DocumentCode :
3313226
Title :
A real time motion estimation for traffic monitoring using sloped diamond search
Author :
Johri, Tony ; Bahri, Varun ; Sahu, Rajendra
Author_Institution :
ABV-IIITM Gwalior, Gwalior
fYear :
2008
fDate :
3-6 April 2008
Firstpage :
511
Lastpage :
514
Abstract :
This paper focus on fast block based motion estimation for traffic monitoring using a stationary camera. As the traffic needs to be monitored continuously a real time motion estimation algorithm is required which could provide good match as well. Most of the existing block matching algorithms fail to give good match when the speed of motion varies too much. This algorithm (RTME-SDS) overcomes this problem by estimating the initial position to be searched using the motion vector of previous frame. At this position we apply sloped diamond search. Since the traffic move along a fixed path at different speed, this algorithm gives a good initial position to continue with the estimation. RTME-SDS improves over the above mentioned algorithm by more than 45% in terms of complexity giving a match close to above mentioned algorithm.
Keywords :
cameras; image matching; motion estimation; traffic engineering computing; vectors; video signal processing; block matching algorithm; motion vector; position estimation; real time motion estimation; sloped diamond search; stationary camera; traffic monitoring; traffic video; Cameras; Condition monitoring; MPEG 4 Standard; Motion detection; Motion estimation; PSNR; Road vehicles; Video coding; Mean square error(MSE); Peak Signal to noise ratio(PSNR); motion estimation; motion vector;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Southeastcon, 2008. IEEE
Conference_Location :
Huntsville, AL
Print_ISBN :
978-1-4244-1883-1
Electronic_ISBN :
978-1-4244-1884-8
Type :
conf
DOI :
10.1109/SECON.2008.4494348
Filename :
4494348
Link To Document :
بازگشت