DocumentCode
1531130
Title
High-Frame-Rate Optical Flow System
Author
Ishii, Idaku ; Taniguchi, Taku ; Yamamoto, Kenkichi ; Takaki, Takeshi
Author_Institution
Dept. of Syst. Cybern., Hiroshima Univ., Hiroshima, Japan
Volume
22
Issue
1
fYear
2012
Firstpage
105
Lastpage
112
Abstract
In this paper, we develop a high-frame-rate (HFR) vision system that can estimate the optical flow in real time at 1000 f/s for 1024×1024 pixel images via the hardware implementation of an improved optical flow detection algorithm on a high-speed vision platform. Based on the Lucas-Kanade method, we adopt an improved gradient-based algorithm that can adaptively select a pseudo-variable frame rate according to the amplitude of the estimated optical flow to accurately detect the optical flow for objects moving at high and low speeds in the same image. The performance of our developed HFR optical flow system was verified through experimental results for high-speed movements such as a top´s spinnning motion and a human´s pitching motion.
Keywords
image sequences; motion estimation; object detection; HFR optical flow system; HFR vision system; Lucas-Kanade method; gradient-based algorithm; high-frame-rate optical flow system; high-speed vision platform; optical flow detection algorithm; optical flow estimation; optical flow object detection; pseudo-variable frame rate; Adaptive optics; Estimation; Hardware; High speed optical techniques; Optical imaging; Optical sensors; Pixel; Gradient-based algorithm; hardware implementation; high-frame-rate vision; motion estimation;
fLanguage
English
Journal_Title
Circuits and Systems for Video Technology, IEEE Transactions on
Publisher
ieee
ISSN
1051-8215
Type
jour
DOI
10.1109/TCSVT.2011.2158340
Filename
5782945
Link To Document