Agreement-Driven Multi-View 3D Reconstruction for Live Cattle Weight Estimation

TL;DR

This paper presents a cost-effective, non-contact 3D reconstruction method using multi-view RGB images and agreement-guided fusion to accurately estimate live cattle weight, emphasizing practical farm deployment.

Contribution

It introduces a novel agreement-guided fusion technique for 3D reconstruction and compares classical and deep learning models under low-data conditions for cattle weight estimation.

Findings

SAM 3D with multi-view agreement fusion outperforms other methods.

Classical ensemble models show consistent performance in practical scenarios.

Improving reconstruction quality is more crucial than increasing model complexity.

Abstract

Accurate cattle live weight estimation is vital for livestock management, welfare, and productivity. Traditional methods, such as manual weighing using a walk-over weighing system or proximate measurements using body condition scoring, involve manual handling of stock and can impact productivity from both a stock and economic perspective. To address these issues, this study investigated a cost-effective, non-contact method for live weight calculation in cattle using 3D reconstruction. The proposed pipeline utilized multi-view RGB images with SAM 3D-based agreement-guided fusion, followed by ensemble regression. Our approach generates a single 3D point cloud per animal and compares classical ensemble models with deep learning models under low-data conditions. Results show that SAM 3D with multi-view agreement fusion outperforms other 3D generation methods, while classical ensemble models provide the most consistent performance for practical farm scenarios (R$^2$ = 0.69 $\pm$ 0.10, MAPE = 2.22 $\pm$ 0.56 \%), making this practical for on-farm implementation. These findings demonstrate that improving reconstruction quality is more critical than increasing model complexity for scalable deployment on farms where producing a large volume of 3D data is challenging.