2026-03-08T16:49:41Z https://iwate-u.repo.nii.ac.jp/oai

oai:iwate-u.repo.nii.ac.jp:02001335 2026-01-07T06:58:55Z 1504:1510 1515:1519

Advanced Dairy Cow Monitoring : Enhanced Detection with Precision 3D Tracking WANG, Ranran Shandong Agricultural University LI, Yingxiu Shandong Agricultural University YUE, Peng University of Sheffield YUAN, Chunhong Iwate University TIAN, Fuyang Shandong Agricultural University LU, Xin Iwate University open access Dairy cow monitoring Multi-target detection Multi-target tracking YOLOv5 DeepSORT Ensuring the welfare of dairy cows requires precise monitoring of their daily exercise to evaluate their physical health. This necessitates innovative methods beyond traditional motion sensors. We present a novel method that integrates an enhanced YOLOv5s object detection model with the DeepSORT multi-object tracking algorithm to meticulously track dairy cow movements, providing holistic information about their health. Our research started with the establishment of a dedicated dataset tailored for cow detection. We then segmented the detection scope to focus on specific regions of interest. Within the modified YOLOv5s model, we replaced the standard CSPDarknet53 backbone with DenseNet to achieve deep separable convolution and feature reorganization modules, leading to reduced parameters, augmented feature expression, and better information flow. In particular, the SPD-Conv module was incorporated to retain intricate details, essential for detecting smaller and low-resolution targets. The transition from Generalized Intersection over Union (GIoU) Loss to Complete Intersection over Union (CIoU) loss improved detection accuracy and sped up model convergence. Our clustering approach, based on the elbow rule, optimized K-means clustering, enhancing speed and precision. For multi-object tracking, the DeepSORT model was tailored to cater to varying cow sizes, and we chose an algorithm to associate appearance information. We converted pixel data into real-world distances, providing exact 3D cow movement metrics. Experimental validation confirmed the efficacy of our approach. Our enhanced model surpassed the original YOLOv5s in performance by 11.1% for accuracy (97.4%), 9.6% for recall (97.8%), and 11.0% for average accuracy (98.2%). The comprehensive accuracy stood at 92.1% for our model. In conclusion, our innovative methodology offers a non-invasive means to monitor dairy cow exercise, paving the way for advanced health assessment techniques in the dairy sector. This work was supported by the National Key Technologies Research and Development Program of China, Subproject: 'Development of an Intelligent Inspection Robot for Health Assessment in Beef Cattle Factory Farming' (Project No. 2023YFD2000704-2). This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/s11042-024-19791-8 Springer Nature 2024-07-13 eng departmental bulletin paper AM https://doi.org/10.15113/0002001335 https://iwate-u.repo.nii.ac.jp/records/2001335 10.15113/0002001335 https://doi.org/10.1007/s11042-024-19791-8 1573-7721 Multimedia Tools and Applications 84 30 19117 19146 https://iwate-u.repo.nii.ac.jp/record/2001335/files/mta-v84p19117-19146.pdf application/pdf 6 MB 2026-01-07