3D Object Recognition and Localization with a Dense LiDAR Scanner
Dense scanning is an effective solution for refined geometrical modeling applications. The previous studies in dense environment modeling mostly focused on data acquisition techniques without emphasizing autonomous target recognition and accurate 3D localization. Therefore, they lacked the capabilit...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Actuators |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-0825/11/1/13 |
| _version_ | 1827667404985991168 |
|---|---|
| author | Hao Geng Zhiyuan Gao Guorun Fang Yangmin Xie |
| author_facet | Hao Geng Zhiyuan Gao Guorun Fang Yangmin Xie |
| author_sort | Hao Geng |
| collection | DOAJ |
| description | Dense scanning is an effective solution for refined geometrical modeling applications. The previous studies in dense environment modeling mostly focused on data acquisition techniques without emphasizing autonomous target recognition and accurate 3D localization. Therefore, they lacked the capability to output semantic information in the scenes. This article aims to make complementation in this aspect. The critical problems we solved are mainly in two aspects: (1) system calibration to ensure detail-fidelity for the 3D objects with fine structures, (2) fast outlier exclusion to improve 3D boxing accuracy. A lightweight fuzzy neural network is proposed to remove most background outliers, which was proven in experiments to be effective for various objects in different situations. With precise and clean data ensured by the two abovementioned techniques, our system can extract target objects from the original point clouds, and more importantly, accurately estimate their center locations and orientations. |
| first_indexed | 2024-03-10T03:10:10Z |
| format | Article |
| id | doaj.art-1e03b77ce43f46e2ad949ec58da4496c |
| institution | Directory Open Access Journal |
| issn | 2076-0825 |
| language | English |
| last_indexed | 2024-03-10T03:10:10Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Actuators |
| spelling | doaj.art-1e03b77ce43f46e2ad949ec58da4496c2023-11-23T12:33:36ZengMDPI AGActuators2076-08252022-01-011111310.3390/act110100133D Object Recognition and Localization with a Dense LiDAR ScannerHao Geng0Zhiyuan Gao1Guorun Fang2Yangmin Xie3Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200444, ChinaShanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200444, ChinaShanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200444, ChinaShanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200444, ChinaDense scanning is an effective solution for refined geometrical modeling applications. The previous studies in dense environment modeling mostly focused on data acquisition techniques without emphasizing autonomous target recognition and accurate 3D localization. Therefore, they lacked the capability to output semantic information in the scenes. This article aims to make complementation in this aspect. The critical problems we solved are mainly in two aspects: (1) system calibration to ensure detail-fidelity for the 3D objects with fine structures, (2) fast outlier exclusion to improve 3D boxing accuracy. A lightweight fuzzy neural network is proposed to remove most background outliers, which was proven in experiments to be effective for various objects in different situations. With precise and clean data ensured by the two abovementioned techniques, our system can extract target objects from the original point clouds, and more importantly, accurately estimate their center locations and orientations.https://www.mdpi.com/2076-0825/11/1/133D Lidar scanningLidar calibration3D object localizationfuzzy neural network |
| spellingShingle | Hao Geng Zhiyuan Gao Guorun Fang Yangmin Xie 3D Object Recognition and Localization with a Dense LiDAR Scanner Actuators 3D Lidar scanning Lidar calibration 3D object localization fuzzy neural network |
| title | 3D Object Recognition and Localization with a Dense LiDAR Scanner |
| title_full | 3D Object Recognition and Localization with a Dense LiDAR Scanner |
| title_fullStr | 3D Object Recognition and Localization with a Dense LiDAR Scanner |
| title_full_unstemmed | 3D Object Recognition and Localization with a Dense LiDAR Scanner |
| title_short | 3D Object Recognition and Localization with a Dense LiDAR Scanner |
| title_sort | 3d object recognition and localization with a dense lidar scanner |
| topic | 3D Lidar scanning Lidar calibration 3D object localization fuzzy neural network |
| url | https://www.mdpi.com/2076-0825/11/1/13 |
| work_keys_str_mv | AT haogeng 3dobjectrecognitionandlocalizationwithadenselidarscanner AT zhiyuangao 3dobjectrecognitionandlocalizationwithadenselidarscanner AT guorunfang 3dobjectrecognitionandlocalizationwithadenselidarscanner AT yangminxie 3dobjectrecognitionandlocalizationwithadenselidarscanner |