EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ReViTA-Unet: An Enhanced Semantic Segmentation Model for Automated Morphometric Analysis of Macrobrachium rosenbergii

Dawei Sun, Qi Chen iD, Guanghui Yu, Xinran Han, Chen Li iD, Chengquan Zhou, Hongbao Ye

Sensors · 19.07.2026 · 26 (14) · 4570

DOI: 10.3390/s26144570 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.07.2026. Verfasst von Dawei Sun und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Agricultural Equipment, Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, China. Hauptthemen laut MEDLINE: Palaemonidae, Image Processing, Computer-Assisted. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Research and Development Program of Zhejiang Province, Zhejiang Province "San Nong Jiu Fang" Project, Zhejiang Province “San Nong Jiu Fang” Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate morphometric analysis of Macrobrachium rosenbergii is essential for selective breeding, growth monitoring, and precision aquaculture, yet conventional manual measurements are labor-intensive, time-consuming, and prone to operator variability. This study presents ReViTA-UNet, an automated, non-contact morphometric analysis framework based on an enhanced semantic segmentation network coupled with a geometric topology refinement algorithm to accurately extract multiple morphological traits. The proposed framework integrates complementary feature extraction to improve segmentation of elongated anatomical structures and complex body boundaries. A complete automated measurement system was subsequently developed to convert segmented images into biologically meaningful morphometric parameters. The results demonstrated that ReViTA-UNet achieved a Dice coefficient of 97.7%, a mean Intersection over Union (mIoU) of 96.7%, a precision of 98.3%, and a recall of 98.4%, outperforming eight representative semantic segmentation models. The automated measurement system achieved a mean absolute percentage error of 1.83% for body length, with strong agreement with manual measurements (R2 = 0.987), while maintaining high accuracy for other major morphometric traits. These results indicate that the proposed framework provides an accurate and efficient solution for automated prawn phenotyping under controlled imaging conditions. It establishes a practical foundation for future intelligent aquaculture applications following validation under commercial farming environments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PalaemonidaeImage Processing, Computer-AssistedAnimalsAlgorithmsSemantics

Stichwörter der Autor:innen

Macrobrachium rosenbergiideep learningprawnprecision agriculturevision transformer

Autor:innen und Institutionen

  • Institute of Agricultural Equipment, Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, China.
  • Key Laboratory of Agricultural Equipment for Hilly and Mountainous Areas in Southeastern China (Co-Construction by Ministry and Province), Ministry of Agriculture and Rural Affairs, Hangzhou 310021, China.
  • East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai 200090, China.

ORCID-Profile: Qi Chen, Chen Li

Förderung

  • Key Research and Development Program of Zhejiang Province
  • Zhejiang Province "San Nong Jiu Fang" Project
  • Zhejiang Province “San Nong Jiu Fang” Project

Zitieren

APA

Sun, D., Chen, Q., Yu, G., Han, X., Li, C., Zhou, C., & Ye, H. (2026). ReViTA-Unet: An Enhanced Semantic Segmentation Model for Automated Morphometric Analysis of Macrobrachium rosenbergii. Sensors, 26(14), 4570. https://doi.org/10.3390/s26144570

Vancouver

Sun D, Chen Q, Yu G, Han X, Li C, Zhou C, et al. ReViTA-Unet: An Enhanced Semantic Segmentation Model for Automated Morphometric Analysis of Macrobrachium rosenbergii. Sensors. 2026;26(14):4570. doi:10.3390/s26144570

BibTeX
@article{Sun2026,
  author = {Sun, Dawei and Chen, Qi and Yu, Guanghui and Han, Xinran and Li, Chen and Zhou, Chengquan and Ye, Hongbao},
  title = {ReViTA-Unet: An Enhanced Semantic Segmentation Model for Automated Morphometric Analysis of Macrobrachium rosenbergii},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4570},
  doi = {10.3390/s26144570}
}
Kostenlos starten →