3차원 포인트 클라우드 데이터를 활용한 객체 탐지 기법인 PointNet과 RandLA-Net
PointNet and RandLA-Net Algorithms for Object Detection using 3D Point Clouds
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Research on object detection algorithms using 2D data has already progressed to the level of commercialization and is being applied to various manufacturing industries. Object detection technology using 2D data has an effective advantage, there are technical limitations to accurate data generation and analysis. Since 2D data is two-axis data without a sense of depth, ambiguity arises when approached from a practical point of view. Advanced countries such as the United States are leading 3D data collection and research using 3D laser scanners. Existing processing and detection algorithms such as ICP and RANSAC show high accuracy, but are used as a processing speed problem in the processing of large-scale point cloud data. In this study, PointNet a representative technique for detecting objects using widely used 3D point cloud data is analyzed and described. And RandLA-Net, which overcomes the limitations of PointNet's performance and object prediction accuracy, is described a review of detection technology using point cloud data was conducted.
Abstract
Research on object detection algorithms using 2D data has already progressed to the level of commercialization and is being applied to various manufacturing industries. Object detection technology using 2D data has an effective advantage, there are technical limitations to accurate data generation and analysis. Since 2D data is two-axis data without a sense of depth, ambiguity arises when approached from a practical point of view. Advanced countries such as the United States are leading 3D data collection and research using 3D laser scanners. Existing processing and detection algorithms such as ICP and RANSAC show high accuracy, but are used as a processing speed problem in the processing of large-scale point cloud data. In this study, PointNet a representative technique for detecting objects using widely used 3D point cloud data is analyzed and described. And RandLA-Net, which overcomes the limitations of PointNet's performance and object prediction accuracy, is described a review of detection technology using point cloud data was conducted.
참고문헌 (9)
- Chen, X., "Individual tree crown segmentation directly from UAV-Borne LiDAR data using the PointNet of deep learning", Journal of the Forests, 12(2), pp.131~ (2021)
- Hu, Q., "RandLA-Net: Efficient semantic segmentation of large-scale point clouds", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)
- Jaderberg, M., "Spatial transformer networks", Part of Advances in Neural Information Processing Systems, 28, pp.1213~ (2015)
- Jing, L., "Depth estimation matters most: improving per-object depth estimation for monocular 3D detection and tracking", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2022)
- 이동건, "딥러닝 기반 LNGC 화물창 스캐닝 점군 데이터의 비계 시스템 객체 탐지 및 후처리", 대한조선학회 논문집, 58(5), pp.303~313 (2021), 대한조선학회[DOI]
- 송상호, "인공지능 기반 선체 균열 탐지 현장 적용성 연구", 대한조선학회 논문집, 59(4), pp.192~199 (2022), 대한조선학회[DOI]
- 송상호, "포인트 클라우드 기반 선체 구조 변형 탐지 알고리즘 적용 연구", 대한조선학회 논문집, 59(4), pp.235~242 (2022), 대한조선학회[DOI]
- Qi, C. R., "Imvotenet: boosting 3d object detection in point clouds with image votes", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)
- Qi, C. R., "PointNet: Deep learning on point sets for 3D classification and segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)