摘要
在智能机器人技术中,视觉识别是关键。在智能机器人视觉系统获得的图像中,由于图像倾斜而造成的识别错误是视觉识别难以解决的问题。针对机器人所要完成的具体任务,对机器人的视觉识别问题进行探讨,为实现机器人对图像命令的识别,首先对机器人视觉系统获得的倾斜图像,采用Hough变换进行倾斜度检测并进行校正,然后采用人工神经网络法进行识别,根据识别结果对机器人的下一步运动进行决策与控制,达到了预期的目的。实验结果表明,该方法具有较高的识别率。
Visual recognition is the key in intelligent robot. The problem in visual system of intelligent robot is the wrong recognition because of tilting image obtained from robot visual system. According to the concrete task of robot , this paper discusses the visual recognition problem. In order to recognize the image command , tilting angle is tested by using Hough transfer and the tilting image is verified at first, then the image is recognized by ANN, and the results of recognition are used to plan and control mobile robot. Experimental results show that the method in this paper is reliable and accurate.
出处
《计算机仿真》
CSCD
北大核心
2009年第6期171-174,共4页
Computer Simulation
关键词
机器人视觉
图像处理
图像命令
霍夫变换
人工神经网络
Robot vision
Image processing
Image command
Hough transfer
Artificial neural networks
