搜索资源列表
FastStereoMatchingUsingRectangularSubregioningand3
- 本文提出了一种快速，可靠的立体匹配算法产生浓密视差图，通过使用快速互相关、矩形秩和3D最大表面技术粗到细计划。-This paper presents a fast and reliable stereo matching algorithm which produces a dense disparity map by using fast cross correlation, rectangular subregioning (RSR) and 3D maximum-surfac
3d-matching
- 提出了一种用于物体外形非接触式提取的综合立体匹配方法。该方法综合了基于面积的立体匹配过程和基于特征的立体匹配过程。能充分利用它们各自的优点。 既能产生致密视差图。又能获得不连续处的准确匹配。 解决了物体外形非接触式提取中的关键性的问题实验结果以及实际应用都收到了很好的效果。-Proposed for object shape extraction of non-contact integrated stereo matching method. This method is an integra
Study-on-Iterative-Depth-Estimation-for-Multi-vie
- The increasing availability of 3D displays, such as 3D monitors, 3D TVs and 3D cinema, is raising consumer demand for stereo content [1-3]. Most 3D displays use the difference in viewpoint between the viewer s eyes to produce a stereosco
Robot(OpenNIPKinect)
- 我们把Kinect相机作为3D测量设备来分析，试验性的研究深度测量分辨率和错误属性，并将Kinect与SLP相机和一个3D-TOF相机就立体重建的准确性做定量比较。我们提出了Kinect几何模型、Kinect相机的标定步骤和Kinect 3D测量的准确标定流程。我们展示了Kinect标定的功能-通过将它融入到一条SfM Pipeline中，在这里从动态的Kinect相机获得的3D测量数据通过计算彩色相机中与之相匹配的位姿被变换到普通坐标系。 -We put the Kinect came
Model-based-3D-Motion
- 为解决非刚体运动分析中模型精度和计算复杂度之间的平衡问题,该文提出了一种基 于圆锥曲线模型的弹性连接体(人体)三维运动估计方法。建立了人体三维模型,根据双目图 像序列进行基于该模型的人肢体三维变形和运动参数估计,采用圆锥曲线三维模型及其在图像 平面上投影的联系方程估计三维运动参数。人手臂运动估计实验结果表明该运动估计算法能 够正确估计人体运动参数。-To offer a good tradeoff between computational complexity and mode
FACE3D-Series
- Abstract—Recently, a 3D face recognition approach based on geometric invariant signatures, has been proposed. The key idea of the algorithm is a representation of the facial surface, invariant to isometric deformations, such as those result
artp3A10.1007p2Fs00371-014-1009-3
- 3D entity-based stereo matching with ground control points and joint second-order smoothness prior
3d-MATCH
- 关于立体匹配很好的一篇论文，讲述了立体匹配的四个主要方向，配有详细的算法描述-Stereo matching on good paper, tells the story of four main directions of stereo matching, with a detailed descr iption of the algorithm