{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T11:02:02Z","timestamp":1785409322266,"version":"3.56.0"},"reference-count":43,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Anhui Provincial Key Laboratory of Smart Agricultural Technology and Equipment","award":["APKLSA-TE2021X004"],"award-info":[{"award-number":["APKLSA-TE2021X004"]}]},{"name":"Natural Science Research Key Project of Anhui Provincial University","award":["2022AH040125"],"award-info":[{"award-number":["2022AH040125"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32371993"],"award-info":[{"award-number":["32371993"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jianghuai Watershed Experimental Station of Anhui Agricultural University and Anhui Darsing Intelligent Technology Co. LTD"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,1,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Having comprehensive access to information on sheep behaviors is essential for acquiring relevant insights into the health status of sheep and preventing diseases promptly. In particular, the ruminating behavior of sheep tends to reflect the health of their digestive system. However, due to the challenging nature of detecting ruminating behavior, traditional research has not yielded satisfactory results. In fact, many computer vision-based methods do not consider ruminating behavior as a distinctive feature for recognizing sheep behavior. To this end, we proposed an efficient model for recognizing active (standing, feeding, drinking, suckling), inactive (kneeling), and ruminating behaviors of sheep flock based on You Only Look Once-v5 (YOLOv5). This model improved the original structure through introducing the latest fully convolutional neural network in the backbone network, thereby reducing parameters cost and improving the classification accuracy. At the same time, the Spatial Pyramid Pooling Cross Stage Partial Connection module from You Only Look Once-v7 was added at the end of the backbone network, which improved the ability of the model to recognize multiscale sheep behaviors by increasing the receptive field. In the neck network part, a new algorithm named Concat optimization algorithm based on channel concatenation (CiConcat) was proposed to optimize the regular Concat operation, which enhanced the filtering ability of the small target detection layer of the model for nonruminating behavior information, thereby improving the ability to accurately extract local details. In addition, Selective Kernel attention mechanism was introduced before the detection head to enhance the feature extraction and expression ability of sheep. Finally, a detection head matching strategy was proposed to promote the accuracy when detecting distant ruminating behavior of sheep. This study used a self-collected and annotated outdoor sheep farm image dataset for experimental validation. The results showed that the improved network achieved the mean Average Precision of 94.1% on outdoor grazing sheep flock images which was more accurate and faster than state-of-the-arts. Simultaneously, the Average Precision for ruminating detection reached 80.2%, showing an improvement of 35.44% compared to YOLOv5, markedly enhancing the accuracy of ruminating behavior recognition. Our model was proved to be able to continuously monitor the behavior frequency of sheep, providing a robust technical foundation for analyzing behavior patterns and understanding the physiological and behavioral needs of sheep.<\/jats:p>","DOI":"10.1093\/jas\/skaf084","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T04:18:56Z","timestamp":1745295536000},"source":"Crossref","is-referenced-by-count":3,"title":["An improved YOLOv5 method for accurate recognition of grazing sheep activities: active, inactive, ruminating behaviors"],"prefix":"10.1093","volume":"103","author":[{"given":"Xiao","family":"Dong","sequence":"first","affiliation":[{"name":"College of Engineering, Anhui Agricultural University , Hefei ,","place":["China"]},{"name":"Anhui Provincial Key Laboratory of Smart Agricultural Technology and Equipment , Hefei ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zirui","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Engineering, Anhui Agricultural University , Hefei ,","place":["China"]},{"name":"Anhui Provincial Key Laboratory of Smart Agricultural Technology and Equipment , Hefei ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Liao","sequence":"additional","affiliation":[{"name":"College of Engineering, Anhui Agricultural University , Hefei ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahong","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Animal Science and Technology, Anhui Agricultural University , Hefei ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shunlong","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Engineering, Anhui Agricultural University , Hefei ,","place":["China"]},{"name":"Anhui Provincial Key Laboratory of Smart Agricultural Technology and Equipment , Hefei ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Rao","sequence":"additional","affiliation":[{"name":"College of Information and Artificial Intelligence, Anhui Agricultural University , Hefei ,","place":["China"]},{"name":"Anhui Provincial Key Laboratory of Smart Agricultural Technology and Equipment , Hefei ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"2025052714112621100_CIT0001","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/electronics9081295","article-title":"The k-means algorithm: a comprehensive survey and performance evaluation","volume":"9","author":"Ahmed","year":"2020","journal-title":"Electronics (Switzerland)"},{"key":"2025052714112621100_CIT0002","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.applanim.2010.09.010","article-title":"A meta-analysis of the combined effect of housing and environmental enrichment characteristics on the behaviour and performance of pigs","volume":"127","author":"Aver\u00f3s","year":"2010","journal-title":"Appl. Anim. Behav. Sci"},{"key":"2025052714112621100_CIT0003","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/DeSE60595.2023.10469582","article-title":"A non-restraining sheep activity detection and surveillance using deep machine learning","author":"Ayub","year":"2023"},{"key":"2025052714112621100_CIT0004","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934","volume-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"key":"2025052714112621100_CIT0005","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1304.6478","volume-title":"The K-modes algorithm for clustering","author":"Carreira-Perpi\u00f1\u00e1n","year":"2013"},{"key":"2025052714112621100_CIT0006","doi-asserted-by":"publisher","first-page":"107010","DOI":"10.1016\/j.compag.2022.107010","article-title":"Application of deep learning in sheep behaviors recognition and influence analysis of training data characteristics on the recognition effect","volume":"198","author":"Cheng","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"2025052714112621100_CIT0007","doi-asserted-by":"publisher","first-page":"108143","DOI":"10.1016\/j.compag.2023.108143","article-title":"A two-stage recognition method based on deep learning for sheep behavior","volume":"212","author":"Gu","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"2025052714112621100_CIT0008","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","author":"He","year":"2014"},{"key":"2025052714112621100_CIT0009","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","volume-title":"Deep","author":"He","year":"2015"},{"key":"2025052714112621100_CIT0010","doi-asserted-by":"publisher","first-page":"13713","DOI":"10.48550\/arXiv.2103.02907","volume-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"},{"key":"2025052714112621100_CIT0011","doi-asserted-by":"publisher","first-page":"1314","DOI":"10.1109\/ICCV.2019.00140","volume-title":"Searching for MobileNetV3","author":"Howard","year":"2019"},{"key":"2025052714112621100_CIT0012","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00746","volume-title":"Squeeze-and-Excitati","author":"Hu","year":"2019"},{"issue":"10","key":"2025052714112621100_CIT0013","doi-asserted-by":"publisher","first-page":"4752","DOI":"10.3390\/s23104752","article-title":"Grazing sheep behaviour recognition based on improved YOLOV5","volume":"23","author":"Hu","year":"2023","journal-title":"Sensors"},{"key":"2025052714112621100_CIT0014","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.489","volume-title":"Densely con","author":"Huang","year":"2016"},{"key":"2025052714112621100_CIT0015","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.applanim.2004.10.020","article-title":"Thermal behaviour of growing pigs in response to high temperature and humidity","volume":"91","author":"Huynh","year":"2005","journal-title":"Appl. Anim. Behav. Sci"},{"key":"2025052714112621100_CIT0016","doi-asserted-by":"publisher","first-page":"105706","DOI":"10.1016\/j.compag.2020.105706","article-title":"Automatic behavior recognition of group-housed goats using deep learning","volume":"177","author":"Jiang","year":"2020","journal-title":"Comput. Electron. Agric"},{"key":"2025052714112621100_CIT0017","doi-asserted-by":"publisher","first-page":"108894","DOI":"10.1016\/j.compag.2024.108894","article-title":"Behavior classification and spatiotemporal analysis of grazing sheep using deep learning","volume":"220","author":"Jin","year":"2024","journal-title":"Comput. Electron. Agric"},{"key":"2025052714112621100_CIT0018","article-title":"ultralytics\/yolov5: v6. 0-YOLOv5n\u2019Nano\u2019models","author":"Jocher","year":"2021"},{"key":"2025052714112621100_CIT0019","doi-asserted-by":"publisher","first-page":"110027","DOI":"10.1016\/j.dib.2024.110027","article-title":"Video dataset of sheep activity for animal behavioral analysis via deep learning","volume":"52","author":"Kelly","year":"2024","journal-title":"Data Brief"},{"key":"2025052714112621100_CIT0020","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60796-8_35","article-title":"Feature extraction and random forest to identify sheep behavior from accelerometer data","volume-title":"Intelligent computing methodologies","author":"Kleanthous","year":"2020"},{"key":"2025052714112621100_CIT0021","doi-asserted-by":"publisher","first-page":"117925","DOI":"10.1016\/j.eswa.2022.117925","article-title":"Deep transfer learning in sheep activity recognition using accelerometer data","volume":"207","author":"Kleanthous","year":"2022","journal-title":"Expert Syst. Appl"},{"key":"2025052714112621100_CIT0022","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1109\/CVPR.2019.00060","volume-title":"Selective","author":"Li","year":"2019"},{"key":"2025052714112621100_CIT0023","doi-asserted-by":"publisher","first-page":"2117","DOI":"10.1109\/CVPR.2017.106","volume-title":"Feature pyramid networks for object detection","author":"Lin","year":"2016"},{"key":"2025052714112621100_CIT0024","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"SSD: single shot MultiBox detector","author":"Liu","year":"2016"},{"key":"2025052714112621100_CIT0025","doi-asserted-by":"publisher","first-page":"8759","DOI":"10.1109\/CVPR.2018.00913","volume-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018"},{"key":"2025052714112621100_CIT0026","doi-asserted-by":"publisher","first-page":"10012","DOI":"10.1109\/ICCV48922.2021.00986","volume-title":"Swin transformer: hierarchical vision transformer using shifted w","author":"Liu","year":"2021"},{"key":"2025052714112621100_CIT0027","doi-asserted-by":"publisher","first-page":"11976","DOI":"10.48550\/arXiv.2201.03545","article-title":"A ConvNet for the 2020s","author":"Liu","year":"2022"},{"key":"2025052714112621100_CIT0029","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1506.02640","volume-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"2025052714112621100_CIT0030","year":"."},{"key":"2025052714112621100_CIT0031","doi-asserted-by":"publisher","first-page":"3398","DOI":"10.3168\/jds.2017-12686","article-title":"Evaluation of an ear-tag-based accelerometer for monitoring rumination in dairy cows","volume":"101","author":"Reiter","year":"2018","journal-title":"J. Dairy Sci"},{"key":"2025052714112621100_CIT0032","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume-title":"Faster R-CNN: towards real-time object detection wit","author":"Ren","year":"2016"},{"key":"2025052714112621100_CIT0033","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.107217","article-title":"Technological revolutions in smart","volume-title":"Computers and electronics in agriculture","author":"Sharma","year":"2022"},{"key":"2025052714112621100_CIT0034","doi-asserted-by":"publisher","first-page":"7422","DOI":"10.3168\/jds.2016-11352","article-title":"Use of rumination and activity monitoring for the identification of dairy cows with health disorders: Part III. Metritis","volume":"99","author":"Stangaferro","year":"2016","journal-title":"J. Dairy Sci"},{"key":"2025052714112621100_CIT0035","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1038\/sj.bjc.6603525","article-title":"ASPP: a new family of oncogenes and tumour suppressor genes","volume":"96","author":"Sullivan","year":"2007","journal-title":"Br J Cancer"},{"key":"2025052714112621100_CIT0036","doi-asserted-by":"publisher","first-page":"e01510","DOI":"10.1016\/j.gecco.2021.e01510","article-title":"Giant panda behaviour recognition using images","volume":"26","author":"Swarup","year":"2021","journal-title":"Global Ecol. Conserv"},{"key":"2025052714112621100_CIT0037","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.11946","volume-title":"EfficientNet: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"2025052714112621100_CIT0038","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.inpa.2022.04.001","article-title":"Deep learning based classification of sheep behaviour from accelerometer data with imbalance","volume":"10","author":"Turner","year":"2023","journal-title":"Inf Process Agric"},{"key":"2025052714112621100_CIT0039","doi-asserted-by":"publisher","first-page":"5998","DOI":"10.48550\/arXiv.1706.03762","volume-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"2025052714112621100_CIT0040","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1109\/CVPRW50498.2020.00203","volume-title":"CSPNet: a new backbone that can enhance learning capability of CNN","author":"Wang","year":"2019"},{"key":"2025052714112621100_CIT0041","doi-asserted-by":"publisher","first-page":"11534","DOI":"10.1109\/CVPR42600.2020.01155","volume-title":"ECA-Net: efficient channel attention for deep convolutional neural networks","author":"Wang","year":"2020"},{"key":"2025052714112621100_CIT0042","doi-asserted-by":"publisher","first-page":"7464","DOI":"10.1109\/CVPR52729.2023.00721","volume-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time o","author":"Wang","year":"2022"},{"key":"2025052714112621100_CIT0043","doi-asserted-by":"publisher","first-page":"3","DOI":"10.48550\/arXiv.1807.06521","volume-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"2025052714112621100_CIT0044","doi-asserted-by":"publisher","first-page":"108171","DOI":"10.1016\/j.compag.2023.108171","article-title":"Non-contact sensing technology enables precision livestock farming in smart farms","volume":"212","author":"Yin","year":"2023","journal-title":"Comput. Electron. Agric."}],"container-title":["Journal of Animal Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jas\/advance-article-pdf\/doi\/10.1093\/jas\/skaf084\/62963150\/skaf084.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jas\/article-pdf\/doi\/10.1093\/jas\/skaf084\/62963150\/skaf084.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jas\/article-pdf\/doi\/10.1093\/jas\/skaf084\/62963150\/skaf084.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T18:11:35Z","timestamp":1748369495000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jas\/article\/doi\/10.1093\/jas\/skaf084\/8117208"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1093\/jas\/skaf084","relation":{},"ISSN":["0021-8812","1525-3163"],"issn-type":[{"value":"0021-8812","type":"print"},{"value":"1525-3163","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2025]]},"article-number":"skaf084"}}