188宝金博页面版

2 0 1 3 年 8 月农 业 机 械 学 报第 44 卷 第 8 期doi:10. 6041 /j. issn. 1000鄄1298. 2013. 08. 040葡萄套袋机器人目 标识别方法*杨庆华摇刘摇灿摇荀摇一摇鲍官军摇王志恒摇黄鹏程( 浙江工业大学特种装备制造与先进加工技术188宝金博页面版部/浙江省重点实验室, 杭州 310014)摘要: 针对水平棚架栽培模式下采集的单幅葡萄果树图像,提出了结合葡萄颜色与形状特征的目标识别定位方法,获得果穗的中心线和长度特征参数。 通过提取葡萄图像的 | G - R | + | G - B | 色差图, 利用 Sobel 算子进行边缘提取。 构建葡萄果粒轮廓的数学模型进行 Hough 变换, 实现葡萄果粒的初步识别。 结合葡萄果穗的颜色、纹理特征以及果粒分布较为集中的特点判断 Hough 变换检测出的圆区域是否为果粒。 综合利用识别出的果粒信息找到葡萄图像的外接矩形完成目标提取。 对 78 幅图像进行测试, 正确识别出葡萄区域的图像为 70 幅, 正确识别率约为90% 。关键词: 葡萄摇套袋机器人摇机器视觉摇Hough 变换摇识别中图分类号: TP391郾 41文献标识码: A文章编号: 1000鄄1298(2013)08鄄0234鄄06Target Recognition for Grape Bagging RobotYang Qinghua摇Liu Can摇Xun Yi摇Bao Guanjun摇Wang Zhiheng摇Huang Pengcheng( Key Laboratory of Special Purpose Equipment and Advanced Processing Technology, Ministry of Education andZhejiang Province, Zhejiang University of Technology, Hangzhou 310014, China)Abstract: Aimed at the image of the simple grapevine taken in the pergola trellis, a grape recognitionalgorithm combined with color and texture feature of color image was suggested in order to get the centerline and the length of the grape. Firstly, Sobel operation was used to get the edge of the | G - R| + | G -B | chromatic aberration image. Then, berries of the grape were detected by Hough transform according tothe mathematical model of the outline of the grape berries. The circles detected by the Hough transformwere judged by the feature of the color and texture of grape berries and the concentrated berries. At last,the shape parameters of the grape bunch were determined by the information of the berries after judged,which was needed by bagging automation of grape. The experimental results showed that the method ofgrape recognition was effective in segmenting the comparison of grapes. There were totally 78 images usedin test, and 70 of them were correctly recognized. The correct recognition of grapes reached to 90% .Key words: Grape摇Bagging robot摇Machine vision摇Hough transform摇Recognition收稿日 期: 2012* 国家自 然科学基金资助项目(51075363) 、浙江省自 然科学基金杰出青年团队资助项目 ( R1090674) 和浙江省特种装备制造和先进加工技术重点实验室开放基金资助项目 (2011EM002)作者简介: 杨庆华,教授,博士生导师,主要从事机器人研究,E鄄mail: zjutme@ 163. com0801摇修回日 期: 20120907摇摇引言葡萄套袋的作用是将果实与外界环境隔离, 防止果实受到外界环境的不良损伤, 提高葡萄的外观及好果率, 是我国葡萄栽培中的关键技术之一[1]。目前葡萄套袋主要采用人工套袋操作,劳动强度大、效率低、工作繁琐,对人力资源贫乏地区的葡萄栽培造成了很大制约, 因此开发智能化的葡萄套袋机器人具有重要的实际意义。机器视觉作为农业机器人外部传感器最大信息源,是农业机器人研究领域的关键技术之一。 但由于农业对象的多样性及作业环境的复杂性, 尚未有一种通用的目标识别算法[2]。近年来,国内外学者对苹果、橘子、番茄等形状