EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A deep segmentation architecture for grasshopper detection using a squeeze-and-excitation attention convolutional U-Net

JUTANG PHYLLA SWER, DEBDATTA KANDAR, GOUTAM SAHA

Turkish Journal of Electrical Engineering and Computer Sciences · 13.11.2026 · 34 (6) · 1054-1068

DOI: 10.55730/1300-0632.4289 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Turkish Journal of Electrical Engineering and Computer Sciences, online erschienen am 13.11.2026. Verfasst von JUTANG PHYLLA SWER und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Grasshoppers can seriously harm crops, but it can be challenging to identify them in field images because they might appear in different lighting settings and blend in with the background. A U-Net-based grasshopper segmentation model is presented in this study. MobileNetV2 is used as the encoder to reduce computational cost, while squeeze-and-excitation blocks are combined with the decoder to improve feature selection during segmentation. An exclusive dataset of 4743 manually annotated RGB images taken from rice fields in Meghalaya, in India's Ri Bhoi District, was used to test the model. Two separate training runs with different random seeds were carried out using the same fixed training-validation split. A mean Dice score of 0.9052 ± 0.0022 and a mean intersection over union value of 0.8278 ± 0.0032 were attained using the proposed model. Approximately 11.57 million parameters and 56.988 billion floating point operations are needed for the model. It was also contrasted with DeepLabV3+, the conventional U-Net, and other U-Net variations. Further experiments were conducted using partial occlusion, blur, and brightness adjustments. The results show that the proposed model achieves good segmentation performance with reduced computational cost compared with the standard U-Net, although its performance decreases under strong occlusion.

Zitieren

APA

SWER, J. P., KANDAR, D., & SAHA, G. (2026). A deep segmentation architecture for grasshopper detection using a squeeze-and-excitation attention convolutional U-Net. Turkish Journal of Electrical Engineering and Computer Sciences, 34(6), 1054-1068. https://doi.org/10.55730/1300-0632.4289

Vancouver

SWER JP, KANDAR D, SAHA G. A deep segmentation architecture for grasshopper detection using a squeeze-and-excitation attention convolutional U-Net. Turkish Journal of Electrical Engineering and Computer Sciences. 2026;34(6):1054-1068. doi:10.55730/1300-0632.4289

BibTeX
@article{SWER2026,
  author = {SWER, JUTANG PHYLLA and KANDAR, DEBDATTA and SAHA, GOUTAM},
  title = {A deep segmentation architecture for grasshopper detection using a squeeze-and-excitation attention convolutional U-Net},
  journal = {Turkish Journal of Electrical Engineering and Computer Sciences},
  year = {2026},
  volume = {34},
  number = {6},
  pages = {1054--1068},
  doi = {10.55730/1300-0632.4289}
}
Kostenlos starten →