Title

Automatic Segmentation of Trees in Dynamic Outdoor Environments

Document Type

Article

Language

eng

Publication Date

6-2018

Publisher

Elsevier

Source Publication

Computers in Industry

Source ISSN

0166-3615

Abstract

Segmentation in dynamic outdoor environments can be difficult when the illumination levels and other aspects of the scene cannot be controlled. Specifically in orchard and vineyard automation contexts, a background material is often used to shield a camera's field of view from other rows of crops. In this paper, we describe a method that uses superpixels to determine low texture regions of the image that correspond to the background material, and then show how this information can be integrated with the color distribution of the image to compute optimal segmentation parameters to segment objects of interest. Quantitative and qualitative experiments demonstrate the suitability of this approach for dynamic outdoor environments, specifically for tree reconstruction and apple flower detection applications

Comments

Computers in Industry, Vol. 98 (June 2018): 90-99. DOI.

Share

COinS