数字农科院2.0

Non-Contact Measurement of Pregnant Sows' Backfat Thickness Based on a Hybrid CNN-ViT Model

文献类型： 外文期刊

作者： Li, Xuan;Yu, Mengyuan;Xu, Dihong;Zhao, Shuhong;Tan, Hequn;Liu, Xiaolei

作者机构：

关键词： backfat thickness;non-contact measurement;Vision Transformer;pregnant sow;self-attention

期刊名称： AGRICULTURE-BASEL

ISSN：

年卷期： 2023 年 13 卷 7 期

页码：

收录情况： SCIE（2023版）

摘要： Backfat thickness (BF) is closely related to the service life and reproductive performance of sows. The dynamic monitoring of sows' BF is a critical part of the production process in large-scale pig farms. This study proposed the application of a hybrid CNN-ViT (Vision Transformer, ViT) model for measuring sows' BF to address the problems of high measurement intensity caused by the traditional contact measurement of sows' BF and the low efficiency of existing non-contact models for measuring sows' BF. The CNN-ViT introduced depth-separable convolution and lightweight self-attention, mainly consisting of a Pre-local Unit (PLU), a Lightweight ViT (LViT) and an Inverted Residual Unit (IRU). This model could extract local and global features of images, making it more suitable for small datasets. The model was tested on 106 pregnant sows with seven randomly divided datasets. The results showed that the CNN-ViT had a Mean Absolute Error (MAE) of 0.83 mm, a Root Mean Square Error (RMSE) of 1.05 mm, a Mean Absolute Percentage Error (MAPE) of 4.87% and a coefficient of determination (R-Square, R-2) of 0.74. Compared to LviT-IRU, PLU-IRU and PLU-LviT, the CNN-ViT's MAE decreased by more than 12%, RMSE decreased by more than 15%, MAPE decreased by more than 15% and R-2 improved by more than 17%. Compared to the Resnet50 and ViT, the CNN-ViT's MAE decreased by more than 7%, RMSE decreased by more than 13%, MAPE decreased by more than 7% and R-2 improved by more than 15%. The method could better meet the demand for the non-contact automatic measurement of pregnant sows' BF in actual production and provide technical support for the intelligent management of pregnant sows.

分类号：

  • 相关文献

[1]细粒度图像分类上Vision Transformer的发展综述. 孙露露,刘建平,王健,邢嘉璐,张越,王晨阳. 2024

[2]Crop Land Change Detection with MC&N-PSPNet. Yuxin Chen,Yulin Duan,Wen Zhang,Chang Wang,Qiangyi Yu,Xu Wang. 2024

[3]Robot Dexterous Grasping in Cluttered Scenes Based on Single-View Point Cloud. Zhao, Qingxing,Zheng, Minhua,Li, Zhaoxin,Huang, Shichang,Shi, Wen. 2025

[4]LOGOWheat: deep learning–based prediction of regulatory effects for noncoding variants in wheats. Lingpeng Kong,Hong Cheng,Kun Zhu,Bo Song. 2025

[5]Single nucleotide polymorphism of CACNA2D1 gene and its association with milk somatic cell score in cattle. Yuan, Zheng Rong,Li, Jiao,Liu, Li,Zhang, Lu Pei,Zhang, Li Min,Chen, Cui,Chen, Xiao Jie,Gao, Xue,Li, Jun Ya,Chen, Jin Bao,Gao, Hui Jiang,Xu, Shang Zhong.

[6]Expression and Genetic Effects of GLI Pathogenesis-Related 1 Gene on Backfat Thickness in Pigs. Xin Liu,Hanmei Li,Longchao Zhang,Ligang Wang,Lixian Wang. 2022

[7]Integrating genome-wide association studies and population genomics analysis reveals the genetic architecture of growth and backfat traits in pigs. Liangyu Shi,Ligang Wang,Lingzhao Fang,Mianyan Li,Jingjing Tian,Lixian Wang,Fuping Zhao. 2022

[8]Research on Contactless Detection of Sow Backfat Thickness Based on Segmented Images with Feature Visualization. Cao, Tingjin,Li, Xuan,Liu, Xiaolei,Liang, Hao,Wang, Haiyan,Xu, Dihong. 2024

[9]Rice leaf disease identification by residual-distilled transformer. Changjian Zhou,Yujie Zhong,Sihan Zhou,Jia Song,Wensheng Xiang. 2023

[10]SFCE-VT: Spatial feature fusion and contrast-enhanced visual transformer for fine-grained agricultural pests visual classification. Jian Ping Liu,Lulu Sun,Guomin Zhou,Jian Wang,Jialu Xing,Chenyang Wang. 2025

[11]Intelligent vineyard blade density measurement method incorporating a lightweight vision transformer. Shan Ke,Guowei Dai,Hui Pan,Bowen Jin. 2024

[12]ViTKAB: an efficient deep learning network for cotton leaf disease identification. Xu, Laixiang,Song, Hongyun,Yang, Xiaodong,Xu, Peng,Cai, Zhaopeng. 2025

作者其他论文 更多>>