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

Review of Weed Detection Methods Based on Computer Vision

“…The spraying mechanism was combined with a machine vision system to realize the classification task in the case of high weed density and achieve the purpose of precise spraying of weeds with herbicides. Khan et al [ 150 ] proposed a small-cascaded encoder-decoder (CED-NET) architecture to distinguish crops from weeds, in which each level of the encoder and decoder network was independently trained for crop or weed segmentation. This network was compared with other state-of-the-art networks in four public datasets.…”

DNA sequences performs as natural language processing by exploiting deep learning algorithm for the identification of N4-methylcytosine

“…Whereas, an assorted CNN model can be made by using handcrafted features. Convolution Neural Network has been utilized in several research areas such as image processing 39,40 , natural language processing 41 , and computational biology [42][43][44][45][46][47] . A grid search algorithm was implemented with different hyper-parameters values to obtain the most optimal CNN model during its learning.…”

RecSNO: Prediction of Protein S-Nitrosylation Sites Using a Recurrent Neural Network

“…By contrast, a computational architecture based on deep learning is capable of extracting the essential features of a sequence without any human intervention, leading to an accurate and robust computational model. Deep learning based models are associated with extraordinary advancements in the fields of natural language processing [44], speech recognition [45], energy load forecasting [46], image recognition [47] and computational biology [48]- [51]. However Recently, advanced machine learning techniques based on deep forest models were proposed such as DTI-CDF [52] and LMI-DForest [53].…”