Abstract
Finding high-level semantic information from a point cloud is a challenging task, and it can be used in various applications. For instance, it is useful to compactly represent the scene structure and efficiently understand the scene context. This task is even more challenging when using a hand-held monocular visual SLAM system that outputs a noisy sparse point cloud. In order to tackle this issue, we propose an incremental primitive modeling method using both geometric and statistical analyses for such point cloud. The main idea is to select only reliably-modeled shapes by analyzing the geometric relationship between the point cloud and the estimated shapes. Besides that, a statistical evaluation is incorporated to filter wrongly-detected primitives in a noisy point cloud. As a result of this processing, our approach largely improved precision when compared with state of the art methods. We also show the impact of segmenting and representing a scene using primitives instead of a point cloud.
Original language | English |
---|---|
Title of host publication | Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018 |
Publisher | IEEE |
Pages | 955-963 |
Number of pages | 9 |
ISBN (Electronic) | 9781538648865 |
DOIs | |
Publication status | Published - 3 May 2018 |
Event | 18th IEEE Winter Conference on Applications of Computer Vision, WACV 2018 - Lake Tahoe, USA United States Duration: 12 Mar 2018 → 15 Mar 2018 |
Publication series
Name | Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018 |
---|---|
Volume | 2018-January |
Conference
Conference | 18th IEEE Winter Conference on Applications of Computer Vision, WACV 2018 |
---|---|
Country/Territory | USA United States |
City | Lake Tahoe |
Period | 12/03/18 → 15/03/18 |
Bibliographical note
Funding Information:The authors would like to thank CNPq (process 140898/2014-0and456800/2014-0), CAPES(process 88881.134246/2016-01)andtheAustrianFFGunderthe Matahariprojectnr. 859208forpartiallyfundingthis research.
Funding Information:
The authors would like to thank CNPq (process 140898/2014-0 and 456800/2014-0), CAPES (process 88881.134246/2016-01) and the Austrian FFG under the Matahari project nr. 859208 for partially funding this research.
Publisher Copyright:
© 2018 IEEE.
Funding
The authors would like to thank CNPq (process 140898/2014-0and456800/2014-0), CAPES(process 88881.134246/2016-01)andtheAustrianFFGunderthe Matahariprojectnr. 859208forpartiallyfundingthis research. The authors would like to thank CNPq (process 140898/2014-0 and 456800/2014-0), CAPES (process 88881.134246/2016-01) and the Austrian FFG under the Matahari project nr. 859208 for partially funding this research.
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Computer Science Applications