Applications of a Graph Theoretic Based Clustering Framework in Computer Vision and Pattern Recognition

TL;DR

This paper introduces a unified graph-theoretic clustering framework based on dominant set clustering to address various challenging tasks in computer vision and pattern recognition, demonstrating superior results over existing methods.

Contribution

It presents novel clustering approaches for multi-target tracking, visual geo-localization, and outlier detection, unifying these tasks under a single graph-theoretic framework.

Findings

Superior performance over state-of-the-art methods

Effective for multi-target tracking and geo-localization

Robust outlier detection capabilities

Abstract

Recently, several clustering algorithms have been used to solve variety of problems from different discipline. This dissertation aims to address different challenging tasks in computer vision and pattern recognition by casting the problems as a clustering problem. We proposed novel approaches to solve multi-target tracking, visual geo-localization and outlier detection problems using a unified underlining clustering framework, i.e., dominant set clustering and its extensions, and presented a superior result over several state-of-the-art approaches.