Improving analytical color and texture similarity estimation methods for dataset-agnostic person reidentification

TL;DR

This paper presents a low-computation, dataset-agnostic person re-identification method using human parsing, color and texture analysis, and a novel autoencoder for improved similarity estimation, achieving competitive results on Market1501.

Contribution

It introduces a new re-id approach combining interpretable features and a supervised autoencoder, eliminating the need for re-id dataset training.

Findings

Comparable rank-1 and mAP results to deep learning methods

Effective color analysis in CIE-Lab space with histogram smoothing

Novel autoencoder improves texture similarity measurement

Abstract

This paper studies a combined person reidentification (re-id) method that uses human parsing, analytical feature extraction and similarity estimation schemes. One of its prominent features is its low computational requirements so it can be implemented on edge devices. The method allows direct comparison of specific image regions using interpretable features which consist of color and texture channels. It is proposed to analyze and compare colors in CIE-Lab color space using histogram smoothing for noise reduction. A novel pre-configured latent space (LS) supervised autoencoder (SAE) is proposed for texture analysis which encodes input textures as LS points. This allows to obtain more accurate similarity measures compared to simplistic label comparison. The proposed method also does not rely upon photos or other re-id data for training, which makes it completely re-id dataset-agnostic. The viability of the proposed method is verified by computing rank-1, rank-10, and mAP re-id metrics on Market1501 dataset. The results are comparable to those of conventional deep learning methods and the potential ways to further improve the method are discussed.