Improved RT-DETR Combined with Digital Twin for Accurate Posture Detection of Sows
Open Access
- 26 February 2026
- journal article
- research article
- Published by MDPI AG in Agriculture
- Vol. 16 (5) , 509
Abstract
Precise monitoring of sow behaviour is essential for enhancing animal welfare and production efficiency in precision husbandry. This study proposes an improved RT-DETR model to address real-time detection challenges in complex farming environments. By integrating innovative multi-scale feature fusion and lightweight attention mechanisms, the model achieves high-precision detection of four key postures (standing, sitting, sternal recumbency, and lateral recumbency). Experimental results show that the model attains an mAP@0.5 of 96.6% and a processing speed of 56 FPS, significantly outperforming existing methods. Furthermore, a Unity3D-based digital twin system was constructed to enable real-time bidirectional mapping, achieving a low latency of 320 ms. This system proposes a potential technical framework for intelligent pig farm management, providing a reliable tool for automated welfare assessment and operational decision support.Keywords
Funding Information
- National Natural Science Foundation of China (32272929)
- Fundamental Research Funds for the Central Universities (KYCYXT2022019)
- Jiangsu Provincial Key Research and Development Program (BE2021363)
This publication has 32 references indexed in Scilit:
- Real-time detection of blade surface defects based on the improved RT-DETRJournal of Intelligent Manufacturing, 2025
- Slim-neck by GSConv: a lightweight-design for real-time detector architecturesJournal of Real-Time Image Processing, 2024
- End-to-End Object Detection with Transformers2020
- An automatic recognition framework for sow daily behaviours based on motion and image analysesBiosystems Engineering, 2020
- CBAM: Convolutional Block Attention Module2018
- Automatic recognition of lactating sow postures from depth images by deep learning detectorComputers and Electronics in Agriculture, 2018
- Porcine lie detectors: Automatic quantification of posture state and transitions in sows using inertial sensorsComputers and Electronics in Agriculture, 2016
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition2014
- Sow-activity classification from acceleration patterns: A machine learning approachComputers and Electronics in Agriculture, 2013
- Classifying sows’ activity types from acceleration patternsApplied Animal Behaviour Science, 2008