|
Title:
|
PSEUDO-DENSE OPTICAL FLOW BASED ON PUZZLED IMAGES |
|
Author(s):
|
Olivier Demuynck |
|
ISBN:
|
978-989-8533-52-4 |
|
Editors:
|
Katherine Blashki and Yingcai Xiao |
|
Year:
|
2016 |
|
Edition:
|
Single |
|
Keywords:
|
Image segmentation, optical flow |
|
Type:
|
Full Paper |
|
First Page:
|
165 |
|
Last Page:
|
171 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
A novel image segmenting method is proposed in this paper. This segmenting method based on region growing returns images further entitled puzzled images. Based on puzzled image, a new pseudo-dense optical flow method is presented and discussed. Additionally, an optical flow cumulative function, assisted by a Least Square based iterative error filtering method, is presented and proposed for background detection and/or 3D background estimation. |
|
|
|
|
|
|
