3D Object Recognition and Pose Estimation From Point Cloud Using Stably Observed Point Pair Feature
Recognition and pose estimation from 3D free-form objects is a key step for autonomous robotic manipulation. Recently, the point pair features (PPF) voting approach has been shown to be effective for simultaneous object recognition and pose estimation. However, the global model descriptor (e.g., PPF...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9024052/ |
| _version_ | 1830191874715942912 |
|---|---|
| author | Deping Li Hanyun Wang Ning Liu Xiaoming Wang Jin Xu |
| author_facet | Deping Li Hanyun Wang Ning Liu Xiaoming Wang Jin Xu |
| author_sort | Deping Li |
| collection | DOAJ |
| description | Recognition and pose estimation from 3D free-form objects is a key step for autonomous robotic manipulation. Recently, the point pair features (PPF) voting approach has been shown to be effective for simultaneous object recognition and pose estimation. However, the global model descriptor (e.g., PPF and its variants) that contained some unnecessary point pair features decreases the recognition performance and increases computational efficiency. To address this issue, in this paper, we introduce a novel strategy for building a global model descriptor using stably observed point pairs. The stably observed point pairs are calculated from the partial view point clouds which are rendered by the virtual camera from various viewpoints. The global model descriptor is extracted from the stably observed point pairs and then stored in a hash table. Experiments on several datasets show that our proposed method reduces redundant point pair features and achieves better compromise of speed vs accuracy. |
| first_indexed | 2024-12-17T23:46:22Z |
| format | Article |
| id | doaj.art-49c054bd665c46dfb79fb44fd37d979a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T23:46:22Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-49c054bd665c46dfb79fb44fd37d979a2022-12-21T21:28:19ZengIEEEIEEE Access2169-35362020-01-018443354434510.1109/ACCESS.2020.297825590240523D Object Recognition and Pose Estimation From Point Cloud Using Stably Observed Point Pair FeatureDeping Li0https://orcid.org/0000-0003-4489-2517Hanyun Wang1Ning Liu2Xiaoming Wang3https://orcid.org/0000-0002-8109-3020Jin Xu4College of Information Science and Technology, Jinan University, Guangzhou, ChinaInstitute of Surveying and Mapping, Information Engineering University, Zhengzhou, ChinaCollege of Information Science and Technology, Jinan University, Guangzhou, ChinaCollege of Information Science and Technology, Jinan University, Guangzhou, ChinaCollege of Information Science and Technology, Jinan University, Guangzhou, ChinaRecognition and pose estimation from 3D free-form objects is a key step for autonomous robotic manipulation. Recently, the point pair features (PPF) voting approach has been shown to be effective for simultaneous object recognition and pose estimation. However, the global model descriptor (e.g., PPF and its variants) that contained some unnecessary point pair features decreases the recognition performance and increases computational efficiency. To address this issue, in this paper, we introduce a novel strategy for building a global model descriptor using stably observed point pairs. The stably observed point pairs are calculated from the partial view point clouds which are rendered by the virtual camera from various viewpoints. The global model descriptor is extracted from the stably observed point pairs and then stored in a hash table. Experiments on several datasets show that our proposed method reduces redundant point pair features and achieves better compromise of speed vs accuracy.https://ieeexplore.ieee.org/document/9024052/3D object recognition3D pose estimationpoint cloudpoint pair feature |
| spellingShingle | Deping Li Hanyun Wang Ning Liu Xiaoming Wang Jin Xu 3D Object Recognition and Pose Estimation From Point Cloud Using Stably Observed Point Pair Feature IEEE Access 3D object recognition 3D pose estimation point cloud point pair feature |
| title | 3D Object Recognition and Pose Estimation From Point Cloud Using Stably Observed Point Pair Feature |
| title_full | 3D Object Recognition and Pose Estimation From Point Cloud Using Stably Observed Point Pair Feature |
| title_fullStr | 3D Object Recognition and Pose Estimation From Point Cloud Using Stably Observed Point Pair Feature |
| title_full_unstemmed | 3D Object Recognition and Pose Estimation From Point Cloud Using Stably Observed Point Pair Feature |
| title_short | 3D Object Recognition and Pose Estimation From Point Cloud Using Stably Observed Point Pair Feature |
| title_sort | 3d object recognition and pose estimation from point cloud using stably observed point pair feature |
| topic | 3D object recognition 3D pose estimation point cloud point pair feature |
| url | https://ieeexplore.ieee.org/document/9024052/ |
| work_keys_str_mv | AT depingli 3dobjectrecognitionandposeestimationfrompointcloudusingstablyobservedpointpairfeature AT hanyunwang 3dobjectrecognitionandposeestimationfrompointcloudusingstablyobservedpointpairfeature AT ningliu 3dobjectrecognitionandposeestimationfrompointcloudusingstablyobservedpointpairfeature AT xiaomingwang 3dobjectrecognitionandposeestimationfrompointcloudusingstablyobservedpointpairfeature AT jinxu 3dobjectrecognitionandposeestimationfrompointcloudusingstablyobservedpointpairfeature |