Person Re-Identification across Data Distributions Based on General Purpose DNN Object Detector

Roxana-Elena Mihaescu,Marian Ghenescu,Serban Carata,Constantin Paleologu,Mihai Chindea

doi:10.3390/a13120343

Roxana-Elena Mihaescu, Marian Ghenescu + Show 3 more

Open Access

https://doi.org/10.3390/a13120343

Copy DOI

Abstract

Solving the person re-identification problem involves making associations between the same person’s appearances across disjoint camera views. Further, those associations have to be made on multiple surveillance cameras in order to obtain a more efficient and powerful re-identification system. The re-identification problem becomes particularly challenging in very crowded areas. This mainly happens for two reasons. First, the visibility is reduced and occlusions of people can occur. Further, due to congestion, as the number of possible matches increases, the re-identification is becoming challenging to achieve. Additional challenges consist of variations of lightning, poses, or viewpoints, and the existence of noise and blurring effects. In this paper, we aim to generalize person re-identification by implementing a first attempt of a general system, which is robust in terms of distribution variations. Our method is based on the YOLO (You Only Look Once) model, which represents a general object detection system. The novelty of the proposed re-identification method consists of using a simple detection model, with minimal additional costs, but with results that are comparable with those of the other existing dedicated methods.

Highlights

Nowadays, the surrounding world is full of surveillance cameras, so that data that are generated from video surveillance are continuously expanding
The testing stage involves passing each image from the test database through the Convolutional Neural Network (CNN), obtaining the feature vectors
The ultimate goal is to compare each feature vector with all of the other vectors that belong to the previous images, and associate people based on the similarity between the vectors

Summary

Introduction

The surrounding world is full of surveillance cameras, so that data that are generated from video surveillance are continuously expanding. It has become impossible for a human operator to track and verify people’s identities in the entire database on its own. For this reason, the tendency is to use systems that are capable of achieving the recognition [1,2] and tracking [3,4] of people automatically. Most algorithms in the field focus on detecting and recognizing people [5] It faces many obstacles, the recognition has evolved considerably over the last years

Objectives

Methods

Results

Conclusion