LiDAR-based background interpolation method for obstacles
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
LiDAR is a crucial element of location-based services (LBSs), including autonomous driving, and is a technology that can identify surrounding objects and terrain. The topography changes due to the occlusion at the indoor where the movement of objects is frequent limits positioning using LiDAR. We propose the dual-background segmentation model, which can distinguish terrain and remove obstacles, and the Binning-based Mode Interpolation Algorithm, which can interpolate the removed obstacles into the back-ground, is combined in LiDAR-based Background Interpolation Method for Obstacles. The proposed model recognizes an obstacle as an object using a detection model, locates the object, and expresses its shape. Thus, an object is detected in the LiDAR image, and the information of the corresponding ROI is removed. Then, using the binning-based mode interpolation algorithm, the background of the obstacle is restored by interpolating the remaining area based on depth information from the surrounding terrain of the object. Thus, the proposed method can acquire the topography even in an indoor space with many object changes.
Abstract
LiDAR is a crucial element of location-based services (LBSs), including autonomous driving, and is a technology that can identify surrounding objects and terrain. The topography changes due to the occlusion at the indoor where the movement of objects is frequent limits positioning using LiDAR. We propose the dual-background segmentation model, which can distinguish terrain and remove obstacles, and the Binning-based Mode Interpolation Algorithm, which can interpolate the removed obstacles into the back-ground, is combined in LiDAR-based Background Interpolation Method for Obstacles. The proposed model recognizes an obstacle as an object using a detection model, locates the object, and expresses its shape. Thus, an object is detected in the LiDAR image, and the information of the corresponding ROI is removed. Then, using the binning-based mode interpolation algorithm, the background of the obstacle is restored by interpolating the remaining area based on depth information from the surrounding terrain of the object. Thus, the proposed method can acquire the topography even in an indoor space with many object changes.
참고문헌 (21)
- S. Pang, "CLOCs: Camera-Li-DAR object candidates fusion for 3D object detection", 2020 IEEE, 2020, 10386~10393
- Y. Li, "DeepFusion: Lidar-camera deep fusion for multi-modal 3D object detection", 2022 IEEE, 2022, 17161~17170
- Z. Li, "LiDAR R-CNN : An efficient and universal 3D object detector", 2021 IEEE, 2021, 7542~7551
- S. Ren, "Faster r-cnn: towards real-time object detection with region proposal net-works", Advances in neural information processing systems (NIPS), 28 (2015)
- R. Girshick, "Rich fea-ture hierarchies for accurate object detection and semantic segmentation", 2014 Proceedings of the IEEE conference on computer vision and pattern recognition(CVPR), pp.580~587 (2014)
- R. Girshick, "Fast R-CNN", 2015 Proceedings of the IEEE international conference on computer vision, pp.1440~1448 (2015)
- M. Tang, "High-speed track-ing with multi-kernel correlation filters", 2018 Proceedings of the IEEE Conference On Computer Vision and Pattern Recognition(CVPR), pp.4874~4883 (2018)
- H. Fan, "Siamese cascaded region proposal net-works for real-time visual tracking", 2019 Proceedings of the IEEE, 2019, 7944~7953
- P. Anderson, "Bottom-up and top-down attention for image captioning and visual question answering", 2018 Proceedings of the IEEE Conference On Computer Vision And Pattern Recognition(CVPR), pp.6077~6086 (2018)
- Y. Pan, "X-linear attention net-works for image captioning", 2020 Proceedings of the IEEE, 2020, 10968~10977
- 이동석, "Faster R-CNN 기반의 실시간 번호판 검출", 정보처리학회 논문지, 5(11), pp.511~520 (2016), 한국정보처리학회[DOI]
- N. P. Ap, "Automatic number plate detection in vehicles using faster R-CNN", 2020 International Conference On System, Computation, Automation And Networking (ICSCAN), pp.1~6 (2020)
- P. Lyu, "Multi-oriented scene text detection via corner localization and region seg-mentation", 2018 Proceedings of the IEEE Conference On Computer Vision And Pattern Recognition(CVPR), pp.7553~7563 (2018)
- 선민혁, "자율 주행을 위한 딥러닝 기반 라이다 객체 인식 신경망 연구 분석", 한국자동차공학회 논문집, 30(8), pp.635~647 (2022), 한국자동차공학회
- G. Melotti, "Multimodal deep-learning for object recognition combining camera and LIDAR data", 2020 IEEE International Conference on Au-tonomous Robot Systems and Competitions(ICARSC), pp.177~182 (2020)
- 백수진, "카메라와 라이다의 센서융합을 이용한 객체 추적 시스템 개발", 한국지능시스템학회 논문지, 32(6), pp.500~506 (2022), 한국지능시스템학회[DOI]
- S. Wang, "Object tracking based on the fusion of roadside lidar and camera data", IEEE Transactions on Instrumentation and Measurement, 71, pp.1~14 (2022)
- J. Roche, "A multimodal data processing system for LiDAR-based human activity recognition", IEEE Transactions on Cybernetics, 52(10), pp.10027~10040 (2022)
- M. A. U. Alam, "Lamar: LiDAR based multi-inhabitant activity recog-nition", MobiQuitous 2020-17th EAI International Con-ference on Mobile and Ubiquitous Systems: Computing, Networking and Services, pp.1~9 (2020)
- 이준구, "드론과 지상 LiDAR를 활용한 포인트클라우드 데이터 융합 기반의 건물 실내외 모델링", 한국측량학회지, 40(6), pp.613~620 (2022), 한국측량학회[DOI]
- J. Huang, "City3D: Large-scale building reconstruction from airborne LiDAR point clouds", Remote Sensing, 14(9), pp.2254~ (2022)