Person Re-Identification System at Semantic Level based on Pedestrian Attributes Ontology

TL;DR

This paper presents a novel person re-identification system that leverages pedestrian attribute ontology, local multi-task deep learning, and imbalance data handling to improve accuracy in large-scale surveillance datasets.

Contribution

The proposed system uniquely combines pedestrian attribute ontology, local multi-task deep neural networks, and imbalance data solutions without altering network architecture or data augmentation.

Findings

Achieved higher accuracy on Market1501 dataset compared to state-of-the-art methods.

Effectively exploited semantic attribute correlations for better re-identification.

Handled attribute imbalance without network modifications or data augmentation.

Abstract

Person Re-Identification (Re-ID) is a very important task in video surveillance systems such as tracking people, finding people in public places, or analysing customer behavior in supermarkets. Although there have been many works to solve this problem, there are still remaining challenges such as large-scale datasets, imbalanced data, viewpoint, fine grained data (attributes), the Local Features are not employed at semantic level in online stage of Re-ID task, furthermore, the imbalanced data problem of attributes are not taken into consideration. This paper has proposed a Unified Re-ID system consisted of three main modules such as Pedestrian Attribute Ontology (PAO), Local Multi-task DCNN (Local MDCNN), Imbalance Data Solver (IDS). The new main point of our Re-ID system is the power of mutual support of PAO, Local MDCNN and IDS to exploit the inner-group correlations of attributes and pre-filter the mismatch candidates from Gallery set based on semantic information as Fashion Attributes and Facial Attributes, to solve the imbalanced data of attributes without adjusting network architecture and data augmentation. We experimented on the well-known Market1501 dataset. The experimental results have shown the effectiveness of our Re-ID system and it could achieve the higher performance on Market1501 dataset in comparison to some state-of-the-art Re-ID methods.