Person Re-Identification

TL;DR

This paper reviews and analyzes existing person re-identification methods, evaluates their performance on benchmarks, and proposes improvements to enhance accuracy in surveillance applications.

Contribution

It provides a comprehensive analysis of current Re-ID methods and introduces proposed techniques to improve their effectiveness on benchmark datasets.

Findings

Existing methods achieve state-of-the-art performance on benchmarks.

Qualitative and quantitative analysis reveals strengths and weaknesses of current approaches.

Proposed methods show improved accuracy over baseline models.

Abstract

Person Re-Identification (Re-ID) is an important problem in computer vision-based surveillance applications, in which one aims to identify a person across different surveillance photographs taken from different cameras having varying orientations and field of views. Due to the increasing demand for intelligent video surveillance, Re-ID has gained significant interest in the computer vision community. In this work, we experiment on some existing Re-ID methods that obtain state of the art performance in some open benchmarks. We qualitatively and quantitaively analyse their performance on a provided dataset, and then propose methods to improve the results. This work was the report submitted for COL780 final project at IIT Delhi.