EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Light Attention Encoder–Decoder for Cattle Body Segmentation and Body Weight Estimation

Sahilpreet Singh Mann iD, Halah K Shehada iD, Sabrina T Amorim iD, Dong S Ha, Gota Morota iD, Sook Shin iD

Animals · 08.06.2026 · 16 (12) · 1773

DOI: 10.3390/ani16121773 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animals, online erschienen am 08.06.2026. Verfasst von Sahilpreet Singh Mann und 5 weiteren Autor:innen. Beteiligte Einrichtung: Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, Blacksburg, VA 24061, USA. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate, non-invasive body weight estimation is essential for management and performance monitoring in beef cattle systems, yet conventional scales and manual measurements require animal handling, infrastructure, and labor. This study presents an integrated pipeline that segments cattle from overhead depth images and predicts body weight from extracted image features. The approach uses a Light Attention Encoder–Decoder (LAED) segmentation model combining depthwise separable convolutions, Gaussian Context Transformer (GCT) attention, a multi-scale dilated bottleneck, and dual heads for region and boundary prediction. Depth videos were collected using an overhead Intel RealSense D435 RGB-D camera from 60 beef heifers. To reduce animal-level leakage, leave-one-animal-out cross-validation was used for segmentation. LAED + GCT achieved 96.91% Dice (95% confidence interval (CI): 96.56–97.21%) and 94.22% IoU (95% CI: 93.58–94.77%), while operating at 33.08 frames per second. For weight prediction, biometric traits and deep features were evaluated using random forest, support vector regression, and fully connected neural networks. The best primary-metric body-weight model used biometric traits with support vector regression, achieving MAPE = 6.75%, pooled R2 = 0.68, MAE = 23.92 kg, and RMSE = 31.79 kg. Among FCNN models trained independently within each cattle-level fold, the best result used ResNet50 features and achieved MAPE = 7.76%, a pooled R2 = 0.56, an MAE = 27.60 kg, and an RMSE = 37.07 kg. The mean signed prediction bias for the biometric-SVR model was −1.04 kg, using predicted minus observed body weight, with a bootstrap 95% confidence interval of −9.63 to 7.41 kg. These results support the promise of overhead depth imaging for non-invasive cattle body segmentation and weight estimation, while larger external validation remains necessary.

Schlagwörter

Stichwörter der Autor:innen

U-Netboundary-aware segmentationconvolutional networksdepth mapsgaussian context transformer

Autor:innen und Institutionen

  • Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, Blacksburg, VA 24061, USA.
  • Department of Animal and Food Sciences, Oklahoma State University, Stillwater, OK 74078, USA.
  • Laboratory of Biometry and Bioinformatics, Department of Agricultural and Environmental Biology, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Bunkyo, Tokyo 113-8657, Japan.

ORCID-Profile: Sahilpreet Singh Mann, Halah K Shehada, Sabrina T Amorim, Gota Morota, Sook Shin

Zitieren

APA

Mann, S. S., Shehada, H. K., Amorim, S. T., Ha, D. S., Morota, G., & Shin, S. (2026). Light Attention Encoder–Decoder for Cattle Body Segmentation and Body Weight Estimation. Animals, 16(12), 1773. https://doi.org/10.3390/ani16121773

Vancouver

Mann SS, Shehada HK, Amorim ST, Ha DS, Morota G, Shin S. Light Attention Encoder–Decoder for Cattle Body Segmentation and Body Weight Estimation. Animals. 2026;16(12):1773. doi:10.3390/ani16121773

BibTeX
@article{Mann2026,
  author = {Mann, Sahilpreet Singh and Shehada, Halah K and Amorim, Sabrina T and Ha, Dong S and Morota, Gota and Shin, Sook},
  title = {Light Attention Encoder–Decoder for Cattle Body Segmentation and Body Weight Estimation},
  journal = {Animals},
  year = {2026},
  volume = {16},
  number = {12},
  pages = {1773},
  doi = {10.3390/ani16121773}
}
Kostenlos starten →