Keypoint-Less, Heuristic Application of Local 3D Descriptors
One of the most important topics in the research concerning 3D local descriptors is computational efficiency. The state-of-the-art approach addressing this matter consists in using keypoint detectors that effectively limit the number of points for which the descriptors are computed. However, the cho...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2017-09-01
|
| Series: | Foundations of Computing and Decision Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/fcds-2017-0012 |
| _version_ | 1811321159806877696 |
|---|---|
| author | Harasymowicz-Boggio Bogdan Chechliński Łukasz |
| author_facet | Harasymowicz-Boggio Bogdan Chechliński Łukasz |
| author_sort | Harasymowicz-Boggio Bogdan |
| collection | DOAJ |
| description | One of the most important topics in the research concerning 3D local descriptors is computational efficiency. The state-of-the-art approach addressing this matter consists in using keypoint detectors that effectively limit the number of points for which the descriptors are computed. However, the choice of keypoints is not trivial and might have negative implications, such as the omission of relevant areas. Instead, focusing on the task of single object detection, we propose a keypoint-less approach to attention focusing in which the full scene is processed in a hierarchical manner: weaker, less rejective and faster classification methods are used as heuristics for increasingly robust descriptors, which allows to use more demanding algorithms at the top level of the hierarchy. We have developed a massively-parallel, open source object recognition framework, which we use to explore the proposed method on demanding, realistic indoor scenes, applying the full power available in modern computers. |
| first_indexed | 2024-04-13T13:13:08Z |
| format | Article |
| id | doaj.art-9d3d2d1f092b4dcfbe45efa51c9455e3 |
| institution | Directory Open Access Journal |
| issn | 2300-3405 |
| language | English |
| last_indexed | 2024-04-13T13:13:08Z |
| publishDate | 2017-09-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Foundations of Computing and Decision Sciences |
| spelling | doaj.art-9d3d2d1f092b4dcfbe45efa51c9455e32022-12-22T02:45:34ZengSciendoFoundations of Computing and Decision Sciences2300-34052017-09-0142323925510.1515/fcds-2017-0012fcds-2017-0012Keypoint-Less, Heuristic Application of Local 3D DescriptorsHarasymowicz-Boggio Bogdan0Chechliński Łukasz1Faculty of Mechatronics, Warsaw University of Technology, Warsaw, PolandFaculty of Mechatronics, Warsaw University of Technology, Warsaw, PolandOne of the most important topics in the research concerning 3D local descriptors is computational efficiency. The state-of-the-art approach addressing this matter consists in using keypoint detectors that effectively limit the number of points for which the descriptors are computed. However, the choice of keypoints is not trivial and might have negative implications, such as the omission of relevant areas. Instead, focusing on the task of single object detection, we propose a keypoint-less approach to attention focusing in which the full scene is processed in a hierarchical manner: weaker, less rejective and faster classification methods are used as heuristics for increasingly robust descriptors, which allows to use more demanding algorithms at the top level of the hierarchy. We have developed a massively-parallel, open source object recognition framework, which we use to explore the proposed method on demanding, realistic indoor scenes, applying the full power available in modern computers.https://doi.org/10.1515/fcds-2017-0012rgbdobject detection3d descriptorskeypointless |
| spellingShingle | Harasymowicz-Boggio Bogdan Chechliński Łukasz Keypoint-Less, Heuristic Application of Local 3D Descriptors Foundations of Computing and Decision Sciences rgbd object detection 3d descriptors keypointless |
| title | Keypoint-Less, Heuristic Application of Local 3D Descriptors |
| title_full | Keypoint-Less, Heuristic Application of Local 3D Descriptors |
| title_fullStr | Keypoint-Less, Heuristic Application of Local 3D Descriptors |
| title_full_unstemmed | Keypoint-Less, Heuristic Application of Local 3D Descriptors |
| title_short | Keypoint-Less, Heuristic Application of Local 3D Descriptors |
| title_sort | keypoint less heuristic application of local 3d descriptors |
| topic | rgbd object detection 3d descriptors keypointless |
| url | https://doi.org/10.1515/fcds-2017-0012 |
| work_keys_str_mv | AT harasymowiczboggiobogdan keypointlessheuristicapplicationoflocal3ddescriptors AT chechlinskiłukasz keypointlessheuristicapplicationoflocal3ddescriptors |