Pillar-Voxel Fusion Network for 3D Object Detection in Airborne Hyperspectral Point Clouds
This addresses 3D object detection in airborne hyperspectral point clouds, a domain-specific task with incremental improvements over existing fusion methods.
The paper tackles the problem of geometric-spectral distortions in hyperspectral point clouds (HPCs) for 3D object detection, proposing PiV-AHPC, which achieves state-of-the-art detection performance and high generalization capability on two airborne HPCs datasets.
Hyperspectral point clouds (HPCs) can simultaneously characterize 3D spatial and spectral information of ground objects, offering excellent 3D perception and target recognition capabilities. Current approaches for generating HPCs often involve fusion techniques with hyperspectral images and LiDAR point clouds, which inevitably lead to geometric-spectral distortions due to fusion errors and obstacle occlusions. These adverse effects limit their performance in downstream fine-grained tasks across multiple scenarios, particularly in airborne applications. To address these issues, we propose PiV-AHPC, a 3D object detection network for airborne HPCs. To the best of our knowledge, this is the first attempt at this HPCs task. Specifically, we first develop a pillar-voxel dual-branch encoder, where the former captures spectral and vertical structural features from HPCs to overcome spectral distortion, while the latter emphasizes extracting accurate 3D spatial features from point clouds. A multi-level feature fusion mechanism is devised to enhance information interaction between the two branches, achieving neighborhood feature alignment and channel-adaptive selection, thereby organically integrating heterogeneous features and mitigating geometric distortion. Extensive experiments on two airborne HPCs datasets demonstrate that PiV-AHPC possesses state-of-the-art detection performance and high generalization capability.