Hardware feasibility analysis for motion segmentation initialization
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Hardware feasibility analysis for motion segmentation initialization. / Tripathi, Subarna; Youngbae Hwang, Y.; Sung-Joon, Jang; Belongie, Serge; Truong, Nguyen.
In: ISOCC 2014 - International SoC Design Conference, 16.04.2015, p. 148-149.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Hardware feasibility analysis for motion segmentation initialization
AU - Tripathi, Subarna
AU - Youngbae Hwang, Y.
AU - Sung-Joon, Jang
AU - Belongie, Serge
AU - Truong, Nguyen
N1 - Publisher Copyright: © 2014 IEEE.
PY - 2015/4/16
Y1 - 2015/4/16
N2 - We analyze and evaluate different initialization methods for motion layers segmentation, a powerful mid-level vision tool. We estimate 6-D affine motion models from the optical flow corresponding to different over-segmentations. Over-segmentations can be either uniform rectangular blocks; or adaptive sized rectangular blocks; or super-pixels; or based on any other clustering methods. We present performance analysis of motion segmentation initialization algorithms on video sequences and discuss the relative pros and cons of these methods in terms of hardware implementation issues.
AB - We analyze and evaluate different initialization methods for motion layers segmentation, a powerful mid-level vision tool. We estimate 6-D affine motion models from the optical flow corresponding to different over-segmentations. Over-segmentations can be either uniform rectangular blocks; or adaptive sized rectangular blocks; or super-pixels; or based on any other clustering methods. We present performance analysis of motion segmentation initialization algorithms on video sequences and discuss the relative pros and cons of these methods in terms of hardware implementation issues.
KW - affine motion
KW - layered representation
KW - optical flow
KW - superpixel
KW - video segmentation
UR - http://www.scopus.com/inward/record.url?scp=84929428392&partnerID=8YFLogxK
U2 - 10.1109/ISOCC.2014.7087670
DO - 10.1109/ISOCC.2014.7087670
M3 - Conference article
AN - SCOPUS:84929428392
SP - 148
EP - 149
JO - ISOCC 2014 - International SoC Design Conference
JF - ISOCC 2014 - International SoC Design Conference
T2 - 11th International SoC Design Conference, ISOCC 2014
Y2 - 3 November 2014 through 6 November 2014
ER -
ID: 301829472