Paper Info
Title
MEMOCODE 2013 hardware/software co-design contest: Stereo matching
Abstract
The MEMOCODE 2013 design contest problem is stereo matching. Given a stereo image pair (i.e., a left image and a right image), the challenge is to infer the depth information (i.e., third dimension) for each pixel in the image utilizing belief propagation algorithm. Contestants were given a month to develop a fast and/or cost-effective system for stereo matching. From a total of eight participating teams, three winners were selected based on pure-performance and cost-adjusted-performance metrics, taking into consideration inference accuracy achieved by their design solutions. The winning teams used hierarchical belief propagation algorithm on Intel multicore systems, streaming tree-reweighted message passing (TRW-S) algorithm on Convey HC-1 FPGA platform, and tile-based belief propagation algorithm on Nvidia GTX 680 GPU platform.
Year
Venue
Keywords
2013
Formal Methods and Models for Codesign
field programmable gate arrays,hardware-software codesign,image matching,stereo image processing,HC-1 FPGA platform,Intel multicore systems,MEMOCODE 2013 hardware-software codesign contest,Nvidia GTX 680 GPU platform,belief propagation algorithm,cost-adjusted performance metrics,depth information,hierarchical belief propagation algorithm,inference accuracy,stereo image pair,stereo matching,streaming tree-reweighted message passing algorithm,tile-based belief propagation algorithm,FPGAs,GPUs,belief propagation,hardware-software codesign,multicore,stereo matching
Field
DocType
ISSN
Stereo matching,Co-design,Computer science,Inference,CONTEST,Field-programmable gate array,Theoretical computer science,Real-time computing,Pixel,Message passing,Belief propagation
Conference
1936-9492
ISBN
Citations 
PageRank 
978-1-4799-0903-2
3
0.46
References 
Authors
5
1
Name
Order
Citations
PageRank
Eriko Nurvitadhi139933.08