Cargando…

Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms

The accurate identification of weeds is an essential step for a site-specific weed management system. In recent years, deep learning (DL) has got rapid advancements to perform complex agricultural tasks. The previous studies emphasized the evaluation of advanced training techniques or modifying the...

Descripción completa

Detalles Bibliográficos
Autores principales: Saleem, Muhammad Hammad, Velayudhan, Kesini Krishnan, Potgieter, Johan, Arif, Khalid Mahmood
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9083231/
https://www.ncbi.nlm.nih.gov/pubmed/35548295
http://dx.doi.org/10.3389/fpls.2022.850666
_version_ 1784703379845414912
author Saleem, Muhammad Hammad
Velayudhan, Kesini Krishnan
Potgieter, Johan
Arif, Khalid Mahmood
author_facet Saleem, Muhammad Hammad
Velayudhan, Kesini Krishnan
Potgieter, Johan
Arif, Khalid Mahmood
author_sort Saleem, Muhammad Hammad
collection PubMed
description The accurate identification of weeds is an essential step for a site-specific weed management system. In recent years, deep learning (DL) has got rapid advancements to perform complex agricultural tasks. The previous studies emphasized the evaluation of advanced training techniques or modifying the well-known DL models to improve the overall accuracy. In contrast, this research attempted to improve the mean average precision (mAP) for the detection and classification of eight classes of weeds by proposing a novel DL-based methodology. First, a comprehensive analysis of single-stage and two-stage neural networks including Single-shot MultiBox Detector (SSD), You look only Once (YOLO-v4), EfficientDet, CenterNet, RetinaNet, Faster Region-based Convolutional Neural Network (RCNN), and Region-based Fully Convolutional Network (RFCN), has been performed. Next, the effects of image resizing techniques along with four image interpolation methods have been studied. It led to the final stage of the research through optimization of the weights of the best-acquired model by initialization techniques, batch normalization, and DL optimization algorithms. The effectiveness of the proposed work is proven due to a high mAP of 93.44% and validated by the stratified k-fold cross-validation technique. It was 5.8% improved as compared to the results obtained by the default settings of the best-suited DL architecture (Faster RCNN ResNet-101). The presented pipeline would be a baseline study for the research community to explore several tasks such as real-time detection and reducing the computation/training time. All the relevant data including the annotated dataset, configuration files, and inference graph of the final model are provided with this article. Furthermore, the selection of the DeepWeeds dataset shows the robustness/practicality of the study because it contains images collected in a real/complex agricultural environment. Therefore, this research would be a considerable step toward an efficient and automatic weed control system.
format Online
Article
Text
id pubmed-9083231
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-90832312022-05-10 Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms Saleem, Muhammad Hammad Velayudhan, Kesini Krishnan Potgieter, Johan Arif, Khalid Mahmood Front Plant Sci Plant Science The accurate identification of weeds is an essential step for a site-specific weed management system. In recent years, deep learning (DL) has got rapid advancements to perform complex agricultural tasks. The previous studies emphasized the evaluation of advanced training techniques or modifying the well-known DL models to improve the overall accuracy. In contrast, this research attempted to improve the mean average precision (mAP) for the detection and classification of eight classes of weeds by proposing a novel DL-based methodology. First, a comprehensive analysis of single-stage and two-stage neural networks including Single-shot MultiBox Detector (SSD), You look only Once (YOLO-v4), EfficientDet, CenterNet, RetinaNet, Faster Region-based Convolutional Neural Network (RCNN), and Region-based Fully Convolutional Network (RFCN), has been performed. Next, the effects of image resizing techniques along with four image interpolation methods have been studied. It led to the final stage of the research through optimization of the weights of the best-acquired model by initialization techniques, batch normalization, and DL optimization algorithms. The effectiveness of the proposed work is proven due to a high mAP of 93.44% and validated by the stratified k-fold cross-validation technique. It was 5.8% improved as compared to the results obtained by the default settings of the best-suited DL architecture (Faster RCNN ResNet-101). The presented pipeline would be a baseline study for the research community to explore several tasks such as real-time detection and reducing the computation/training time. All the relevant data including the annotated dataset, configuration files, and inference graph of the final model are provided with this article. Furthermore, the selection of the DeepWeeds dataset shows the robustness/practicality of the study because it contains images collected in a real/complex agricultural environment. Therefore, this research would be a considerable step toward an efficient and automatic weed control system. Frontiers Media S.A. 2022-04-25 /pmc/articles/PMC9083231/ /pubmed/35548295 http://dx.doi.org/10.3389/fpls.2022.850666 Text en Copyright © 2022 Saleem, Velayudhan, Potgieter and Arif. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Plant Science
Saleem, Muhammad Hammad
Velayudhan, Kesini Krishnan
Potgieter, Johan
Arif, Khalid Mahmood
Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms
title Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms
title_full Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms
title_fullStr Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms
title_full_unstemmed Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms
title_short Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms
title_sort weed identification by single-stage and two-stage neural networks: a study on the impact of image resizers and weights optimization algorithms
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9083231/
https://www.ncbi.nlm.nih.gov/pubmed/35548295
http://dx.doi.org/10.3389/fpls.2022.850666
work_keys_str_mv AT saleemmuhammadhammad weedidentificationbysinglestageandtwostageneuralnetworksastudyontheimpactofimageresizersandweightsoptimizationalgorithms
AT velayudhankesinikrishnan weedidentificationbysinglestageandtwostageneuralnetworksastudyontheimpactofimageresizersandweightsoptimizationalgorithms
AT potgieterjohan weedidentificationbysinglestageandtwostageneuralnetworksastudyontheimpactofimageresizersandweightsoptimizationalgorithms
AT arifkhalidmahmood weedidentificationbysinglestageandtwostageneuralnetworksastudyontheimpactofimageresizersandweightsoptimizationalgorithms