检索结果-南通市图书馆

Hybrid tree guided PatchMatch and quantizing acceleration for multiple views disparity estimation

在线全文

学校读者我要写书评

暂无评论

中国体视学与图像分析 2021年第1期26卷 47-61页

作者：张吉光徐士彪张晓鹏 National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijingChina

Existing stereo matching methods cannot guarantee both the computational accuracy and efficiency for ihe disparity estimation of large-scale or multi-view *** tree method can obtain a disparity estimation fast with relatively low accuracy,while PatchMatch can give high-precision disparity value with relatively high computational *** this work,we propose the Hybrid Tree Guided PatchMatch which can calculate the disparity fast and ***,an initial disparity map is estimated by employing hybrid tree cost aggregation,which is used to constrain the label searching range of the ***,a reliable normal searching range for each current normal vector defined on the initial disparity map is calculated to refine the ***,an effective quantizing acceleration strategy is designed to decrease the matching computational cost of continuous *** results demonstrate that the disparity estimation based on our algorithm is better in binocular image benchmarks such as Middlebury and *** also provide the disparity estimation results for multi-view stereo in real scenes.

关键词： stereo matching multiple views disparity estimation hybrid tree PatchMatch

A Multi-Correlation Stereo Matching Network for disparity estimation

在线全文

学校读者我要写书评

暂无评论

A Multi-Correlation Stereo Matching Network for Disparity Es...

A Stereo Matching Algorithm Based on Four-Moded Census and Relative Confidence Plane Fitting

第40届中国控制会议

作者： Jianqiang Mei Shengxiao Guan College of Information Sciences and Technology University of Science and Technology of China

Recent Convolutional Neural Networks（CNNs） based networks for disparity estimation has a better performance in both prediction accuracy and time efficiency compared with traditional hand-crafted feature based methods. However, to achieve SOTA accuracy, CNN models tend to require a large amount of memory and computing resources, especially for those networks with 3D convolution. Hence we propose a compact and effective 2D convolution based network for disparity estimation, called MCSMNet, which has three main features:1) It introduces the basic units of ShuffleNet[1] and SENet[2] to make the training of network more effective without reducing network parameters;2)It contains Multi-Correlation so that the context information could be fused in high-level features well;3)It uses hierarchical refinement strategy to further improve the accuracy of *** conduct experiments to demonstrate the effectiveness of MCSMNet on the popular datasets, Scene Flow. Experimental results show that MCSMNet achieves competitive accuracy compared with existing 3D convolution based networks.

关键词： Computer Vision disparity estimation Convolutional Neural Networks Stereo Matching

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2015年第4期24卷 807-812页

作者： MEN Yubo ZHANG Guoyin MEN Chaoguang LI Xiang MA Ning Collage of Computer Science and Technology Harbin Engineering University Harbin Commercial University

A four-moded Census transform stereo matching algorithm using bidirectional constraint dynamic programming and relative confidence plane fitting is proposed to solve the problems of matching quality. Using the four-moded Census transform which adds a restrictive condition replaces traditional Census transform to improve matching accuracy and mean value of all pixels intensity replaces the center pixel intensity in the Census window to solve the problem of the center pixel distortion effectively,a refined initial local matching cost can be obtained. During the disparity optimization, the difficulty of disparity computation in textureless areas is overcome by the estimated condition and defined relative confident pixels. Experiment results show that a better dense matching map can be obtained by the proposed algorithm.

关键词： Stereo matching disparity estimation Census transform Plane fitting

Fast view prediction for stereo images based on Delaunay triangular mesh model

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2009年第1期20卷 32-40页

作者： Guo Dabo Lu Zhaoyang Jiao Weidong State Key Laboratory of Integrated Service Networks Xidian Univ. Xi'an 710071 P. R. China Coll. of Physics & Electronics Engineering Shanxi Univ. Taiyuan 030006 P. R. China

The view prediction is an important step in stereo/multiview video coding, wherein, disparity estil mation （DE） is a key and difficult operation. DE algorithms usually require enormous computing power. A fast DE algorithm based on Delaunay triangulation （DT） is proposed. First, a flexible and content adaptive DT mesh is established on a target frame by an iterative split-merge algorithm. Second, DE on DT nodes are performed in a three-stage algorithm, which gives the majority of nodes a good estimate of the disparity vectors （DV）, by removing unreliable nodes due to occlusion, and forcing the minority of ＇problematic nodes＇ to be searched again, within their umbrella-shaped polygon, to the best. Finally, the target view is predicted by using affine transformation. Experimental results show that the proposed algorithm can give a satisfactory DE with less computational cost.

关键词： image reconstruction disparity estimation view prediction triangular mesh.

A fast stereoscopic video coding algorithm based on JMVM

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2011年第6期54卷 1218-1226页

作者： DENG ZhiPin 1,2 , JIA KeBin 1 , CHAN YuiLam 2 , FU ChangHong 2 & SIU WanChi 2 1 Department of Electronic Information & Control Engineering, Beijing University of Technology, Beijing 100124, China 2 Department of Electronic Information Engineering, Hong Kong Polytechnic University, Hong Kong, China Department of Electronic Information & Control Engineering Beijing University of Technology Beijing China Department of Electronic Information Engineering Hong Kong Polytechnic University Hong Kong China

In order to exploit the intra-view and inter-view dependencies in stereo video coding, a fast joint motion and disparity estimation algorithm is proposed in this paper. An efficient search strategy based on the motion-disparity constraint is developed, in which both the motion and disparity vectors can be obtained simultaneously with low complexity. Moreover, a credible initial predictive vector set is designed with the aid of the temporal and spatial neighboring blocks so that the coding efficiency can be further enhanced. The experimental results demonstrate that the proposed algorithm can reduce more than 96% coding time compared with the JMVM full search with a negligible quality drop.

关键词： H.264 stereoscopic video coding disparity estimation motion estimation

Intermediate view synthesis from stereoscopic images

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2005年第2期16卷 279-283页

作者： LüChaohui AnPing ZhangZhaoyang SchoolofInformationEngineering CommunicationUniversityofChinaBeijing100024P.R.China SchoolofCommunicationandInformationEngineering ShanghaiUniversityShanghai200072P.R.China

A new method is proposed for synthesizing intermediate views from a pair of stereoscopic images. In order to synthesize high-quality intermediate views, the block matching method together with a simplified multi-window technique and dynamic programming is used in the process of disparity estimation. Then occlusion detection is performed to locate occluded regions and their disparities are compensated. After the projecton of the left-to-right and right-to-left disparities onto the intermediate image, intermediate view is synthesized considering occluded regions. Experimental results show that our synthesis method can obtain intermediate views with higher quality.

关键词： intermediate view synthesis disparity estimation dynamic programming occlusion detection.

A three-dimensional measurement method for binocular endoscopes based on deep learning

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2022年第4期23卷 653-660页

作者： Hao YU Changjiang ZHOU Wei ZHANG Liqiang WANG Qing YANG Bo YUAN State Key Laboratory of Modern Optical Instrumentation College of Optical Science and EngineeringZhejiang UniversityHangzhou310027China Research Center for Intelligent Sensing Zhejiang LabHangzhou311100China

In the practice of clinical endoscopy,the precise estimation of the lesion size is quite significant for *** this paper,we propose a three-dimensional(3D)measurement method for binocular endoscopes based on deep learning,which can overcome the poor robustness of the traditional binocular matching algorithm in texture-less areas.A simulated binocular image dataset is created from the target 3D data obtained by a 3D scanner and the binocular camera is simulated by 3D rendering software to train a disparity estimation model for 3D *** experimental results demonstrate that,compared with the traditional binocular matching algorithm,the proposed method improves the accuracy and disparity map generation speed by 48.9%and 90.5%,*** can provide more accurate and reliable lesion size and improve the efficiency of endoscopic diagnosis.

关键词： Binocular endoscope Three-dimensional measurement Deep learning disparity estimation