文献类型： 外文期刊

作者： Xiao, Wenbo ¹ ; Han, Qiannan ¹ ; Shu, Gang ⁴ ; Liang, Guiping ¹ ; Zhang, Hongyan ¹ ; Wang, Song ¹ ; Xu, Zhihao ¹ ; Wan, Weican ² ; Li, Chuang ² ; Jiang, Guitao ² ; Xiao, Yi ¹ ;

作者机构： 1.Hunan Agr Univ, Coll Informat & Technol, Changsha 410128, Peoples R China

2.Hunan Acad Agr Sci, Inst Anim Sci & Vet Med, Changsha 410131, Peoples R China

3.Univ New South Wales, Sch Comp Sci & Engn, Sydney, NSW 2052, Australia

4.Sichuan Agr Univ, Coll Anim Sci & Technol, Chengdu 611130, Peoples R China

关键词： poultry; weight prediction; body dimension prediction; multimodal fusion; deep learning; point cloud

期刊名称：AGRICULTURE-BASEL （ 影响因子：3.6； 五年影响因子：3.8 ）

ISSN：

年卷期： 2025 年 15 卷 10 期

页码：

收录情况： SCI

摘要： 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 1023 Linwu ducks, comprising over 5000 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 5.73% and an R2 of 0.953 across seven morphometric parameters describing body dimensions, and an MAPE of 10.49% with an R2 of 0.952 for body weight, indicating robust and consistent predictive performance across both structural and mass-related phenotypes. 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.