Vehicle Re-Identification via Multi-Scale Feature Learningand Dual Attention Fusion.

In the continuous evolution of intelligent transportation systems, vehicle re-identification technology faces numerous technical challenges, including variations in perspective and equipment resolution. These factors lead to significant intra-class discrepancies in the performance of identical vehicles under varying conditions, as well as inter-class confusion among vehicles with similar appearances. To address these challenges, we integrate vehicle color and type attribute information, enhancing the model’s ability to capture semantic features and improve its discriminative performance. Additionally, we propose a wavelet feature enhancement module that employs wavelet transform to decompose images at multiple scales, effectively capturing fine-grained features such as edges and textures. This enables the model to better represent intricate visual details. Finally, we introduce a dual attention mechanism that combines global and local features, strengthening contextual understanding through interactive feature modeling. Experimental results demonstrate the effectiveness of our approach, achieving a Rank-1 accuracy of 96.8 percent on the VeRi-776 dataset and 84.9 percent on the VehicleID dataset, outperforming existing methods and highlighting the efficacy of our proposed framework.