Introduction
Person re-identification (PRe-ID) is an important topic in the field of computer vision, gaining significant attention in recent years. It involves the identification of individuals across different camera views where there is no overlap. In this article, we introduce a novel PRe-ID system that employs tensor feature representation and multilinear subspace learning. Our approach harnesses the capabilities of pre-trained Convolutional Neural Networks (CNNs) as a robust deep feature extractor, alongside two complementary descriptors – Local Maximal Occurrence (LOMO) and Gaussian Of Gaussian (GOG). To enhance the discriminative power between different individuals, we utilize Tensor-based Cross-View Quadratic Discriminant Analysis (TXQDA) to learn a discriminative subspace. During matching and similarity computation between query and gallery samples, the Mahalanobis distance metric is employed. Our proposed method is evaluated through experiments conducted on three datasets – VIPeR, GRID, and PRID450s.
Abstract:Person re-identification (PRe-ID) is a computer vision issue, that has been a fertile research area in the last few years. It aims to identify persons across different non-overlapping camera views. In this paper, We propose a novel PRe-ID system that combines tensor feature representation and multilinear subspace learning. Our method exploits the power of pre-trained Convolutional Neural Networks (CNNs) as a strong deep feature extractor, along with two complementary descriptors, Local Maximal Occurrence (LOMO) and Gaussian Of Gaussian (GOG). Then, Tensor-based Cross-View Quadratic Discriminant Analysis (TXQDA) is used to learn a discriminative subspace that enhances the separability between different individuals. Mahalanobis distance is used to match and similarity computation between query and gallery samples. Finally, we evaluate our approach by conducting experiments on three datasets VIPeR, GRID, and PRID450s.