26 October 2013 New navigation algorithm based on the entropy image
Author Affiliations +
Proceedings Volume 8921, MIPPR 2013: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications; 892109 (2013) https://doi.org/10.1117/12.2031885
Event: Eighth International Symposium on Multispectral Image Processing and Pattern Recognition, 2013, Wuhan, China
Abstract
Optical flow is a critical component of video processing applications, e.g. for tasks such as object tracking, segmentation, and navigation. In this paper, we present a novel concept entropy flow based on the visual mechanism of bee. It not only generates motion fields form real sequences but also speed up the calculation of optical flow. The introduction of entropy image has shown the information distribution for the given image, and the optical flow algorithm is utilized to get the entropy flow. Global motion estimation and an auto-selecting algorithm of assessment threshold are employed to give a motion image and then the accuracy is improved.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yi Liu, Yi Liu, Jianguo Liu, Jianguo Liu, Qian Liu, Qian Liu, } "New navigation algorithm based on the entropy image", Proc. SPIE 8921, MIPPR 2013: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 892109 (26 October 2013); doi: 10.1117/12.2031885; https://doi.org/10.1117/12.2031885
PROCEEDINGS
6 PAGES


SHARE
Back to Top