期刊文献+

一种改进AD代价的立体匹配算法

下载PDF
导出
摘要 本文提出了一种基于改进AD-Census的立体匹配算法,旨在获得最优匹配代价,引入机器学习训练特征思想和数据分析思想,以此获取最优代价对应的匹配效果。对于AD代价函数,引入了动态参数,便于动态调参。用基本单位化操作和异化操作调整AD代价函数结构,用于更密的代价集合,且便于配合最优动态参数获取最优代价。考虑到AD匹配代价的不足之处,将新改进后的AD代价和Census代价进行代价融合,得到最优AD代价。最优AD代价匹配算法的实验结果表明,匹配精度更高,鲁棒性更好。实验应用Middlebury数据集,平均误匹率相较于AD-Census算法整体平均提高了3.9002%。
作者 李文泽
机构地区 哈尔滨工程大学
出处 《数字技术与应用》 2023年第7期11-14,17,共5页 Digital Technology & Application
  • 相关文献

参考文献3

二级参考文献29

  • 1章国峰,姜翰青,鲍虎军.基于图像的深度计算[J].中国计算机学会通讯,2012,78(8):29-37.
  • 2Scharstein D,Szeliski R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J].Int Journal of Computer Vision,2002,47(1/2/3):7-42.
  • 3Boykov Y,Veksler O,Zabih R.Fast approximate energy minimization via graph cuts[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2001,23(11):1222-1239.
  • 4Yang Q,Wang L,Yang R,et al.Stereo matching with colorweighted correlation,hierarchical belief propagation and occlusion handling[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2008,31(3):492-504.
  • 5Yoon K J,Kweon I S.Adaptive support-weight approach for correspondence search[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2006,28(4):650-656.
  • 6Zhang K,Lu J,Lafruit G.Cross-based local stereo matching using orthogonal integral images[J].IEEE Trans on Circuits and Systems for Video Technology,2009,19(7):1073-1079.
  • 7Gong M,Yang R,Wang L,et al.A performance study on different cost aggregation approaches used in real-time stereo matching[J].Int Journal of Computer Vision,2007,75(2):283-296.
  • 8Yu W,Chen T,Franchetti F,et al.High performance stereo vision designed for massively data parallel platforms[J].IEEE Trans on Circuits and Systems for Video Technology,2010,20(11):1509-1519.
  • 9Zhang K,Lu J,Yang Q,et al.Real-time and accurate stereo:a scalable approach with bitwise fast voting on CUDA[J].IEEE Trans on Circuits and Systems for Video Technology,2011,21(7):867-878.
  • 10Kowalczuk J,Psota E T,Perez L C.Real-time stereo matching on CUDA using an iterative refinement method for adaptive support-weight correspondences[J].IEEE Trans on Circuits and Systems for Video Technology,2013,23(1):94-104.

共引文献11

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部