Version 1
: Received: 26 October 2023 / Approved: 26 October 2023 / Online: 27 October 2023 (03:52:14 CEST)
How to cite:
Wang, X.; Liu, J.; Liao, Z. AGPNet: Augmented Graph Pointpillars for Object Detection from Point Clouds. Preprints2023, 2023101729. https://doi.org/10.20944/preprints202310.1729.v1
Wang, X.; Liu, J.; Liao, Z. AGPNet: Augmented Graph Pointpillars for Object Detection from Point Clouds. Preprints 2023, 2023101729. https://doi.org/10.20944/preprints202310.1729.v1
Wang, X.; Liu, J.; Liao, Z. AGPNet: Augmented Graph Pointpillars for Object Detection from Point Clouds. Preprints2023, 2023101729. https://doi.org/10.20944/preprints202310.1729.v1
APA Style
Wang, X., Liu, J., & Liao, Z. (2023). AGPNet: Augmented Graph Pointpillars for Object Detection from Point Clouds. Preprints. https://doi.org/10.20944/preprints202310.1729.v1
Chicago/Turabian Style
Wang, X., Jian Liu and Zhonghe Liao. 2023 "AGPNet: Augmented Graph Pointpillars for Object Detection from Point Clouds" Preprints. https://doi.org/10.20944/preprints202310.1729.v1
Abstract
In the realm of autonomous vehicle environment perception, the primary objective of point cloud target detection is to swiftly and accurately identify three-dimensional objects from point cloud data. To meet this requirement, the prevalent network architecture employed in the industry is the voxel-based PointPillars model. Nonetheless, this model faces challenges in maintaining detection accuracy when objects are obscured or diminutive in size. In response to this issue, we introduce AGPNet, a novel model that seamlessly integrates four key modules: Data Augmentation, Dynamic Graph CNN, Pillar Feature Net, and Detection Head (SSD). The Data Augmentation module enhances the adaptability of point cloud data to complex and ever-changing real-world environments. The Dynamic Graph CNN module endows the network structure with geometric features, which encapsulate not only the point itself but also its adjacent points. The Pillar Feature Net module translates three-dimensional point cloud data into pseudo-image data through the utilization of voxels. Subsequently, the Detection Head (SSD) module leverages this pseudo-image data to conduct target detection of three-dimensional objects. Our experiments, conducted on the KITTI dataset, demonstrate that our proposed method boosts object detection accuracy by 6-7 percentage points compared to the PointPillars model, while maintaining similar detection times.
Keywords
3D object detection; point cloud; voxel; deep learning
Subject
Computer Science and Mathematics, Computer Vision and Graphics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.