DAM: Hierarchical Adaptive Feature Selection Using Convolution Encoder Decoder Network for Strawberry Segmentation

Ilyas Talha¹, Umraiz Muhammad¹, Khan Abbas¹, Kim Hyongsuk^1,2,*

¹Division of Electronic Engineering, Intelligent Robots Research Center, Jeonbuk National University, Jeonju, South Korea
²Division of Electronic and Information Engineering, Jeonbuk National University, Jeonju, South Korea
^*Corresponding author: hskim@jbnu.ac.kr

In this paper, a new dataset (i.e., SS1K) is introduced for the segmentation of strawberries into four classes depending upon the ripeness of the fruit (including a background class). The proposed segmentation network named Straw-Net improves the performance of ASHs in unconstrained and natural farming environments.

Abstract

Autonomous harvesters can be used for the timely cultivation of high-value crops such as strawberries, where the robots have the capability to identify ripe and unripe crops. However, the real-time segmentation of strawberries in an unbridled farming environment is a challenging task due to fruit occlusion by multiple trusses, stems, and leaves. In this work, we propose a possible solution by constructing a dynamic feature selection mechanism for convolutional neural networks (CNN). The proposed building block namely a dense attention module (DAM) controls the flow of information between the convolutional encoder and decoder. DAM enables hierarchical adaptive feature fusion by exploiting both inter-channel and intra-channel relationships and can be easily integrated into any existing CNN to obtain category-specific feature maps. We validate our attention module through extensive ablation experiments. In addition, a dataset is collected from different strawberry farms and divided into four classes corresponding to different maturity levels of fruits and one is devoted to background. Quantitative analysis of the proposed method showed a 4.1% and 2.32% increase in mean intersection over union, over existing state-of-the-art semantic segmentation models and other attention modules respectively, while simultaneously retaining a processing speed of 53 frames per second.

Files

• Paper

Citation

@article{ilyas2021dam,
title={DAM: Hierarchical Adaptive Feature Selection using Convolution Encoder Decoder Network for Strawberry Segmentation},
author={Ilyas, Talha and Umraiz, Muhammad and Khan, Abbas and Kim, Hyongsuk},
journal={Frontiers in Plant Science},
year={2021},
volume={12},
pages={189},
publisher={Frontiers}
}