Traditional 3D object detectors use BEV (bird’s eye view) feature maps to generate 3D object proposals, but in a single BEV feature map, there are inevitably the problems of high compression and information loss. To solve this problem, we propose a multi-view joint learning and BEV feature-fusion network. In this network, we mainly propose two fusion modules: the multi-view feature-fusion module and the multi-BEV feature-fusion module. The multi-view feature fusion module performs joint learning from multiple views, fusing features learned from multiple views, and supplementing missing information in the BEV feature map. The multi-BEV feature-fusion module fuses BEV feature map outputs from different feature extractors to further enrich the feature information in the BEV feature map, in order to generate better quality 3D object proposals. We conducted experiments on a widely used KITTI dataset. The results show that our method has significantly improved the detection accuracy of the cyclist category.For cyclist detection tasks at the easy, moderate, and hard levels of the KITTI test dataset, our method improves by $1.57\%$, $2.03\%$, and $0.67\%$, respectively, compared to PV-RCNN.

As a core technology in intelligent transportation systems, vehicle re-identification has attracted growing attention. Most existing methods use CNNs to extract global and local features from vehicle images and roughly integrate them for identifying vehicles, addressing intra-class similarity and inter-class difference. However, a significant challenge arises from redundant information between global and local features and possible misalignment among local features, resulting in suboptimal efficiency when combined. To further improve vehicle re-identification, we propose a stripe-assisted global transformer (SaGT) method, which leverages a dual-branch network based on transformers to learn a discriminative whole representation for each vehicle image. Specifically, one branch exploits a standard transformer layer to extract a global feature, while the other branch employs a stripe feature module (SFM) to construct stripe-based features. To further facilitate the effective incorporation of local information into the learning process of the global feature, we introduce a novel stripe-assisted global loss (SaGL), which combines ID losses to optimize the model. Considering redundancy, we only use the global feature for inference, as we enhance the whole representation with stripe-specific details. Finally, we introduce a spatial-temporal probability (STPro) to provide a complementary metric for robust vehicle re-identification. Extensive and comprehensive evaluations on two public datasets validate the effectiveness and superiority of our proposed method.