Concurrent Tracking of Inliers and Outliers

TL;DR

This paper introduces a novel object tracking algorithm that concurrently tracks inliers and outliers, leveraging both for robust motion estimation, resulting in improved stability under occlusion and high processing speed.

Contribution

The paper presents a new tracking method that considers outliers as valuable information, enhancing robustness and speed without requiring hardware acceleration.

Findings

Enhanced tracking stability under severe occlusion

Achieves over 100 frames per second in real-time

Outperforms state-of-the-art algorithms in benchmark tests

Abstract

In object tracking, outlier is one of primary factors which degrade performance of image-based tracking algorithms. In this respect, therefore, most of the existing methods simply discard detected outliers and pay little or no attention to employing them as an important source of information for motion estimation. We consider outliers as important as inliers for object tracking and propose a motion estimation algorithm based on concurrent tracking of inliers and outliers. Our tracker makes use of pyramidal implementation of the Lucas-Kanade tracker to estimate motion flows of inliers and outliers and final target motion is estimated robustly based on both of these information. Experimental results from challenging benchmark video sequences confirm enhanced tracking performance, showing highly stable target tracking under severe occlusion compared with state-of-the-art algorithms. The proposed algorithm runs at more than 100 frames per second even without using a hardware accelerator, which makes the proposed method more practical and portable.