...
首页> 外文期刊>Journal of Residuals Science & Technology >Binocular Stereo Matching Algorithm Based on Deep Learning
【24h】

Binocular Stereo Matching Algorithm Based on Deep Learning

机译:基于深度学习的双目立体匹配算法

获取原文
           

摘要

In view of low precision combination of using binocular stereo local matching algorithm to calculate deep area, binocular stereo matching calculation method based on the advantages of integrated binocular and binocular local matching. The two-dimensional binocular stereo matching algorithm was not efficient, so a one-dimensional dynamic binocular stereo matching algorithm was designed. In order to solve the problem that the Potts dynamic global planning was not rigorous, one-dimensional differential dynamic matching was designed. The planning scheme was applied to the graph, which led to the difference of the visual contrast of the stereo matching.Through the comparison and analysis of the experimental results with other algorithms, the computational efficiency of this method was higher and the combination of practical application was better. Combined with the Matlab calibration, the calculating method was used for the real-time graphics proofreading, and binocular vision difference met the desired research goals.
机译:鉴于使用双目立体局部匹配算法来计算深度区域的精度低下,结合了双目和双目局部匹配的优点,双目立体匹配计算方法。二维双目立体匹配算法效率不高,因此设计了一种一维动态双目立体匹配算法。为了解决Potts动态全局规划不严格的问题,设计了一维差分动态匹配方法。图中采用了规划方案,导致立体匹配的视觉对比度有所不同。通过与其他算法的实验结果对比分析,该方法的计算效率较高,结合实际应用更好。结合Matlab标定,该计算方法用于实时图形校对,双目视差达到了预期的研究目标。

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