基于Blob算法的机器视觉系统设计与实现  

Design and Realization about A robot-Vision System Based on Blob-Algorithm

作　　者：耿瑞芳[1] 沈晋慧[1] 曹辉[1] 马永华[1] 

机构地区：[1]北京联合大学生物化学工程学院,北京100023

出　　处：《微计算机信息》2009年第1期249-250,264,共3页Control & Automation

摘　　要：本文设计了一种基于Blob分析的智能机器人视觉系统。在此基础上提出识别规则物体的方法,利用不变矩、图形的面积和周长比来识别物体的形状,并采用Blob算法求取目标物的中心坐标及其任一斜边与坐标轴之间的夹角,从而识别出规定形状的物体,实现对微小或缓慢运动的目标物的定位。系统选用VCSBC4018智能摄像机来完成场景图像的采集及量化任务,并利用其自带的嵌入式操作系统及开发平台编写相应的目标识别与定位程序。实验结果表明,该系统能满足实际项目中对目标姿态信息的需要,目标识别准确率达到100%,定位相对误差小于4%。An intelligent robot-vision system based, on Blob-Algorithm is designed. It utilizes Blob-algorithm method to recognize the center of objects with arbitrary form and the angle between axis and arbitrary hypotenuse of objects. A VCSBC-4018 intelligent camera is used to fulfill the collection and quantification of scene picture data, and an embedded-operating system and developing platform are involved to implement the corresponding target-recognition and localization program. The experiments indicated that the system can meet the requirements of system design, the target recognition accurate-rate can reach 100%, and the localization relative error is less than 5%.

关 键 词：机器视觉系统 DSP BLOB算法 目标识别与定位 

分 类 号：TP302.1[自动化与计算机技术—计算机系统结构]