Occlusion Aware Kernel Correlation Filter Tracker using RGB-D

TL;DR

This paper introduces an occlusion-aware RGB-D kernel correlation filter tracker that enhances real-time object tracking by addressing common challenges like occlusions, scale changes, and object rotation, with experimental validation on standard datasets and Kinect V2 data.

Contribution

The paper presents a novel RGB-D kernel correlation filter tracker that improves robustness against occlusions and other challenges, supported by theoretical analysis and experimental evaluation.

Findings

Enhanced tracking accuracy with RGB-D data

Effective occlusion handling in real-time tracking

Improved robustness over traditional KCF methods

Abstract

Unlike deep learning which requires large training datasets, correlation filter-based trackers like Kernelized Correlation Filter (KCF) uses implicit properties of tracked images (circulant matrices) for training in real-time. Despite their practical application in tracking, a need for a better understanding of the fundamentals associated with KCF in terms of theoretically, mathematically, and experimentally exists. This thesis first details the workings prototype of the tracker and investigates its effectiveness in real-time applications and supporting visualizations. We further address some of the drawbacks of the tracker in cases of occlusions, scale changes, object rotation, out-of-view and model drift with our novel RGB-D Kernel Correlation tracker. We also study the use of particle filters to improve trackers' accuracy. Our results are experimentally evaluated using a) standard dataset and b) real-time using the Microsoft Kinect V2 sensor. We believe this work will set the basis for a better understanding of the effectiveness of kernel-based correlation filter trackers and to further define some of its possible advantages in tracking.