›› 2017, Vol. 29 ›› Issue (6): 1009-1016.DOI: 10.3969/j.issn.1004-1524.2017.06.22

• Biosystems Engineering • Previous Articles     Next Articles

Location of occluded apples based on gradient Hough transform

WU Qinggang1, ZHANG Weiguo1, CHANG Huawen1, JIN Baohua1, LIU Zhaoxia2   

  1. 1. School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450001, China;
    2. School of Software, Dalian University of Foreign Languages, Dalian 116044, China
  • Received:2016-12-28 Online:2017-06-20 Published:2017-09-07

Abstract: In order to accurately locate the apples occluded by branches or other apples in natural environment, a method based on gradient Hough transform was proposed in the present study. Firstly, K-means clustering algorithm was used in Lab space to segment apples in natural environment. Secondly, morphological operations were made based on the segmented results to remove the influence of small area. Then, Sobel operator was adopted to extract the edge of apples. Finally, gradient Hough transform was applied to estimate the center and radius of target apples. Thus, the occluded apples could be automatically located. Experimental results showed that the method could effectively locate the occluded apples with the precision as high as 93.17%.

Key words: gradient Hough transform, natural environment, target location, apple images, K-means clustering algorithm, morphology

CLC Number: