DocumentCode :
300578
Title :
Estimating image motion from smear: a sensor system and extensions
Author :
Chen, Wei-ge ; Nandhakumar, N. ; Martin, Worthy N.
Author_Institution :
Microsoft Corp., Redmond, WA, USA
Volume :
1
fYear :
1995
fDate :
23-26 Oct 1995
Firstpage :
199
Abstract :
Image motion estimation usually relies on using interframe displacement as the information cue for motion. Another cue has been proposed, namely motion smear. An algorithm used to compute the image motion from the smear information (“motion-from-smear”) was proposed by Chen, Nandhakumar and Martin (see Proc. IEEE Intern. Conf. Image Proc., vol.III, p.761-765, Austin, Texas, November 1994) where the algorithm was verified with simulated motion smeared images. This paper extends the work of Chen et al. by presenting (1) experimental results on real data, (2) a feasible sensor design and (3) a generalization to space-varying motion
Keywords :
array signal processing; image sequences; motion estimation; algorithm; experimental results; image motion estimation; information cue; interframe displacement; motion from smear; motion smear; sensor design; sensor system; simulated motion smeared images; smear information; space-varying motion; Computational modeling; Computer science; Computer vision; Humans; Machine vision; Motion estimation; Pixel; Psychology; Sensor systems; Video compression;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing, 1995. Proceedings., International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-8186-7310-9
Type :
conf
DOI :
10.1109/ICIP.1995.529580
Filename :
529580
Link To Document :
بازگشت