Data fusion in 3D vision using a RGB-D data via switching observation model and its application to people tracking
In this paper, we propose a new method for 3D people tracking with RGB-D observations. The proposed method fuses RGB and depth data via a switching observation model. Specifically, the proposed switching observation model intelligently exploits both final detection results and raw signal intensity i...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
IEEE
2013
|
| Online Access: | http://hdl.handle.net/20.500.11937/45983 |
| _version_ | 1848757434676412416 |
|---|---|
| author | Kim, D. Vo, Ba Tuong Vo, Ba-Ngu |
| author2 | N/A |
| author_facet | N/A Kim, D. Vo, Ba Tuong Vo, Ba-Ngu |
| author_sort | Kim, D. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | In this paper, we propose a new method for 3D people tracking with RGB-D observations. The proposed method fuses RGB and depth data via a switching observation model. Specifically, the proposed switching observation model intelligently exploits both final detection results and raw signal intensity in a complementary manner in order to cope with missing detections. In real-world applications, the detector response to RGB data is frequently missing. When this occurs the proposed algorithm exploits the raw depth signal intensity. The fusion of detection result and raw signal intensity is integrated with the tracking task in a principled manner via the Bayesian paradigm and labeled random finite set (RFS). Our case study shows that the proposed method can reliably track people in a recently published 3D indoor data set. |
| first_indexed | 2025-11-14T09:28:02Z |
| format | Conference Paper |
| id | curtin-20.500.11937-45983 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T09:28:02Z |
| publishDate | 2013 |
| publisher | IEEE |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-459832017-09-13T15:05:24Z Data fusion in 3D vision using a RGB-D data via switching observation model and its application to people tracking Kim, D. Vo, Ba Tuong Vo, Ba-Ngu N/A In this paper, we propose a new method for 3D people tracking with RGB-D observations. The proposed method fuses RGB and depth data via a switching observation model. Specifically, the proposed switching observation model intelligently exploits both final detection results and raw signal intensity in a complementary manner in order to cope with missing detections. In real-world applications, the detector response to RGB data is frequently missing. When this occurs the proposed algorithm exploits the raw depth signal intensity. The fusion of detection result and raw signal intensity is integrated with the tracking task in a principled manner via the Bayesian paradigm and labeled random finite set (RFS). Our case study shows that the proposed method can reliably track people in a recently published 3D indoor data set. 2013 Conference Paper http://hdl.handle.net/20.500.11937/45983 10.1109/ICCAIS.2013.6720536 IEEE restricted |
| spellingShingle | Kim, D. Vo, Ba Tuong Vo, Ba-Ngu Data fusion in 3D vision using a RGB-D data via switching observation model and its application to people tracking |
| title | Data fusion in 3D vision using a RGB-D data via switching observation model and its application to people tracking |
| title_full | Data fusion in 3D vision using a RGB-D data via switching observation model and its application to people tracking |
| title_fullStr | Data fusion in 3D vision using a RGB-D data via switching observation model and its application to people tracking |
| title_full_unstemmed | Data fusion in 3D vision using a RGB-D data via switching observation model and its application to people tracking |
| title_short | Data fusion in 3D vision using a RGB-D data via switching observation model and its application to people tracking |
| title_sort | data fusion in 3d vision using a rgb-d data via switching observation model and its application to people tracking |
| url | http://hdl.handle.net/20.500.11937/45983 |