Intelligent Identification of Jute Pests Based on Transfer Learning and Deep Convolutional Neural Networks

Sourav, Md Sakib Ullah; Wang, Huidong

doi:10.1007/s11063-022-10978-4

Cited by 13 publications

(7 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of smartphones in crops is gaining more space with the development of smart agriculture. Smartphones are used to run systems, capture images, send to a model to identify pests in real time (Sourav;. A pest identification/recognition and detection system using DL can run on both desktop and mobile devices (Chudzik et al, 2020;Gasaye;Mollo, 2022;Rimal;Shah;Jha, 2022).…”

Section: Qp1 -What Are Computational Technologies Used To Combat and ...mentioning

confidence: 99%

“…This issue was addressed by authors who used the CNN architecture to identify contaminated regions detect pests using images(Liu et al 2019b;Gao;Hang, 2019). A model was proposed bySourav, Wang (2022) using DCNN and transfer learning to identify pests.The Vector Machine Support (SVM) tool is used in models to perform image processing to identify and classify crop pests. Vivek A.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence and Its Tools in Pest Control for Agricultural Production: A Review

Mignoni,

Soares Monteiro,

Zagonel

et al. 2024

RECIMA21

View full text Add to dashboard Cite

Artificial Intelligence (AI) and its tools are being widely used worldwide. In the area of agriculture, AI is being widely studied and expanding. The use of AI in agriculture is being widely studied and expanding from pre-harvest to post-harvest. The increase in world population has triggered the need to increase food production. This need has triggered a search for solutions that promote increased food production and quality. One way to increase food production and quality is pest control. AI and its tools have proven to be a growing and rising solution in controlling and combating pests. This research focuses on reviewing and demonstrating the advances in combating and controlling pests using AI tools and images. It stands out: the classification of pests; insect identification; use and capture of Unmanned aerial vehicle (UAV) footage; using Deep Learning (DL) and Convolutional Neural Network (CNN). A search engine was applied to 5 databases. Cutting criteria were applied in 3 stages, and there were 71 papers at the end. The 71 went through 3 quality assessment questions, leaving 47 works for final analysis. This study demonstrated that the DL and the CNN tool using real images have the potential for insect control and combat solutions. Another tool in recent studies associated with CNN is the attention mechanism, improving pest identification results. Identification of insects through leaf images using CNN requires.

show abstract

Section: Qp1 -What Are Computational Technologies Used To Combat and ...mentioning

confidence: 99%

mentioning

confidence: 99%

Artificial Intelligence and Its Tools in Pest Control for Agricultural Production: A Review

Mignoni,

Soares Monteiro,

Zagonel

et al. 2024

RECIMA21

View full text Add to dashboard Cite

show abstract

“…In recent years, researchers have developed an increasing number of models using different Convolutional Neural Networks (CNNs), and this section highlights some of the recent noteworthy studies. Sourav et al [9] proposed a target detection model based on Transfer Learning (TL) and Deep Convolutional Neural Networks (DCNN), which was capable of identifying four groups of jute pests, Field cricket, Spilosoma obliqua, Jute stem weevil, and Yellow mite with a final accuracy of 95% for the identification of the four pest categories. However, in general, the accuracy of the network may decrease as the number of categories increases.…”

Section: Related Workmentioning

confidence: 99%

“…To validate the generality and performance of our proposed JutePest-YOLO model on different datasets, we conducted a Generalisation experiment on another jute pest dataset and compared our model with other mainstream target detection models. This dataset is from the dataset used in the paper of Sourav et al [9], which contains images of four categories of jute pests (the specific categories are Field cricket, Spilosoma Obliqu, Jute stem weevil, and Yellow mite). The names of the categories are denoted by D1, D2, D3, and D4, respectively.…”

Section: Hgeneralization Studiesmentioning

confidence: 99%

JutePest-YOLO: A Deep Learning Network for Jute Pest Identification and Detection

Zhang,

Wang,

Zhang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In recent years, jute, as an important natural fiber crop, has become more and more significant in the production process of insect pests, causing serious harm to agricultural production. Especially in the field of crop pest identification with complex backgrounds, fuzzy features, and multiple small targets, the lack of datasets specifically for jute pests has led to the large limitations of traditional pest identification models in terms of generalization. At the same time, the research on models specifically for jute pest detection is still in its infancy. To solve this problem, we constructed a large-scale image dataset containing nine types of jute pests, which was highly targeted and could effectively support model training and evaluation. In this study, we developed a deep convolutional neural network model based on YOLOv7, namely JutePest-YOLO. The model has optimized the Backbone, Head, and loss functions of the baseline model, and introduced the new ELAN-P module and P6 detection layer, which effectively improved the model's ability to identify jute pests in complex backgrounds. The experimental results showed that compared with the baseline model, the Precision, Recall, and F1 scores of the JutePest-YOLO model were improved by 3.45%, 1.76%, and 2.58%, respectively; the

show abstract

“…The application of deep learning methods to the intelligent recognition of crop pest images has become an important research direction, providing a potential solution to the limitations of traditional pest management methods. For example, Sourav et al [ 6 ] pioneered an intelligent model leveraging transfer learning (TL) and a deep convolutional neural network (DCNN) tailored explicitly for identifying jute pests. This model demonstrated remarkable proficiency, achieving a final accuracy of 95.86% across four major jute pest categories.…”

Section: Introductionmentioning

confidence: 99%

Farmland pest recognition based on Cascade RCNN Combined with Swin-Transformer

Xu,

Yu,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Agricultural pests and diseases pose major losses to agricultural productivity, leading to significant economic losses and food safety risks. However, accurately identifying and controlling these pests is still very challenging due to the scarcity of labeling data for agricultural pests and the wide variety of pest species with different morphologies. To this end, we propose a two-stage target detection method that combines Cascade RCNN and Swin Transformer models. To address the scarcity of labeled data, we employ random cut-and-paste and traditional online enhancement techniques to expand the pest dataset and use Swin Transformer for basic feature extraction. Subsequently, we designed the SCF-FPN module to enhance the basic features to extract richer pest features. Specifically, the SCF component provides a self-attentive mechanism with a flexible sliding window to enable adaptive feature extraction based on different pest features. Meanwhile, the feature pyramid network (FPN) enriches multiple levels of features and enhances the discriminative ability of the whole network. Finally, to further improve our detection results, we incorporated non-maximum suppression (Soft NMS) and Cascade R-CNN’s cascade structure into the optimization process to ensure more accurate and reliable prediction results. In a detection task involving 28 pest species, our algorithm achieves 92.5%, 91.8%, and 93.7% precision in terms of accuracy, recall, and mean average precision (mAP), respectively, which is an improvement of 12.1%, 5.4%, and 7.6% compared to the original baseline model. The results demonstrate that our method can accurately identify and localize farmland pests, which can help improve farmland’s ecological environment.

show abstract

Intelligent Identification of Jute Pests Based on Transfer Learning and Deep Convolutional Neural Networks

Cited by 13 publications

References 41 publications

Artificial Intelligence and Its Tools in Pest Control for Agricultural Production: A Review

Artificial Intelligence and Its Tools in Pest Control for Agricultural Production: A Review

JutePest-YOLO: A Deep Learning Network for Jute Pest Identification and Detection

Farmland pest recognition based on Cascade RCNN Combined with Swin-Transformer

Contact Info

Product

Resources

About