|کد مقاله||کد نشریه||سال انتشار||مقاله انگلیسی||ترجمه فارسی||نسخه تمام متن|
|84042||158858||2016||6 صفحه PDF||سفارش دهید||دانلود رایگان|
• BPNN is used to classify pixels based on their color and position.
• The main body and edge of fruits are recognized respectively.
• The position information is represented as the relativity of adjacent pixels.
• The method can reduce the influence of Shadows and faculae effectively.
This paper proposes a method to segment apples on trees at night for apple-harvesting robots based on color and position of pixels. Images of apples acquired under artificial light with low illumination at night include less color information than daytime images, so it is necessary to take position of pixels into consideration. The new method has two main steps. Firstly, color components of sampled pixels in RGB and HSI color space are used to train a neural network model to segment the apples. However, the segmentation results are incomplete and not able to guide apple-harvesting robots accurately, because partial edge regions of apples are dark in shadows and difficult to be recognized due to uneven illumination. Secondly, the color and position of pixels around segmented regions and pixels on the boundary of segmented regions are taken into consideration to segment the edge regions of apples. The union of two segmentation results is the final result. The complete recognition can increase the accuracy of location by about 6.5%, which verified the validity and feasibility of the method.
Journal: Computers and Electronics in Agriculture - Volume 122, March 2016, Pages 118–123