This shows you the differences between two versions of the page.

Link to this comparison view

seminars:seminar_02_24_09 [2017/09/20 22:02] (current)
Line 1: Line 1:
 +======Real-time Stereo Vision Using the GPU======
 +Tuesday February 24, 2009\\
 +Hamerschlag Hall D-210\\
 +4:00 pm\\
 +[[http://​www.ece.cmu.edu/​~http://​amp.ece.cmu.edu/​people/​weiyu/​|Wei Yu]]\\
 +Carnegie Mellon University\\
 +The goal of stereo vision is to reconstruct disparity map from a stereo image pair. Most existing stereo algorithms can be classified into either local or global approaches. Generally speaking, local algorithms are computationally less expensive, while global algorithms produce a higher quality disparity map. Recent research shows that local approaches based on carefully designed cost aggregation strategies can outperform many global approaches.
 +Among local aggregation approaches, adaptive-weight window produces the best quality disparity map under real-time constraints but is relatively slower. ​ We propose a fast adaptive-weight aggregation method based on exponential step information propagation. The idea is to propagate information from long distance pixels within a few iterations.
 +In this talk, I will also present efficient implementation techniques on a GPU platform, which achieve 10.5x speed up over a straightforward implementation. ​ Experimental results show that our technique is Pareto-optimal among existing real-time or near real-time stereo algorithms along the accuracy-speed trade-off space.
 +Wei Yu is a third year PhD student at Carnegie Mellon (ECE), advised by James C. Hoe and Tsuhan Chen.  Her research interests include acceleration of visual computing on multi-core platforms.
 +**[[seminars:​Seminars | Back to the seminar page]]**