Overlapping citrus target recognition and localization method based on convex shell and distance transformation

doi:10.16731/j.cnki.1671-3133.2018.09.016

Abstract

Abstract: In order to realize the recognition and localization of overlapping citrus objects, a method for recognizing and locating overlapping citrus objects based on convex shell and distance transform is proposed. The method divides the target by extracting the center of the recessed area where the target convex shell and the target are subtracted. Then the segmented target center of gravity is extracted by the distance transformation theory, and the target picking center is obtained to realize the positioning of overlapping fruits. This method is compared with the traditional Hough method. The experimental results show that the average positioning error of this method is 1.58 %, which is 4.72 % lower than that of Hough method, which significantly improves the positioning accuracy and provides a new idea for the recognition and localization of overlapping fruit targets.

Key words: positioning, convex shell, distance transform, overlap

CLC Number:

TP391.7

Li Yang, Yang Changhui, Hu Youcheng, Zhang Hong, Yang Yan. Overlapping citrus target recognition and localization method based on convex shell and distance transformation[J]. Modern Manufacturing Engineering, 2018, 456(9): 82-87.

References

[1] BULANON D M,KATAOKA T,OTA Y,et al.A color model for recognition of apples by a robotic harvesting system[J].Journal of the JSAM,2002,64(5):123-133.
[2] STAJNKO D,CMELIK Z.Modeling of apple fruit growth by application of image analysis [J].Agricultural conspectus Scientifics,2005,70(2):59-64.
[3] ZHAO J,TOW J,KATUPITIYA J.On-tree fruit recognition using texture properties and color data.International conference on Intelligent Robots and Systems[C].New York:IEEE Press,2005:3993-3998.
[4] 吕强,蔡健荣,赵文杰,等.自然场景下树上柑橘实时识别技术[J].农业机械学报,2010,41(2):185-188.
[5] LEI Yan,PARK C M,LEE S R,et al.New separation algorithm for touching grain kernels based on contour segments and ellipse fitting[J].Computers in Biology and Medicine,2009,39(1):27-39.
[6] FENG Juan,WANG Shengwei,LIU Gang,et al.A separating method of adjacent apples based on machine vision and chain code information.Computer and Computing Technologies in Agriculture[C].Berlin:Part III,Springer Berlin Heidelberg,2012:258-267.
[7] JI Wei,ZHAO Dean,CHENG Fengyi,et al.Automatic recognition vision system guided for apple harvesting robot[J].Computers and Eletrical Engineering,2012(38):1186-1195.
[8] PETROS K,ARISTIDIS L,DIMITRIOS I,et al.Identifying touching and overlapping chromosomes using the watershed transform and gradient paths[J].Pattern Recogn-iton Letters,2010,31(16):2474-2488.

[9] 张艳诚,毛罕平,胡波,等.作物病害图像中重叠病斑分离算法[J].农业机械学报,2008,39(2):112-115.
[10] 曾庆兵,刘成良,苗玉彬,等.基于形态学图像处理的重叠葡萄果径无损测量[J].农业工程学报,2009,25(9):356-360.
[11] 周天娟,张铁中,杨丽,等.基于数学形态学的相接触草莓果实的分割方法及比较研究[J].农业工程学报,2007,23(9):164-168.
[12] LUO M R,CUI G,RIGG B.The development of the CIE 2000 colour-difference formula:CIEDE2000[J].Color Research and Application,2001,26(5):340-350.
[13] 黄春艳,杨国胜,侯艳丽.基于颜色直方图和空间信息融合的图像分割方法[J].计算机工程与应用,2005,41(3):85-87.
[14] 赵军,曲仕茹.平面点集凸壳的快速算法[J].计算机工程与应用,2009,45(1):56-58.
[15] 周启海.论二维点集或线段集凸壳生成算法改进与优化的同构化方向[J].计算机科学,2007,34(7):216-218,247.