计算机视觉中传感器规划综述  

A Survey of Sensor Planning in Computer Vision

作　　者：孙九爱[1] 吕东辉[2] 宋安平[2] 庄天戈[1] 

机构地区：[1]上海交通大学生物医学工程系,上海200030 [2]上海大学,上海200072

出　　处：《中国图象图形学报（A辑）》2001年第11期1047-1052,共6页Journal of Image and Graphics

基　　金：中法科技合作项目A类第 87号;上海市科学发展基金资助项目(985 10 70 16);上海市高等学校发展科学基金资助项目 (99A2 4)

摘　　要：在摄影测量和目标识别等计算机视觉的应用中 ,为了提高三维定位精度 ,有必要采用传感器规划策略 ,即预先对摄像机和照明参数进行规划 ,因为这样可以更有效地完成视觉任务 .为了使人们对计算机视觉中传感器规划有一概略了解 ,首先分析了传感器和照明参数、特征检测约束、传感器和目标模型等影响传感器规划的各种因素 ;然后在总结传感器规划最近研究进展的基础上 ,根据传感器规划所使用方法等的不同 ,对传感器规划问题进行了分类 ,并将传感器规划问题归纳为组合优化的过程 ;In photogrammetry and object recognition, it's necessary to introduce the sensor planning strategies to improve the measurement accuracy. Sensor planning is a new research area in computer vision. Planning the parameters of camera and illumination purposefully can make task be performed effectively. In this paper some affecting factors which are essential to sensor planning are analyzed firstly. They are the parameters of camera and illumination, constrain of feature detectability, the models of sensor and object. After some specific sensor planning systems were summarized, the sensor planning systems are classified based on the methods they used, the goals, the number of sensors and a prior information. Then the problem of sensor planning is concluded to the optimization process which can be done in high dimensional space composed of the parameters of camera,lens, illumination and object models. Finally we show some possible developing directions , namely single camera system in active machine vision,multi camera network design solution, new optimization and combinatorial search method, rebuilding the uncertainty of characters and multi sensor data fusion.

关 键 词：传感器规划 视点 摄像机 照明参数 被动光学定位器 计算机视觉 计算机辅助外科手术 图象处理 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] R61[自动化与计算机技术—计算机科学与技术]