A Full Density Stereo Matching System Based on the Combination of CNNs and Slanted-Planes

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	A Full Density Stereo Matching System Based on the Combination of CNNs and Slanted-Planes
	Long Chen; Lei Fan; Jianda Chen; Dongpu Cao; Feiyue Wang
发表期刊	IEEE Transactions on Systems, Man and Cybernetics: Systems
	2017
卷号	PP 期号:99 页码:1-12
摘要	Stereo matching methods consist of matching cost computation and several post processing steps. Deep learning methods have greatly raised the accuracy of matching cost and achieved the lowest error rate on several public datasets. However, their generality capabilities are not the best due to potential overfitting, which is the common problem of supervised learning approaches. This paper proposes a convolutional neural network (CNN) based cost estimation method for computing the similarity of image patches. In consideration of accuracy and generalization capability, small size convolution kernels are chosen in the convolution layer and dropout in the decision layer is used for preventing overfitting. After obtaining stereo matching cost from the output of the CNN, several post-processing operations are adopted for disparity optimization, which includes semi-global matching in 1-D from different directions, a left-right consistency check, and the slanted plane smoothing method. The method is evaluated on KITTI 2012, KITTI 2015, and Middlebury stereo datasets and the experimental results on the KITTI benchmark demonstrate the competitive accuracy performance of the approach. Additionally, to test the generalization of the method, a series of extended crossover experiments are conducted in which the training samples and testing samples come from different datasets. The results indicate superior generalization capability of our method than other supervised learning methods.
关键词	Image Reconstruction Image Reconstruction Stereo Vision
WOS记录号	WOS:000508423900002
引用统计	被引频次：18[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/20264
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
推荐引用方式 GB/T 7714	Long Chen,Lei Fan,Jianda Chen,et al. A Full Density Stereo Matching System Based on the Combination of CNNs and Slanted-Planes[J]. IEEE Transactions on Systems, Man and Cybernetics: Systems,2017,PP(99):1-12.
APA	Long Chen,Lei Fan,Jianda Chen,Dongpu Cao,&Feiyue Wang.(2017).A Full Density Stereo Matching System Based on the Combination of CNNs and Slanted-Planes.IEEE Transactions on Systems, Man and Cybernetics: Systems,PP(99),1-12.
MLA	Long Chen,et al."A Full Density Stereo Matching System Based on the Combination of CNNs and Slanted-Planes".IEEE Transactions on Systems, Man and Cybernetics: Systems PP.99(2017):1-12.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
A Full Density Stere（3043KB）			开放获取	--	浏览下载