6533b824fe1ef96bd128143d
RESEARCH PRODUCT
ACCURATE DENSE STEREO MATCHING FOR ROAD SCENES
Cédric DemonceauxMohammed RzizaOussama ZeglaziAouatif Aminesubject
Computer sciencebusiness.industry[ INFO.INFO-RB ] Computer Science [cs]/Robotics [cs.RO][INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO]0211 other engineering and technologiesStereo matchingCross Comparison Census02 engineering and technologyStereo visionCross based aggregationStereopsisCensus TransformRobustness (computer science)0202 electrical engineering electronic engineering information engineeringRadiometry[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]020201 artificial intelligence & image processingComputer visionArtificial intelligencebusiness021101 geological & geomatics engineeringdescription
International audience; Stereo matching task is the core of applications linked to the intelligent vehicles. In this paper, we present a new variant function of the Census Transform (CT) which is more robust against radiometric changes in real road scenes. We demonstrate that the proposed cost function outperforms the conventional cost functions using the KITTI benchmark. The cost aggregation method is also updated for taking into account the edge information. This enables to improve significantly the aggregated costs especially within homogenous regions. The Winner-Takes-All (WTA) strategy is used to compute disparity values. To further eliminate the remainder matching ambiguities , a post-processing step is performed. Experiments were conducted on the new Middlebury 2 dataset, as well as on the real road traffic scenes of the KITTI database. Obtained disparity results have demonstrated that the proposed method is promising.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2017-09-17 |