Globally Optimal Object Tracking with Fully Convolutional Networks

TL;DR

This paper introduces a robust object tracking method combining Fully Convolutional Networks for appearance modeling and Dynamic Programming for global optimality, effectively handling appearance changes and occlusions in videos.

Contribution

The paper presents a novel tracking approach that integrates FCNs and DP to improve robustness against appearance variation and occlusion.

Findings

Effective tracking of various objects in video sequences.

Handles appearance variation with FCN.

Manages occlusion through global optimization.

Abstract

Tracking is one of the most important but still difficult tasks in computer vision and pattern recognition. The main difficulties in the tracking field are appearance variation and occlusion. Most traditional tracking methods set the parameters or templates to track target objects in advance and should be modified accordingly. Thus, we propose a new and robust tracking method using a Fully Convolutional Network (FCN) to obtain an object probability map and Dynamic Programming (DP) to seek the globally optimal path through all frames of video. Our proposed method solves the object appearance variation problem with the use of a FCN and deals with occlusion by DP. We show that our method is effective in tracking various single objects through video frames.