists. In addition, when extracting features, only appearance information is utilized, neither the location relationship nor the information of the tracklets is considered. We present an accurate and end-to-end learning framework for multi-object tracking, namely \textbf{TPAGT}. It re-extracts the features of the tracklets in the current frame based on motion predicting, which is the key to solve the problem of features inconsistent. The adaptive graph neural network in TPAGT is adopted to fuse locations, appearance, and historical information, and plays an important role in distinguishing different objects. In the training phase, we propose the balanced MSE LOSS to successfully overcome the unbalanced samples. Experiments show that our method reaches state-of-the-art performance. It achieves 76.5\% MOTA on the MOT16 challenge and 76.2\% MOTA on the MOT17 challenge.