全局光流场估计技术及展望  

Technology and Prospect of Global Optical Flow

作　　者：宋爽[1] 杨健[1] 王涌天[1] 

机构地区：[1]北京理工大学光电学院光电成像技术与系统教育部重点实验室,北京100081

出　　处：《计算机辅助设计与图形学学报》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)

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.

关 键 词：光流场 运动估计 光照校正 

分 类 号：TP339.1[自动化与计算机技术—计算机系统结构]