GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval

TL;DR

This paper introduces GLAD, a robust descriptor for pedestrian re-identification that combines local and global cues, along with an efficient retrieval framework, to improve accuracy and speed in large-scale surveillance data.

Contribution

The work presents a novel Global-Local-Alignment Descriptor (GLAD) and a hierarchical retrieval framework, enhancing accuracy and efficiency in person re-identification tasks.

Findings

GLAD achieves competitive accuracy with state-of-the-art methods.

The retrieval framework significantly accelerates online Re-ID.

The approach is effective in real-world surveillance scenarios.

Abstract

The huge variance of human pose and the misalignment of detected human images significantly increase the difficulty of person Re-Identification (Re-ID). Moreover, efficient Re-ID systems are required to cope with the massive visual data being produced by video surveillance systems. Targeting to solve these problems, this work proposes a Global-Local-Alignment Descriptor (GLAD) and an efficient indexing and retrieval framework, respectively. GLAD explicitly leverages the local and global cues in human body to generate a discriminative and robust representation. It consists of part extraction and descriptor learning modules, where several part regions are first detected and then deep neural networks are designed for representation learning on both the local and global regions. A hierarchical indexing and retrieval framework is designed to eliminate the huge redundancy in the gallery set, and accelerate the online Re-ID procedure. Extensive experimental results show GLAD achieves competitive accuracy compared to the state-of-the-art methods. Our retrieval framework significantly accelerates the online Re-ID procedure without loss of accuracy. Therefore, this work has potential to work better on person Re-ID tasks in real scenarios.