Abstract
In autonomous driving, 3D object detection based on multi-modal data has become an indispensable perceptual approach when facing complex environments around the vehicle. During multi-modal detection, LiDAR and a camera are simultaneously applied for capturing and modeling. However, due to the intrinsic discrepancies between the LiDAR point and camera image, the fusion of the data for object detection encounters a series of problems, which results in most multi-modal detection methods performing worse than LiDAR-only methods. In this investigation, we propose a method named PTA-Det to improve the performance of multi-modal detection. Accompanied by PTA-Det, a Pseudo Point Cloud Generation Network is proposed, which can represent the textural and semantic features of keypoints in the image by pseudo points. Thereafter, through a transformer-based Point Fusion Transition (PFT) module, the features of LiDAR points and pseudo points from an image can be deeply fused under a unified point-based form. The combination of these modules can overcome the main obstacle of cross-modal feature fusion and achieves a complementary and discriminative representation for proposal generation. Extensive experiments on KITTI dataset support the effectiveness of PTA-Det, achieving a mAP (mean average precision) of 77.88% on the car category with relatively few LiDAR input points.