期刊文献+

单幅图像深度信息的提取 被引量:4

Learning depth information from monocular image
在线阅读 下载PDF
导出
摘要 视觉测距已成为机器人导航领域里一项重要的研究内容。本文提出一种基于高斯-马尔科夫随机场模型,首先通过图像采集及激光测距系统,采集大量图像及其相匹配的深度信息图,在人类视觉系统基础上,提取图像特征,通过训练完善模型,并应用于新采集图像上。结果表明,该方法可以实现单幅图像深度信息的提取。
机构地区 哈尔滨工业大学
出处 《制造业自动化》 北大核心 2010年第3期15-17,共3页 Manufacturing Automation
  • 相关文献

参考文献6

  • 1J.Michels,A.Saxena,and A.Y.Ng. High Speed Obstacle Avoidance Using Monocular Vision and Reinforcement Learning. In ICML,2005.
  • 2H.Guo and Y.Lu.Depth Detection of Targets in a Monocular Image Sequence.18th Digital Avionic Systems Conference, 1999.
  • 3G.Gini and A.Marchi.Indoor Robot Navigation with Single Camera Vision.In PRIS,2002.
  • 4E.R.Davies.Laws' texture energy in TEXTURE.In Machine vision:Theory,Algorithms,Practicalities 3th edition.2005.Pg 756-779.
  • 5Gerhard,Winkler.lmage.Analysis,Random Fields and Dynamic Monte Carlo Methods:A Mathematical Introduction. Springer-Verlag, 1995.
  • 6Ashutosh Saxena,Sung H.Chung,and Andrew Y.Ng.Leaming depth from single monocular images.In NIPS 18,2006.

同被引文献49

  • 1马莉,黄敏.一种基于多分辨率与模糊聚类技术的散焦图像分割算法[J].中国图象图形学报(A辑),2005,10(3):290-294. 被引量:5
  • 2郑芳炫;杨志强.以消失点为基础下从单张影像中估测深度[J]信息技术与应用,2006(3):229-235.
  • 3Sebastiano B,Salvatore C,Marco L C. Depth map generation by image classification[A].Bellingham:Society of Photo-Optical Instrumentation Engineers,2004.95-104.
  • 4Guo G,Zhang N,Huo L S. 2D to 3D convertion based on edge defocus and segmentation[A].Los Alamitos:IEEE Computer Society Press,2008.2181-2184.
  • 5Jung Y J,Baik A,Kim J. A novel 2D-to-3D conversion technique based on relative height-depth cue[A].Bellingham:Society of Photo-Optical Instrumentation Engineers,2009.72371U.
  • 6Saxena A,Chung S H,Ng A Y. 3D depth reconstruction from a single still image[J].{H}International Journal of Computer Vision,2008,(1):53-69.
  • 7Saxena A,Sun M,Ng A Y. Make3D:learning 3D scene structure from a single still image[J].{H}IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,(5):824-840.
  • 8Saxena A. Make3D datasets[OL].http://make3d.cs.cornell.edu/,2012.
  • 9Heitz G,Gould S,Saxena A. Cascaded classification models:combining models for holistic scene understanding[A].{H}Cambridge:The MIT Press,2008.641-648.
  • 10Li C C,Kowdle A,Saxena A. Towards holistic scene understanding:feedback enabled cascaded classification models[A].Cambridge:MITPress,2010.1351-1359.

引证文献4

二级引证文献10

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