CL-fusionBEV: 3D object detection method with camera-LiDAR fusion in Bird’s Eye View

• Published in: Complex & intelligent systems Vol. 10; no. 6; pp. 7681 - 7696
• Main Authors: Shi, Peicheng, Liu, Zhiqiang, Dong, Xinlong, Yang, Aixi
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.12.2024; Springer Nature B.V; Springer
• Subjects: 3D object detection; Attention; Attention mechanism; Autonomous driving; Bird’s Eye View (BEV) perception; Cameras; Cartesian coordinates; Complexity; Computational Intelligence; Data integration; Data Structures and Information Theory; Datasets; Engineering; Lidar; Modal data; Modules; Multisensor fusion; Object recognition; Original Article; Pedestrians; Three dimensional models; Attention mechanism; Bird’s Eye View (BEV) perception; Autonomous driving; 3D object detection
• ISSN: 2199-4536; 2198-6053
• DOI: 10.1007/s40747-024-01567-0

In the wave of research on autonomous driving, 3D object detection from the Bird’s Eye View (BEV) perspective has emerged as a pivotal area of focus. The essence of this challenge is the effective fusion of camera and LiDAR data into the BEV. Current approaches predominantly train and predict within the front view and Cartesian coordinate system, often overlooking the inherent structural and operational differences between cameras and LiDAR sensors. This paper introduces CL-FusionBEV, an innovative 3D object detection methodology tailored for sensor data fusion in the BEV perspective. Our approach initiates with a view transformation, facilitated by an implicit learning module that transitions the camera’s perspective to the BEV space, thereby aligning the prediction module. Subsequently, to achieve modal fusion within the BEV framework, we employ voxelization to convert the LiDAR point cloud into BEV space, thereby generating LiDAR BEV spatial features. Moreover, to integrate the BEV spatial features from both camera and LiDAR, we have developed a multi-modal cross-attention mechanism and an implicit multi-modal fusion network, designed to enhance the synergy and application of dual-modal data. To counteract potential deficiencies in global reasoning and feature interaction arising from multi-modal cross-attention, we propose a BEV self-attention mechanism that facilitates comprehensive global feature operations. Our methodology has undergone rigorous evaluation on a substantial dataset within the autonomous driving domain, the nuScenes dataset. The outcomes demonstrate that our method achieves a mean Average Precision (mAP) of 73.3% and a nuScenes Detection Score (NDS) of 75.5%, particularly excelling in the detection of cars and pedestrians with high accuracies of 89% and 90.7%, respectively. Additionally, CL-FusionBEV exhibits superior performance in identifying occluded and distant objects, surpassing existing comparative methods.