Multimodal Feature-Driven Deep Learning for the Prediction of Duck Body Dimensions and Weight

2025-03-18

AI Summary

This study addresses the need for non-contact, high-precision estimation of body dimensions and weight in poultry farming—specifically for ducks. We propose a multimodal deep learning framework that jointly leverages RGB images, depth maps, and 3D point clouds. To our knowledge, this is the first work to introduce PointNet++ into poultry morphometric analysis; it innovatively integrates keypoint features from 3D point clouds, multi-view 2D convolutional representations, and Transformer-based long-range dependency modeling for end-to-end prediction. Evaluated on eight morphological parameters, the method achieves a mean absolute percentage error (MAPE) of 6.33% and an R² score of 0.953—significantly outperforming conventional manual measurements. Crucially, the entire process is fully contactless, minimizing handling-induced stress and thereby advancing the intelligence and precision of modern poultry farming systems.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate body dimension and weight measurements are critical for optimizing poultry management, health assessment, and economic efficiency. This study introduces an innovative deep learning-based model leveraging multimodal data-2D RGB images from different views, depth images, and 3D point clouds-for the non-invasive estimation of duck body dimensions and weight. A dataset of 1,023 Linwu ducks, comprising over 5,000 samples with diverse postures and conditions, was collected to support model training. The proposed method innovatively employs PointNet++ to extract key feature points from point clouds, extracts and computes corresponding 3D geometric features, and fuses them with multi-view convolutional 2D features. A Transformer encoder is then utilized to capture long-range dependencies and refine feature interactions, thereby enhancing prediction robustness. The model achieved a mean absolute percentage error (MAPE) of 6.33% and an R2 of 0.953 across eight morphometric parameters, demonstrating strong predictive capability. Unlike conventional manual measurements, the proposed model enables high-precision estimation while eliminating the necessity for physical handling, thereby reducing animal stress and broadening its application scope. This study marks the first application of deep learning techniques to poultry body dimension and weight estimation, providing a valuable reference for the intelligent and precise management of the livestock industry with far-reaching practical significance.

Problem

• Non-invasive estimation of duck body dimensions and weight
• Utilizes multimodal data for deep learning-based prediction
• Enhances poultry management and reduces animal stress

Innovation

• Uses multimodal data for duck body estimation
• Integrates PointNet++ for 3D feature extraction
• Employs Transformer encoder for feature refinement