3D Object Detection under Urban Road Traffic Scenarios Based on Dual-Layer Voxel Features Fusion Augmentation
Open Access
Abstract
To enhance the accuracy of detecting objects in front of intelligent vehicles in urban road scenarios, this paper proposes a dual-layer voxel feature fusion augmentation network (DL-VFFA). It aims to address the issue of objects misrecognition caused by local occlusion or limited field of view for targets. The network employs a point cloud voxelization architecture, utilizing the Mahalanobis distance to associate similar point clouds within neighborhood voxel units. It integrates local and global information through weight sharing to extract boundary point information within each voxel unit. The relative position encoding of voxel features is computed using an improved attention Gaussian deviation matrix in point cloud space to focus on the relative positions of different voxel sequences within channels. During the fusion of point cloud and image features, learnable weight parameters are designed to decouple fine-grained regions, enabling two-layer feature fusion from voxel to voxel and from point cloud to image. Extensive experiments on the KITTI dataset demonstrate the significant performance of DL-VFFA. Compared to the baseline network Second, DL-VFFA performs better in medium- and high-difficulty scenarios. Furthermore, compared to the voxel fusion module in MVX-Net, the voxel feature fusion results in this paper are more accurate, effectively capturing fine-grained object features post-voxelization. Through ablative experiments, we conducted in-depth analyses of the three voxel fusion modules in DL-VFFA to enhance the performance of the baseline detector and achieved superior results.Keywords
Funding Information
- National Natural Science Foundation of China (52202414)
This publication has 36 references indexed in Scilit:
- SIANet: 3D object detection with structural information augment networkIET Computer Vision, 2024
- G-Fusion: LiDAR and Camera Feature Fusion on the Ground Voxel SpaceIEEE Access, 2024
- Optimized voxel transformer for 3D detection with spatial-semantic feature aggregationComputers and Electrical Engineering, 2023
- Dual-level Deep Evidential Fusion: Integrating multimodal information for enhanced reliable decision-making in deep learningInformation Fusion, 2023
- V2PNet: Voxel-to-Point Feature Propagation and Fusion That Improves Feature Representation for Point Cloud RegistrationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023
- VP-Net: Voxels as Points for 3-D Object DetectionIEEE Transactions on Geoscience and Remote Sensing, 2023
- HCPVF: Hierarchical Cascaded Point-Voxel Fusion for 3D Object DetectionIEEE Transactions on Circuits and Systems for Video Technology, 2023
- Automated CT pancreas segmentation for acute pancreatitis patients by combining a novel object detection approach and U-NetBiomedical Signal Processing and Control, 2022
- Multi-modal feature fusion for 3D object detection in the production workshopApplied Soft Computing, 2022
- Mahalanobis distanceResonance, 1999