微动机器人视觉伺服控制系统优化  

Optimization of Micro Robot Visual Servo Control System

作　　者：苑隆寅[1] 王哲[1] 耿元芳[1] 

机构地区：[1]重庆邮电大学移通学院,重庆401520

出　　处：《实验室研究与探索》2017年第1期22-24,29,共4页Research and Exploration In Laboratory

基　　金：国家自然科学基金资助项目(90922007)

摘　　要：基于双目显微视觉伺服控制和透视成像原理,优化了双目显微视觉伺服控制模型。结果表明:设计的视觉模型不再含有深度信息,直接采用了图像信息从场景中获取视觉信息,图像特征点的误差向量在0~2 s范围内一直收敛到0;当微立方体处于焦平面上时,图中微立方体形状有微小的变化,这表示物体到摄像机的距离是有微小变化的,深度信息是变化的。设计的模型不再需要测量或估计未知点的深度信息,能够实现准确、快速地获取深度信息,实现了微动机器人视觉伺服控制系统优化。Current monocular visual servo control of a micro robot needs to know the depth of the controlled object.In order to improve the microscopic visual servo control performance,visual servo control is designed based on binocular microscope and X-ray imaging principle,the binocular microscope visual servo control is optimized.The verification results show that the design of the visual model no longer contains depth information,and applies directly to the image information from the visual information in the scene.The error of image feature point vector is in the range of 0 ~ 2 s and always converges to zero.When the cube in the focal plane figure has small change,it means that the distance of the object to the camera has small change,depth of information is changing.Design of the model no longer needs to measure or estimate the unknown point depth information,hence it can realize accurate and fast for depth information,realize the optimization of micro robot visual servo control system.

关 键 词：显微视觉 图像信息 透视成像 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]