Multilinear subspace learning for person re-identification based fusion of high order tensor features

TL;DR

This work addresses cross-camera person re-identification (PRe-ID) by fusing heterogeneous features from CNNs and LOMO into a high-order tensor representation. It introduces High-Dimensional Feature Fusion (HDFF) to produce a 3rd-order tensor, then applies Tensor Cross-View Quadratic Analysis (TXQDA) for multilinear subspace learning, followed by Cosine similarity for matching. The approach yields substantial improvements on VIPeR, GRID, and PRID450S, with GRID showing particularly strong gains (e.g., Rank-1 up to 86.48%), validating the efficacy of 3rd-order tensor fusion for PRe-ID. Overall, the method demonstrates that integrating multi-modality features within a multilinear framework can robustly enhance cross-view person identification, with potential applicability to vehicle Re-ID in future work.

Abstract

Video surveillance image analysis and processing is a challenging field in computer vision, with one of its most difficult tasks being Person Re-Identification (PRe-ID). PRe-ID aims to identify and track target individuals who have already been detected in a network of cameras, using a robust description of their pedestrian images. The success of recent research in person PRe-ID is largely due to effective feature extraction and representation, as well as the powerful learning of these features to reliably discriminate between pedestrian images. To this end, two powerful features, Convolutional Neural Networks (CNN) and Local Maximal Occurrence (LOMO), are modeled on multidimensional data using the proposed method, High-Dimensional Feature Fusion (HDFF). Specifically, a new tensor fusion scheme is introduced to leverage and combine these two types of features in a single tensor, even though their dimensions are not identical. To enhance the system's accuracy, we employ Tensor Cross-View Quadratic Analysis (TXQDA) for multilinear subspace learning, followed by cosine similarity for matching. TXQDA efficiently facilitates learning while reducing the high dimensionality inherent in high-order tensor data. The effectiveness of our approach is verified through experiments on three widely-used PRe-ID datasets: VIPeR, GRID, and PRID450S. Extensive experiments demonstrate that our approach outperforms recent state-of-the-art methods.

Figures (6)

• Figure 1: Person Re-Identification pipeline.
• Figure 2: High-Dimensional Feature Fusion framework.
• Figure 3: Tensor reshaping process: vectorization, Matricization and tensorization.
• Figure 4: The principle of TXQDA algorithm.
• Figure 5: CMC scores for Ranks 1 to 20 and different datasets.