基于NAO机器人的目标识别方法
发布时间：2019-03-17 13:26
【摘要】：针对NAO机器人识别目标准确率过低的问题,为降低光照对识别的影响,提出一种基于HSV颜色空间的轮廓信息特征识别的算法,通过融合颜色特征和轮廓特征识别图像中的目标。利用HSV空间模型,通过颜色阈值分割对图像进行预处理,提取红绿色目标;根据目标规则的多边形轮廓,对其形状信息加以约束;利用二值图像的轮廓特征矩加以判决,得到识别目标及其在图像中的中心坐标,实现目标的精确识别。利用NAO机器人采集图像进行模拟实验,改变NAO与目标的相对位置并多次测量,成功定位的准确率可达到92.67%。实验结果表明,NAO机器人采用该算法可以快速稳定地实现目标识别,提高了准确率。
[Abstract]:In order to reduce the influence of illumination on recognition, an algorithm of contour information feature recognition based on HSV color space is proposed to solve the problem of low accuracy of target recognition by NAO robot. In order to reduce the influence of illumination on recognition, an algorithm is proposed to recognize targets in the image by fusion of color features and contour features. The HSV space model is used to pre-process the image by color threshold segmentation to extract the red-green target, and the shape information of the image is constrained according to the polygon contour of the target rule. The recognition target and its center coordinate in the image can be obtained by using the contour characteristic moment of binary image, and the target recognition can be realized accurately. The NAO robot is used to collect images for simulation experiment, and the relative position between NAO and target is changed and measured many times. The accuracy of successful localization can reach 92.67%. The experimental results show that the NAO robot can quickly and stably realize the target recognition and improve the accuracy.
【作者单位】： 山东大学控制科学与工程学院;
【基金】：国家自然科学基金项目(61673244、61273277)
【分类号】：TP242;TP391.41
本文编号：2442344
[Abstract]:In order to reduce the influence of illumination on recognition, an algorithm of contour information feature recognition based on HSV color space is proposed to solve the problem of low accuracy of target recognition by NAO robot. In order to reduce the influence of illumination on recognition, an algorithm is proposed to recognize targets in the image by fusion of color features and contour features. The HSV space model is used to pre-process the image by color threshold segmentation to extract the red-green target, and the shape information of the image is constrained according to the polygon contour of the target rule. The recognition target and its center coordinate in the image can be obtained by using the contour characteristic moment of binary image, and the target recognition can be realized accurately. The NAO robot is used to collect images for simulation experiment, and the relative position between NAO and target is changed and measured many times. The accuracy of successful localization can reach 92.67%. The experimental results show that the NAO robot can quickly and stably realize the target recognition and improve the accuracy.
【作者单位】： 山东大学控制科学与工程学院;
【基金】：国家自然科学基金项目(61673244、61273277)
【分类号】：TP242;TP391.41
【相似文献】
相关期刊论文 前1条
1 张婷;;基于NAO的迷宫解决算法研究[J];国外电子测量技术;2013年06期
相关硕士学位论文 前1条
1 肖义涵;以NAO机器人为平台的人机互动技术研究[D];上海交通大学;2014年
，本文编号：2442344
本文链接：https://www.wllwen.com/kejilunwen/zidonghuakongzhilunwen/2442344.html
