EUVIMEDEUVIMED entdecken
Crossref

Segmentation and detection of crop pests using novel U‐Net with hybrid deep learning mechanism

Nagaveni Biradar iD, Girisha Hosalli

Pest Management Science · 2024

DOI: 10.1002/ps.8083 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pest Management Science, 2024. Verfasst von Nagaveni Biradar und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science & Engineering, Rao Bahadhur Y Mahabaleswarappa Engineering College, VTU, Belagavi, Karnataka, India. Hauptthemen laut MEDLINE: Deep Learning, Crops, Agricultural. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 32 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE In India, agriculture is the backbone of economic sectors because of the increasing demand for agricultural products. However, agricultural production has been affected due to the presence of pests in crops. Several methods were developed to solve the crop pest detection issue, but they failed to achieve better results. Therefore, the proposed study used a new hybrid deep learning mechanism for segmenting and detecting pests in crops. METHOD Image collection, pre‐processing, segmentation, and detection are the steps involved in the proposed study. There are three steps involved in pre‐processing: image rescaling, equalized joint histogram based contrast enhancement (Eq‐JH‐CE), and bendlet transform based De‐noising (BT‐D). Next, the pre‐processed images are segmented using the DenseNet‐77 UNet model. In this section, the complexity of the conventional UNet model is mitigated by hybridizing it with the DenseNet‐77 model. Once the segmentation is done with an improved model, the crop pests are detected and classified by proposing a novel Convolutional Slice‐Attention based Gated Recurrent Unit (CS‐AGRU) model. The proposed model is the combination of a convolutional Neural Network (CNN) and a Gated Recurrent Unit (GRU). In order to achieve better accuracy outcomes, the proposed study hybridized these models due to their great efficiency. Also, the slice attention mechanism is applied over the proposed model for fetching relevant feature information and thereby enhancing the computational efficiency. So, pests in the crop are finally detected using the proposed method. RESULT The Python programming language is utilized for implementation. The proposed approach shows a better accuracy range of 99.52%, IoU of 99.1%, precision of 98.88%, recall of 99.53%, F1‐score of 99.35%, and FNR of 0.011 compared to existing techniques. DISCUSSION Identifying and classifying pests helps farmers anticipate potential threats to their crops. By knowing which pests are prevalent in their region or are likely to infest certain crops, farmers can implement preventive measures to protect their crops, such as planting pest‐resistant varieties, using crop rotation, or deploying traps and barriers. © 2024 Society of Chemical Industry.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCrops, AgriculturalImage Processing, Computer-AssistedPest ControlIndia

Stichwörter der Autor:innen

UNet modelagriculturecrop pesthybrid deep learningsegmentation

Autor:innen und Institutionen

  • Department of Computer Science & Engineering, Rao Bahadhur Y Mahabaleswarappa Engineering College, VTU, Belagavi, Karnataka, India.

ORCID-Profile: Nagaveni Biradar

Zitieren

APA

Biradar, N., & Hosalli, G. (2024). Segmentation and detection of crop pests using novel U‐Net with hybrid deep learning mechanism. Pest Management Science. https://doi.org/10.1002/ps.8083

Vancouver

Biradar N, Hosalli G. Segmentation and detection of crop pests using novel U‐Net with hybrid deep learning mechanism. Pest Management Science. 2024. doi:10.1002/ps.8083

BibTeX
@article{Biradar2024,
  author = {Biradar, Nagaveni and Hosalli, Girisha},
  title = {Segmentation and detection of crop pests using novel U‐Net with hybrid deep learning mechanism},
  journal = {Pest Management Science},
  year = {2024},
  doi = {10.1002/ps.8083}
}
Kostenlos starten →