| 基于轮廓曲率和距离分析的重叠柑橘分割与重建 |
| |
| 引用本文： | 刘妤,刘洒,杨长辉,王卓,熊龙烨.基于轮廓曲率和距离分析的重叠柑橘分割与重建[J].中国农业科技导报,2020,22(8):93-101. |
| |
| 作者姓名： | 刘妤 刘洒 杨长辉 王卓 熊龙烨 |
| |
| 作者单位： | 1.重庆理工大学机械工程学院， 重庆 400054；2.西安交通大学机械工程学院， 西安 710049 |
| |
| 基金项目： | 重庆市重点产业共性关键技术创新专项(cstc2015zdcy-ztzx70003);重庆市研究生联合培养基地项目;重庆理工大学研究生创新项目（ycx2018213）。 |
| |
| 摘 要： | 自然环境下重叠果实的精准识别是智能采摘面临的难题之一。针对自然环境中成熟的重叠柑橘，提出了一种基于轮廓曲率和距离分析的果实分割方法。首先，提取重叠柑橘果实轮廓并进行高斯平滑，通过曲率分析，找出异常的轮廓像素点；其次，依次连接相邻两个异常像素点，分析该线段上的像素点到轮廓的距离，在相邻两正常线段的交点处完成重叠柑橘轮廓分割，并通过寻找异常线段剔除对应的非柑橘轮廓像素点；在此基础上，采用最小二乘椭圆拟合方法，对获取的柑橘目标进行轮廓重建。结果表明：利用该方法所得到的重叠柑橘重建轮廓的平均误差、不重合度和时间分别为4.903%、5.593%、0.408 s，优于Hough变换算法和RANSAC算法，能够满足自然环境下成熟重叠柑橘果实的智能识别需求。
|
| 关 键 词： | 智能采摘 重叠分割 轮廓重建 曲率 距离分析 |
| 收稿时间： | 2019-03-19 |
Segmentation and Reconstruction of Overlapping Citrus Based on Contour Curvature and Distance Analysis |
| |
| LIU Yu,LIU Sa,YANG Changhui,WANG Zhuo,XIONG Longye.Segmentation and Reconstruction of Overlapping Citrus Based on Contour Curvature and Distance Analysis[J].Journal of Agricultural Science and Technology,2020,22(8):93-101. |
| |
| Authors: | LIU Yu LIU Sa YANG Changhui WANG Zhuo XIONG Longye |
| |
| Abstract: | Accurate identification of overlapped fruits in natural environment is one of the problems that need to be solved in intelligent picking. In this paper, a new method of segmentation for mature overlapping citrus in the natural environment was proposed based on contour curvature and distance analysis. Firstly, the contours of overlapping citrus fruits were extracted and Gaussian smoothing was performed. The abnormal contour pixel points were found by means of the curvature analysis. Secondly, the two adjacent abnormal pixel points were sequentially connected to form a line segment, and the distance from the pixel point to the contour on the line segment was analyzed. The overlapping citrus contour segmentation was completed at the intersection of two adjacent normal segments, and the corresponding non-citrus contour pixels were eliminated by finding the abnormal line segment. Finally, the obtained citrus target was reconstructed by the least squares ellipse fitting method. The experimental results showed that the average error, non-coincidence and time of the citrus targets obtained by this method were 4.903%, 5.593% and 0.408 s, respectively, which were better than those of Hough transform algorithm and RANSAC algorithm, and could meet the intelligent identification requirements of mature overlapping fruits in natural environment. |
| |
| Keywords: | intelligent picking overlapped segmentation contour reconstruction curvature distance analysis |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《中国农业科技导报》浏览原始摘要信息 |
| 点击此处可从《中国农业科技导报》下载免费的PDF全文 |
|
