EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Image enhancement for detection of underwater moulted crabs in greenhouse soft-shell crab farming using deep learning

Mohammad Affaiq Bin Aini, Siow Hoo Leong, Yueh Tiam Yong, Beng Yong Lee, Xiaomin Zhao, Sharifah Raina Manaf, Firdaus Abdullah, Heng Yen Khong

Smart Agricultural Technology · 2025-12 · 12 · 101223

DOI: 10.1016/j.atech.2025.101223 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Smart Agricultural Technology, 2025-12. Verfasst von Mohammad Affaiq Bin Aini und 7 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 95 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Universiti Teknologi MARA.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In soft-shell crab farming, collecting the moulted crabs within a narrow window of one hour is crucial to meet the quality of high-graded paper shell crab. This paper incorporates IoT-based computer vision technology and deep learning techniques in greenhouse soft-shell crab farming to detect moulted crabs. The challenges arise in accurately detecting underwater crabs due to wide-angle distortion and reflections in images captured by cameras installed on rails within the greenhouse. Image enhancement methods are proposed to address these challenges and improve the performance of crab detection using the YOLOv7 deep-learning algorithm. Specifically, the performance of two methods for rectifying wide-angle distortion and two methods for removing reflections are compared, respectively. Data augmentation techniques are also applied to overcome the limitation of annotated underwater crab targets for deep-learning training. Results show that the fisheye flattening method outperforms the stretch flattening method for rectifying wide-angle distortion, while 2D-image flat field correction yields better results than the non-local mean filter for reducing reflections. Furthermore, data augmentation significantly enhances crab detection performance. Application of the best image enhancement methods and data augmentation techniques shows a successful rate of 92% in detecting the moulted crabs in greenhouse soft-shell crab farming..

Förderung

  • Universiti Teknologi MARA

Zitieren

APA

Aini, M. A. B., Leong, S. H., Yong, Y. T., Lee, B. Y., Zhao, X., Manaf, S. R., Abdullah, F., & Khong, H. Y. (2025). Image enhancement for detection of underwater moulted crabs in greenhouse soft-shell crab farming using deep learning. Smart Agricultural Technology, 12, 101223. https://doi.org/10.1016/j.atech.2025.101223

Vancouver

Aini MAB, Leong SH, Yong YT, Lee BY, Zhao X, Manaf SR, et al. Image enhancement for detection of underwater moulted crabs in greenhouse soft-shell crab farming using deep learning. Smart Agricultural Technology. 2025;12:101223. doi:10.1016/j.atech.2025.101223

BibTeX
@article{Aini2025,
  author = {Aini, Mohammad Affaiq Bin and Leong, Siow Hoo and Yong, Yueh Tiam and Lee, Beng Yong and Zhao, Xiaomin and Manaf, Sharifah Raina and Abdullah, Firdaus and Khong, Heng Yen},
  title = {Image enhancement for detection of underwater moulted crabs in greenhouse soft-shell crab farming using deep learning},
  journal = {Smart Agricultural Technology},
  year = {2025},
  volume = {12},
  pages = {101223},
  doi = {10.1016/j.atech.2025.101223}
}
Kostenlos starten →