Deep learning-based 3D point cloud classification: A systematic survey and outlook |
| |
| Affiliation: | 1. Department of Biochemistry and Biophysics, School of Basic Medical Sciences, Peking University, 38 Xueyuan Road, Beijing 100191, China;2. School of Basic Medical Sciences, Peking University, 38 Xueyuan Road, Beijing 100191, China;3. School of Basic Medical Sciences, Peking University, 38 Xueyuan Road, Beijing 100191, China;4. School of Basic Medical Sciences, Peking University, 38 Xueyuan Road, Beijing 100191, China;5. Division of Cervical Spine, Department of Orthopaedic, Third Hospital of Peking University, 49 Huayuanbei Road, Beijing 100191, China;6. Division of Cervical Spine, Department of Orthopaedic, Third Hospital of Peking University, 49 Huayuanbei Road, Beijing 100191, China;7. Division of Cervical Spine, Department of Orthopaedic, Third Hospital of Peking University, 49 Huayuanbei Road, Beijing 100191, China;8. Neuroscience Research Institute and Key Laboratory for Neuroscience, Ministry of Education/National Health Commission of China, Peking University, 38 Xueyuan Road, Beijing 100191, China;1. School of Electronic Engineering, Kumoh National Institute of Technology, Gumi, Gyeongbuk 39177, Republic of Korea;2. The division of AI Software Convergence, Dongguk University, Seoul 04620, Republic of Korea;1. Department of Chemical Engineering, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, Republic of Korea;2. Samsung Display Co., LTD., San #24, Nongseo-dong, Giheung-gu, Yongin-si, Gyeonggi-do 446-711, Republic of Korea;3. Department of Battery Engineering, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, Republic of Korea |
| |
| Abstract: | In recent years, point cloud representation has become one of the research hotspots in the field of computer vision, and has been widely used in many fields, such as autonomous driving, virtual reality, robotics, etc. Although deep learning techniques have achieved great success in processing regular structured 2D grid image data, there are still great challenges in processing irregular, unstructured point cloud data. Point cloud classification is the basis of point cloud analysis, and many deep learning-based methods have been widely used in this task. Therefore, the purpose of this paper is to provide researchers in this field with the latest research progress and future trends. First, we introduce point cloud acquisition, characteristics, and challenges. Second, we review 3D data representations, storage formats, and commonly used datasets for point cloud classification. We then summarize deep learning-based methods for point cloud classification and complement recent research work. Next, we compare and analyze the performance of the main methods. Finally, we discuss some challenges and future directions for point cloud classification. |
| |
| Keywords: | Deep learning Point cloud 3D data Classification |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
