Detecting ground control points via convolutional neural network for stereo matching.

	Detecting ground control points via convolutional neural network for stereo matching.
	Cao, Donglin ; Lv, Zhihan; Li, Shaozi ; Zhong, Zhun ; Su, Songzhi
刊名	MULTIMEDIA TOOLS AND APPLICATIONS
	2017
文献子类	期刊论文
英文摘要	In this paper, we present a novel approach to detect ground control points (GCPs) for stereo matching problem. First of all, we train a convolutional neuralnetwork (CNN) on a large stereo set, and compute the matching confidence of each pixel by using the trained CNN model. Secondly, we present a groundcontrol points selection scheme according to the maximum matching confidence of each pixel. Finally, the selected GCPs are used to refine the matchingcosts, then we apply the new matching costs to perform optimization with semi-global matching algorithm for improving the final disparity maps. We evaluate our approach on the KITTI 2012 stereo benchmark dataset. Our experiments show that the proposed approach significantly improves the accuracy of disparity maps.
URL标识	查看原文
语种	英语
内容类型	期刊论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/12467]
专题	深圳先进技术研究院_数字所
作者单位	MULTIMEDIA TOOLS AND APPLICATIONS
推荐引用方式 GB/T 7714	Cao, Donglin , Lv, Zhihan, Li, Shaozi ,et al. Detecting ground control points via convolutional neural network for stereo matching.[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2017.
APA	Cao, Donglin , Lv, Zhihan, Li, Shaozi ,Zhong, Zhun ,& Su, Songzhi .(2017).Detecting ground control points via convolutional neural network for stereo matching..MULTIMEDIA TOOLS AND APPLICATIONS.
MLA	Cao, Donglin ,et al."Detecting ground control points via convolutional neural network for stereo matching.".MULTIMEDIA TOOLS AND APPLICATIONS (2017).