TGCN: Time Domain Graph Convolutional Network for Multiple Objects Tracking

TL;DR

This paper introduces TGCN, a novel approach combining CNN and GCN to model temporal relationships in features for improved multiple object tracking, achieving better accuracy and high frame rate performance.

Contribution

The paper proposes a time domain graph convolutional network that models past frame features to enhance current object tracking accuracy.

Findings

Improved MOTA score by 1.3 on MOT16 dataset.

Achieved competitive performance at high frame rates.

Effectively models temporal relationships between frames.

Abstract

Multiple object tracking is to give each object an id in the video. The difficulty is how to match the predicted objects and detected objects in same frames. Matching features include appearance features, location features, etc. These features of the predicted object are basically based on some previous frames. However, few papers describe the relationship in the time domain between the previous frame features and the current frame features.In this paper, we proposed a time domain graph convolutional network for multiple objects tracking.The model is mainly divided into two parts, we first use convolutional neural network (CNN) to extract pedestrian appearance feature, which is a normal operation processing image in deep learning, then we use GCN to model some past frames' appearance feature to get the prediction appearance feature of the current frame. Due to this extension, we can get the pose features of the current frame according to the relationship between some frames in the past. Experimental evaluation shows that our extensions improve the MOTA by 1.3 on the MOT16, achieving overall competitive performance at high frame rates.