V²[jls-end-space/]-Fusion: Virtual voxel enhanced 4D radar-image feature fusion for 3D object detection

In recent times, 4D radar sensors have gained significant attention in the autonomous driving sector for their cost-effectiveness and reliability under adverse weather conditions. Despite their advantages, the sparsity and lack of surface texture in the acquired 4D radar data pose challenges for perception tasks. Currently, 4D radar faces the issue of sparse point clouds and a lack of clear geometric appearance. We propose a novel detection method called V²[jls-end-space/]-Fusion using image information to densify the foreground 4D radar voxels to highlight the foreground information and reducing the impact of projection misalignment errors. Firstly, V²[jls-end-space/]-Fusion presents a Voxel-level Foreground Semantic Feature Enhancement Module (VFSFE), utilizing image semantic information to densify the foreground part, improving the model’s capability to discern foreground probabilities and thus refining voxel densification quality. Besides, V²[jls-end-space/]-Fusion exhibits an Objective Contextual Texture Feature Aggregation Module (OCTFA) incorporating contextual information from target position image features, expanding the receptive field, and alleviating the inaccuracies in loss fusion caused by projection alignment errors. Evaluations on the View-of-Delft(VoD) and Dual-Radar datasets demonstrate the efficacy of our proposed method, which shows notable performance enhancements.