CED-Net: Crops and Weeds Segmentation for Smart Farming Using a Small Cascaded Encoder-Decoder Architecture

Khan Abbas¹, Ilyas Talha¹, Umraiz Muhammad¹, 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

This paper presents a small-cascaded encoder-decoder (CED-Net) architecture to detect and extract the precise location of weeds and crops on farmland using semantic segmentation. The proposed network has comparatively less number of parameters compared to the other state-of-the-art architectures, thus results in lesser training and inference time. The improved performance of CED-Net is attributed to its coarse-to-fine approach and cascaded architecture.

Abstract

Convolutional neural networks (CNNs) have achieved state-of-the-art performance in numerous aspects of human life and the agricultural sector is no exception. One of the main objectives of deep learning for smart farming is to identify the precise location of weeds and crops on farmland. In this paper, we propose a semantic segmentation method based on a cascaded encoder-decoder network, namely CED-Net, to differentiate weeds from crops. The existing architectures for weeds and crops segmentation are quite deep, with millions of parameters that require longer training time. To overcome such limitations, we propose an idea of training small networks in cascade to obtain coarse-to-fine predictions, which are then combined to produce the final results. Evaluation of the proposed network and comparison with other state-of-the-art networks are conducted using four publicly available datasets: rice seeding and weed dataset, BoniRob dataset, carrot crop vs. weed dataset, and a paddy–millet dataset. The experimental results and their comparisons proclaim that the proposed network outperforms state-of-the-art architectures, such as U-Net, SegNet, FCN-8s, and DeepLabv3, over intersection over union (IoU), F1-score, sensitivity, true detection rate, and average precision comparison metrics by utilizing only (1/5.74 × U-Net), (1/5.77 × SegNet), (1/3.04 × FCN-8s), and (1/3.24 × DeepLabv3) fractions of total parameters.

Files

• Paper

Citation

@article{khan2020ced,
title={CED-Net: Crops and Weeds Segmentation for Smart Farming Using a Small Cascaded Encoder-Decoder Architecture},
author={Khan, Abbas and Ilyas, Talha and Umraiz, Muhammad and Mannan, Zubaer Ibna and Kim, Hyongsuk},
journal={Electronics},
volume={9},
number={10},
pages={1602},
year={2020},
publisher={Multidisciplinary Digital Publishing Institute}}