This chapter covers how 3D data is represented and processed using voxels, point clouds, and meshes, with methods like PointNet and DGCNN. It discusses early and late fusion strategies for combining sensor data, emphasizing LiDARcamera fusion techniques such as Frustum PointNets and PointPainting to improve object detection. Additionally, feature-level fusion methods like DeepFusion and BEVFusion improve 3D perception by aligning sensor data for more accurate tracking and detection.
Robot Perception: 3D Data and Sensor Fusion
AI for Robotics ; Chapter : 3 ; 107-137
2025-05-03
31 pages
Article/Chapter (Book)
Electronic Resource
English
Multi-sensor fusion mapping robot and data fusion method
European Patent Office | 2023
|Data Fusion in Multi Sensor Platforms for Widearea Perception
British Library Conference Proceedings | 2006
|Perception of Microburst Based on Multi-Sensor Data Fusion
British Library Online Contents | 2011
|Perception Sensor for a Mobile Robot
British Library Conference Proceedings | 1995
|