A Video Image Segmentation System for the Fruit-trees in Multi-stage Outdoors Orchard under Natural Conditions

Abstract

Segmentation is an important part of each machine vision system that has a direct relationship with the final system  accuracy and performance. Outdoors segmentation is often complex and difficult due to both changes in sunlight  intensity and the different nature of background objects. However, in fruit-tree orchards, an automatic segmentation  algorithm with high accuracy and speed is very desirable. For this reason, a multi-stage segmentation algorithm is  applied for the segmentation of apple fruits with Red Delicious cultivar in orchard under natural light and background  conditions. This algorithm comprises a combination of five segmentation stages, based on: 1- L*u*v* color space,  2- local range texture feature, 3- intensity transformation, 4- morphological operations, and 5- RGB color space. To  properly train a segmentation algorithm, several videos were recorded under nine different light intensities in Iran- Kermanshah (longitude: 7.03E; latitude: 4.22N) with natural (real) conditions in terms of both light and background.  The order of segmentation stage methods in multi-stage algorithm is very important since has a direct relationship with  final segmentation accuracy. The best order of segmentation methods resulted to be: 1- color, 2- texture and 3- intensity  transformation methods. Results show that the values of sensitivity, accuracy and specificity, in both classes, were  higher than 97.5%, over the test set. We believe that those promising numbers imply that the proposed algorithm has a  remarkable performance and could potentially be applied in real-world industrial case.