A Separating Method of Adjacent Apples Based on Machine Vision and Chain Code Information - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

A Separating Method of Adjacent Apples Based on Machine Vision and Chain Code Information

Résumé

Fruit location is an important parameter for apple harvesting robot to conduct picking task. However, it is difficult to obtain coordinates of each apple under natural conditions. One of the major challenges is detecting adjacent fruits accurately. Previous studies for adjacent detection have shortcomings such as vast computation, difficulty in implementation and over-segmentation. In this paper, we propose a novel and effective separating method for adjacent apples recognition based on chain code information and obtain the centroid coordinates of each fruit. Firstly, those valid regions of fruit are extracted by pre-processing the initial image. Secondly, chain code information is obtained by following the contour of extracted regions. Thirdly, through observing the changing law of chain code difference and adopting local optimum principle, concave points are found. Finally, the best point pairs are determined with different matching principles, and those adjacent apples are separated exactly. The experimental results show that the average rate of successful separation is greater than 91.2% with the proposed method, which can meet the requirements of applications in harvesting robots.
Fichier principal
Vignette du fichier
978-3-642-27281-3_32_Chapter.pdf (4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01351818 , version 1 (04-08-2016)

Licence

Paternité

Identifiants

Citer

Juan Feng, Shengwei Wang, Gang Liu, Lihua Zeng. A Separating Method of Adjacent Apples Based on Machine Vision and Chain Code Information. 5th Computer and Computing Technologies in Agriculture (CCTA), Oct 2011, Beijing, China. pp.258-267, ⟨10.1007/978-3-642-27281-3_32⟩. ⟨hal-01351818⟩
67 Consultations
163 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More