期刊文献+

全局光流场估计技术及展望 被引量:13

Technology and Prospect of Global Optical Flow
下载PDF
导出
摘要 光流法是运动分析最为重要的技术之一,其能够从相邻帧图像中恢复出目标物体以及背景的运动信息,从而实现目标检测、运动跟踪以及特征识别等.文中从全局光流计算的基本原理出发,详细分析了非均匀光照校正、能量函数构建和优化方案设计等全局光流场估计技术的关键步骤;同时深入探讨了全局光流场估计技术存在的大位移计算、遮挡检测、弱纹理运动估计等难题.最后对全局光流场估计技术所面临的挑战进行了分析,并展望了其未来的发展方向. Optical flow is one of the most important technologies for motion analysis, which can reconstruct the motion of objects from consecutive image frames and hence can be utilized for object detection, motion tracking and feature identification. Based on the principle of global optical flow, the main techniques are reviewed in detail from three sections: non-uniform illumination correction, energy function construction and optimization scheme design. Meanwhile, three main difficulties for global optical flow analysis are studied thoroughly, which include large displacement computation, occlusion detection and weak texture estimation. At last, challenges are summarized and prospects of this technique are made.
出处 《计算机辅助设计与图形学学报》 EI CSCD 北大核心 2014年第5期841-850,共10页 Journal of Computer-Aided Design & Computer Graphics
基金 国家"九七三"重点基础研究发展计划项目(2010CB732505) 国家"八六三"高技术研究发展计划(2013AA013703) 北京市优秀人才支持计划(2010D009011000004)
关键词 光流场 运动估计 光照校正 optical flow motion estimation illumination correction
  • 相关文献

参考文献44

  • 1Gibson J J. The perception of the visual world [M]. Oxford: Houghton Mifflin, 1950.
  • 2Negahdaripour S. Revised definition of optical flow: integration of radiometric and geometric cues for dynamic scene analysis [J]. IEEE Transactions on Pattern Analysis and Maehine Intelligence, 1998, 20(9): 961-979.
  • 3Barron J L, Fleet D J, Beauchemin S S. Performance of optical flow techniques[J] International Journal of Computer Vision, 1994, 12(1): 43-77.
  • 4Baker S, Scharstein D, Lewis J P, et al. A database and evaluation methodology for optical flow [C] //Proceedings of the llth IEEE International Conference on Computer Vision. Los Alamitos: IEEE Computer Society Press, 2007:1-8.
  • 5Baker S, Scharstein D, Lewis J P, et al. A database and evaluation methodology for optical flow [J]. International Journal of Computer Vision, 2011, 92(1) : 1-31.
  • 6Otte M, Nagel H H. Optical flow estimation: advances and comparisons [M] //Lecture Notes in Computer Science, Heidelberg: Springer, 1994, 800:49-60.
  • 7Scharstein D, Szeliski R. High-accuracy stereo depth maps using structured light [C] //Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2003, 1:195-202.
  • 8Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision [C] // Proceedings of the 7th International Joint Con{erence on Artificial Intelligence. San Francisco: Margan Kaufmann, 1981, 81:674-679.
  • 9钱东海,张建明.五点约束最小二乘法估计光流速度场[J].计算机辅助设计与图形学学报,2004,16(9):1275-1278. 被引量:5
  • 10Horn B K P, Schunck B G. Determining optical flow [J]. Artificial Intelligence, 1981, 17(1-3): 185-203.

二级参考文献6

  • 1Horn B K P, Schunck B G. Determining optic flow[J]. Artificial Intelligence, 1981, 17(8): 185~204
  • 2Heeger D J. Optical flow using spatiotemporal filters[J]. International Journal of Computer Vision, 1988, 1(4): 279~302
  • 3Fleet D J, Jepson A D. Computation of component image velocity from local phase information[J]. International Journal of Computer Vision, 1990, 5(1): 77~104
  • 4Singh A. An estimation-theoretic framework for image-flow computation[A]. In: Proceedings of the 3rd International Conference of Computer Vision, Osaka, 1990. 168~177
  • 5Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision[A]. In: Proceedings of the 7th International Joint Conference on Artificial Intelligence, Vancouver, 1981. 674~679
  • 6Barron J L, Fleet D J, Beauchemin S S. Systems and experiment: Performance of optical flow techniques[J]. International Journal of Computer Vision, 1994, 12(1): 43~77

共引文献4

同被引文献107

引证文献13

二级引证文献35

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