Automatic Localization and Count of Agricultural Crop Pests Based on an Improved Deep Learning Pipeline

Abstract Insect pests are known to be a major cause of damage to agricultural crops. This paper proposed a deep learning-based pipeline for localization and counting of agricultural pests in images by self-learning saliency feature maps. Our method integrates a convolutional neural network (CNN) of...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Weilu Li, Peng Chen, Bing Wang, Chengjun Xie
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2019
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/cbf85683fea8493ea6a1cbf6c76672dc
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cbf85683fea8493ea6a1cbf6c76672dc
record_format	dspace
spelling	oai:doaj.org-article:cbf85683fea8493ea6a1cbf6c76672dc2021-12-02T16:08:05ZAutomatic Localization and Count of Agricultural Crop Pests Based on an Improved Deep Learning Pipeline10.1038/s41598-019-43171-02045-2322https://doaj.org/article/cbf85683fea8493ea6a1cbf6c76672dc2019-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-019-43171-0https://doaj.org/toc/2045-2322Abstract Insect pests are known to be a major cause of damage to agricultural crops. This paper proposed a deep learning-based pipeline for localization and counting of agricultural pests in images by self-learning saliency feature maps. Our method integrates a convolutional neural network (CNN) of ZF (Zeiler and Fergus model) and a region proposal network (RPN) with Non-Maximum Suppression (NMS) to remove overlapping detections. First, the convolutional layers in ZF Net, without average pooling layer and fc layers, were used to compute feature maps of images, which can better retain the original pixel information through smaller convolution kernels. Then, several critical parameters of the method were optimized, including the output size, score threshold, NMS threshold, and so on. To demonstrate the practical applications of our method, different feature extraction networks were explored, including AlexNet, ResNet and ZF Net. Finally, the model trained on smaller multi-scale images was tested on original large images. Experimental results showed that our method achieved a precision of 0.93 with a miss rate of 0.10. Moreover, our model achieved a mean Accuracy Precision (mAP) of 0.885.Weilu LiPeng ChenBing WangChengjun XieNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 9, Iss 1, Pp 1-11 (2019)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Weilu Li Peng Chen Bing Wang Chengjun Xie Automatic Localization and Count of Agricultural Crop Pests Based on an Improved Deep Learning Pipeline
description	Abstract Insect pests are known to be a major cause of damage to agricultural crops. This paper proposed a deep learning-based pipeline for localization and counting of agricultural pests in images by self-learning saliency feature maps. Our method integrates a convolutional neural network (CNN) of ZF (Zeiler and Fergus model) and a region proposal network (RPN) with Non-Maximum Suppression (NMS) to remove overlapping detections. First, the convolutional layers in ZF Net, without average pooling layer and fc layers, were used to compute feature maps of images, which can better retain the original pixel information through smaller convolution kernels. Then, several critical parameters of the method were optimized, including the output size, score threshold, NMS threshold, and so on. To demonstrate the practical applications of our method, different feature extraction networks were explored, including AlexNet, ResNet and ZF Net. Finally, the model trained on smaller multi-scale images was tested on original large images. Experimental results showed that our method achieved a precision of 0.93 with a miss rate of 0.10. Moreover, our model achieved a mean Accuracy Precision (mAP) of 0.885.
format	article
author	Weilu Li Peng Chen Bing Wang Chengjun Xie
author_facet	Weilu Li Peng Chen Bing Wang Chengjun Xie
author_sort	Weilu Li
title	Automatic Localization and Count of Agricultural Crop Pests Based on an Improved Deep Learning Pipeline
title_short	Automatic Localization and Count of Agricultural Crop Pests Based on an Improved Deep Learning Pipeline
title_full	Automatic Localization and Count of Agricultural Crop Pests Based on an Improved Deep Learning Pipeline
title_fullStr	Automatic Localization and Count of Agricultural Crop Pests Based on an Improved Deep Learning Pipeline
title_full_unstemmed	Automatic Localization and Count of Agricultural Crop Pests Based on an Improved Deep Learning Pipeline
title_sort	automatic localization and count of agricultural crop pests based on an improved deep learning pipeline
publisher	Nature Portfolio
publishDate	2019
url	https://doaj.org/article/cbf85683fea8493ea6a1cbf6c76672dc
work_keys_str_mv	AT weiluli automaticlocalizationandcountofagriculturalcroppestsbasedonanimproveddeeplearningpipeline AT pengchen automaticlocalizationandcountofagriculturalcroppestsbasedonanimproveddeeplearningpipeline AT bingwang automaticlocalizationandcountofagriculturalcroppestsbasedonanimproveddeeplearningpipeline AT chengjunxie automaticlocalizationandcountofagriculturalcroppestsbasedonanimproveddeeplearningpipeline
_version_	1718384621681377280

Automatic Localization and Count of Agricultural Crop Pests Based on an Improved Deep Learning Pipeline

Ejemplares similares