Semantic Segmentation for Partially Occluded Apple Trees Based on Deep Learning

  title={Semantic Segmentation for Partially Occluded Apple Trees Based on Deep Learning},
  author={Z. Chen and D. Ting and Rhys Newbury and C. Chen},
  journal={Comput. Electron. Agric.},
  • Z. Chen, D. Ting, +1 author C. Chen
  • Published 2021
  • Computer Science
  • Comput. Electron. Agric.
  • Fruit tree pruning and fruit thinning require a powerful vision system that can provide high resolution segmentation of the fruit trees and their branches. However, recent works only consider the dormant season, where there are minimal occlusions on the branches or fit a polynomial curve to reconstruct branch shape and hence, losing information about branch thickness. In this work, we apply two state-of-the-art supervised learning models U-Net and DeepLabv3, and a conditional Generative… CONTINUE READING
    2 Citations

    Figures and Tables from this paper

    Automated Iterative Training of Convolutional Neural Networks for Tree Skeleton Segmentation
    • PDF
    Learning to Place Objects onto Flat Surfaces in Upright Orientations
    • PDF


    Deep learning based segmentation for automated training of apple trees on trellis wires
    • 13
    Fruit Detection, Segmentation and 3D Visualisation of Environments in Apple Orchards
    • 16
    • PDF
    Seeing Behind Things: Extending Semantic Segmentation to Occluded Regions
    • 7
    • PDF
    Fully Convolutional Networks for Semantic Segmentation
    • 8,986
    • PDF
    Semantic Segmentation using Adversarial Networks
    • 442
    • PDF
    Mask R-CNN
    • 4,937
    Rethinking Atrous Convolution for Semantic Image Segmentation
    • 2,120
    • Highly Influential
    • PDF
    Cell Image Segmentation by Integrating Pix2pixs for Each Class
    • H. Tsuda, K. Hotta
    • Computer Science
    • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
    • 2019
    • 3
    • PDF
    U-Net: Convolutional Networks for Biomedical Image Segmentation
    • 19,118
    • Highly Influential
    • PDF