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

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.