立体匹配是视觉算法的核心。
立体匹配是双目视觉系统最困难的环节。
Stereo matching is the most difficult link within a binocular vision system.
立体匹配是立体视觉研究中的关键部分。
适合普通数码近景影像的立体匹配技术方法。
Image stereo-matching method designed for normal close-digital imagery.
基于特征的立体匹配算法，可以固化到芯片上。
Stereo matching algorithm based on feature and can be used in DSP AND ARM etc.
探索了基于线特征的点特征立体匹配的间接方法。
Indirect method of point stereo matching based on line feature is explored.
提出了一种基于邻域差值的非参数变换立体匹配方法。
A new Non-parametric transform for stereo matching was proposed.
提出一种基于地面控制点的迭代动态规划立体匹配算法。
A ground control point based stereo matching algorithm via iterative dynamic programming is proposed.
提出一种基于控制点的分层双向动态规划立体匹配算法。
A stereo matching algorithm based on control points is proposed for layered and bidirectional dynamic programming.
其次，分析了立体匹配中的主要约束及相似性判断准则。
Secondly, we analysis the main constraints and similarity criteria used in stereo matching.
研究并实现了一种基于双目视觉的人脸立体匹配计算方法。
A method for face stereo matching and disparity calculating in binocular vision system is proposed in this paper.
第四章主要介绍了视觉里程计在宽基线立体匹配中的应用。
Chapter IV introduces the application of visual odometry in wide baseline stereo matching.
实现了分水岭图像分割算法，并将该算法应用到立体匹配中。
The paper realizes the watershed image division algorithm, and applies this algorithm to stereo matching.
图割算法是图像立体匹配算法中一种高效的最优化计算方法。
The graph cut algorithm is one of high effective optimal methods in the stereo images matching.
视频目标分割与立体匹配是目标基立体视频编码中的核心技术。
Video object segmentation and stereo correspondence is a key technology in object-based stereo video coding.
系统中融合了基于区域的立体匹配原理，检出的特征定位准确。
The principles of area based matching, epipolar constraint, edge strength and orientation constraints were introduced into the corresponding process.
立体匹配是计算机视觉领域的一个关键问题，同时也是难点问题。
The stereo matching is a key problem of computer vision, and also is the difficult problem.
提出了一种利用遗传算法解决立体匹配问题的方法以获得稠密的视差图。
An approach to addressing the stereo correspondence problem is presented using genetic algorithms (GAs) to obtain a dense disparity map.
在立体匹配过程中，边界问题和遮挡问题一直影响着立体匹配的准确程度。
In stereo matching, the edge problem and the occluded areas problem always affect the accuracy of the disparity image.
基于灰度的数字图像立体匹配算法的中心问题是选择一个适当尺寸的窗口。
A central problem in stereo matching by computing correlation or sum of squared differences (SSD) lies in selecting an appropriate window size.
本文研究结合多基线立体匹配算法采用II直接获取物体空间信息的方法。
This paper introduced the technology of II and presented a method of extracting depth information directly from lenticular II images with a modified-multiple-baseline algorithm.
实验结果表明，该算法具有较高的匹配正确率，是一种有效的立体匹配算法。
Experimental results show that the proposed algorithm has the high probability of correct matching.
为了获取精确的立体匹配结果，提出了一种通用的视差图误差检测与校正算法。
General error detection and correction algorithm for disparity maps is developed to provide precise stereo matching results.
本论文从三个方面总结了立体匹配的方法，即基元选择、匹配准则和算法结构。
This paper concludes the stereo matching methods from some aspects such as primitive factor selection, matching rules and algorithm organization.
首先以双目平行立体视觉系统为例，分析了立体匹配基本原理及常用的约束条件。
Firstly, analyzed the rationale and constraints used in a binocular parallel stereo vision system.
在立体匹配部分，重点研究了区域相关匹配和基于特征的匹配两种类型的匹配算法。
In stereo matching, this paper studied two algorithms, one is area-based matching algorithm, the other is feature-based matching algorithm.
本文对双目视觉目标定位所涉及的摄像机标定、特征提取及立体匹配等关键技术进行研究。
In this thesis, the key technologies such as camera calibration, feature extraction and stereo matching involved in binocular vision were studied.
为了得到准确、稠密的视差图，提出了一种利用自适应能量聚集和动态规划的立体匹配算法。
In order to get precise and dense disparity maps, a stereo matching algorithm using adaptive cost aggregation and dynamic programming is proposed.
为了得到准确、稠密的视差图，提出了一种利用自适应能量聚集和动态规划的立体匹配算法。
In order to get precise and dense disparity maps, a stereo matching algorithm using adaptive cost aggregation and dynamic programming is proposed.
应用推荐