Advancing Person Re-Identification: Tensor-based Feature Fusion and Multilinear Subspace Learning
This work addresses the problem of identifying individuals across non-overlapping camera views for surveillance and security applications, representing an incremental improvement over existing methods.
The paper tackled person re-identification by proposing a system that combines tensor feature representation and multilinear subspace learning, achieving improved performance on datasets like VIPeR, GRID, and PRID450s with concrete gains in accuracy metrics.
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.