Abstract
Obtaining 3D scene flow from sequential images captured by fisheye camera is still challenging to be developed according to today's broad applications. In this research, we focus on generating 3D scene flow directly from sequential fisheye images captured by a binocular stereo camera setup. We adopt Lucas and Kanade's approach to calculate optical flow and stereo image disparity for obtaining the scene flow. The result shows that this method is very promising to produce the 3D motion vectors with respect to certain criteria of captured object movement.
Original language | English |
---|---|
Title of host publication | 2018 International Workshop on Advanced Image Technology, IWAIT 2018 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 1-4 |
Number of pages | 4 |
ISBN (Electronic) | 9781538626153 |
DOIs | |
Publication status | Published - 2018 May 30 |
Event | 2018 International Workshop on Advanced Image Technology, IWAIT 2018 - Chiang Mai, Thailand Duration: 2018 Jan 7 → 2018 Jan 9 |
Other
Other | 2018 International Workshop on Advanced Image Technology, IWAIT 2018 |
---|---|
Country | Thailand |
City | Chiang Mai |
Period | 18/1/7 → 18/1/9 |
Keywords
- disparity
- fisheye
- Lucas and Kanade
- optical flow
- scene flow
- stereo
ASJC Scopus subject areas
- Computer Networks and Communications
- Computer Vision and Pattern Recognition
- Media Technology