• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Industrial Engineering and Applications >The 3D Edge Reconstruction from 2D Image by Using Correlation Based Algorithm
【24h】

The 3D Edge Reconstruction from 2D Image by Using Correlation Based Algorithm

机译：基于相关性算法，通过2D图像从2D图像重建3D边沿重建

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In computer numerical control machine tools, using machining simulation to prevent collision have become more popular due to higher machining speed. The 3D reconstruction of objects is one of the main goals for 3D machine vision is presented in this paper. In the stereo vision, a 2D edge feature detection algorithm designed by integration of vision base image processing which can generate a new straight line on the edges of the object. The matching comparison process is solved with the Normalized Cross Correlation (NCC) to obtain the results of a new straight line matching to find disparity from distance between feature points on plane. The disparity can be obtained from two cameras by overlapped two objects that show the different positions of two objects in horizontal using the principles of geometry of two cameras. The different position results can find the coordinates of 3D (x, y, z) to be generating the straight lines on edge of the 3D objects. This method is simply and easier in the computing process for the reconstruction of the object. The results obtain are presented with an effective and accurate model and can take results input into the 3D recognition process.
机译：在计算机数控机床中，使用加工模拟来防止碰撞由于更高的加工速度而变得更加流行。本文提出了对象的3D重建是3D机器视觉的主要目标之一。在立体声视觉中，通过集成视觉基础图像处理设计的2D边缘特征检测算法，该探测基础图像处理可以在对象的边缘上产生新的直线。匹配比较过程以归一化的横相关（NCC）求解，以获得新的直线匹配的结果，以从平面上的特征点之间的距离找到视差。可以通过重叠的两个物体从两个相机从两个相机获得不同的位置，其使用两个相机的几何形状的原理显示水平中的两个物体的不同位置。不同的位置结果可以找到3D（x，y，z）的坐标，以在3D对象的边缘上生成直线。在对象重建的计算过程中简单而更容易。结果获得了有效且准确的模型，并可以将结果输入到3D识别过程中。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号