{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T11:15:47Z","timestamp":1750072547484,"version":"3.37.3"},"reference-count":32,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007925","name":"Huazhong Agricultural University","doi-asserted-by":"publisher","award":["2018YFD0700804"],"award-info":[{"award-number":["2018YFD0700804"]}],"id":[{"id":"10.13039\/501100007925","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Robotics"],"published-print":{"date-parts":[[2021,4,19]]},"abstract":"<jats:p>How to realize the accurate recognition of 3 parts of sheep carcass is the key to the research of mutton cutting robots. The characteristics of each part of the sheep carcass are connected to each other and have similar features, which make it difficult to identify and detect, but with the development of image semantic segmentation technology based on deep learning, it is possible to explore this technology for real-time recognition of the 3 parts of the sheep carcass. Based on the ICNet, we propose a real-time semantic segmentation method for sheep carcass images. We first acquire images of the sheep carcass and use augmentation technology to expand the image data, after normalization, using LabelMe to annotate the image and build the sheep carcass image dataset. After that, we establish the ICNet model and train it with transfer learning. The segmentation accuracy, MIoU, and the average processing time of single image are then obtained and used as the evaluation standard of the segmentation effect. In addition, we verify the generalization ability of the ICNet for the sheep carcass image dataset by setting different brightness image segmentation experiments. Finally, the U-Net, DeepLabv3, PSPNet, and Fast-SCNN are introduced for comparative experiments to further verify the segmentation performance of the ICNet. The experimental results show that for the sheep carcass image datasets, the segmentation accuracy and MIoU of our method are 97.68% and 88.47%, respectively. The single image processing time is 83\u2009ms. Besides, the MIoU of U-Net and DeepLabv3 is 0.22% and 0.03% higher than the ICNet, but the processing time of a single image is longer by 186\u2009ms and 430\u2009ms. Besides, compared with the PSPNet and Fast-SCNN, the MIoU of the ICNet model is increased by 1.25% and 4.49%, respectively. However, the processing time of a single image is shorter by 469\u2009ms and expands by 7\u2009ms, respectively.<\/jats:p>","DOI":"10.1155\/2021\/8847984","type":"journal-article","created":{"date-parts":[[2021,4,21]],"date-time":"2021-04-21T02:34:28Z","timestamp":1618972468000},"page":"1-12","source":"Crossref","is-referenced-by-count":5,"title":["A Real-Time Semantic Segmentation Method of Sheep Carcass Images Based on ICNet"],"prefix":"10.1155","volume":"2021","author":[{"given":"Shida","family":"Zhao","sequence":"first","affiliation":[{"name":"Departments of Engineering, University of Huazhong Agricultural, Wuhan, Hubei 430070, China"},{"name":"Key Laboratory of Agricultural Equipment in the Mid-lower Yanze River, Ministry of Agriculture and Rural Affairs, Wuhan, Hubei 430070, China"}]},{"given":"Guangzhao","family":"Hao","sequence":"additional","affiliation":[{"name":"Departments of Engineering, University of Huazhong Agricultural, Wuhan, Hubei 430070, China"},{"name":"Key Laboratory of Agricultural Equipment in the Mid-lower Yanze River, Ministry of Agriculture and Rural Affairs, Wuhan, Hubei 430070, China"}]},{"given":"Yichi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Departments of Engineering, University of Huazhong Agricultural, Wuhan, Hubei 430070, China"},{"name":"Key Laboratory of Agricultural Equipment in the Mid-lower Yanze River, Ministry of Agriculture and Rural Affairs, Wuhan, Hubei 430070, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8915-131X","authenticated-orcid":true,"given":"Shucai","family":"Wang","sequence":"additional","affiliation":[{"name":"Departments of Engineering, University of Huazhong Agricultural, Wuhan, Hubei 430070, China"},{"name":"Key Laboratory of Agricultural Equipment in the Mid-lower Yanze River, Ministry of Agriculture and Rural Affairs, Wuhan, Hubei 430070, China"}]}],"member":"311","reference":[{"issue":"2","key":"1","first-page":"35","article-title":"\u201cImport and export situation: import and export situation: lamb imports continue to increase trade and the deficit has expanded significantly","volume":"521","author":"Azouz","year":"2019","journal-title":"China Animal Industry"},{"article-title":"National data","year":"2019","author":"National Bureau of Statistics","key":"2"},{"issue":"1","key":"3","first-page":"1","article-title":"Current situation and future trend of meat processing technology in China","author":"D. Zhang","year":"2020","journal-title":"Meat Research"},{"issue":"3","key":"4","first-page":"31","article-title":"Current status, issues and conutermeasures of sheep slaughtering and processing industry in China","volume":"4","author":"D. Cun-Zhe","year":"2014","journal-title":"Meat Research"},{"issue":"8","key":"5","first-page":"27","article-title":"Development trend and current situation of key technology and equipment in sheep slaughtering and processing in China","volume":"41","author":"N. Guo","year":"2020","journal-title":"Meat Industry"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.6041\/j.issn.1000-1298.2016.11.042"},{"issue":"8","key":"7","first-page":"2396","article-title":"Measuring system of sheep body size based on embedded machine vison","volume":"22","author":"Z. Lin","year":"2014","journal-title":"Computer Measurement & Control"},{"issue":"23","key":"8","first-page":"21","article-title":"Discrimination of chilled lamb in different parts under different storage time based on mobile phone images","volume":"41","author":"L. Meng","year":"2020","journal-title":"Food Science"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfoodeng.2007.01.003"},{"issue":"1","key":"10","first-page":"183","article-title":"Qualitative analysis of mutton freshness by hyperspectral imaging based on BP and adaboost-BP neural network","volume":"55","author":"Z. Fan","year":"2018","journal-title":"Xinjiang Agricultural Sciences"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfoodeng.2010.12.024"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/3738108"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/1520686"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8866406"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.11975\/j.issn.1002-6819.2018.18.024"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.11975\/j.issn.1002-6819.2018.02.028"},{"issue":"5","key":"18","first-page":"66","article-title":"The auto-question answering system based on convolution neural network","volume":"2017","author":"L. Jin","year":"2017","journal-title":"Journal of East China Normal University: Natural Science"},{"issue":"8","key":"19","first-page":"270","article-title":"Real-time detection method of newborn piglets based on deep convolution neural network","volume":"50","author":"M. Shen","year":"2019","journal-title":"Transcations of the Chinese Society of Agricultural Engineering"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.6041\/j.issn.1000-1298.2019.04.020"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.11975\/j.issn.1002-6819.2017.23.028"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105528"},{"issue":"6","key":"23","first-page":"125","article-title":"Automatic segmentation of sheep skeleton based on machine vision and machine learning","volume":"36","author":"Z. Li","year":"2020","journal-title":"Food & Machinery"},{"issue":"9","key":"24","first-page":"116","article-title":"Segmentation of sheep rib image based on U-type convolution neural network","volume":"36","author":"S. Zhao","year":"2020","journal-title":"Food & Machinery"},{"article-title":"Icnet for real-time semantic segmentation on high-resolution images","year":"2017","author":"H. Zhao","key":"25"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"author":"L. C. Chen","key":"27","article-title":"Rethinking atrous convolution for semantic image seg-mentation"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"first-page":"91","article-title":"Faster r-cnn: towards real-time object detection with region proposal networks","author":"S. Ren","key":"29"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2644615"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"author":"A. Paszke","key":"32","article-title":"Enet: a deep neural network architecture for real-time semantic segmentation"}],"container-title":["Journal of Robotics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/jr\/2021\/8847984.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/jr\/2021\/8847984.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/jr\/2021\/8847984.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,21]],"date-time":"2021-04-21T02:34:46Z","timestamp":1618972486000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/jr\/2021\/8847984\/"}},"subtitle":[],"editor":[{"given":"Ramadoni","family":"Syahputra","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,4,19]]},"references-count":32,"alternative-id":["8847984","8847984"],"URL":"https:\/\/doi.org\/10.1155\/2021\/8847984","relation":{},"ISSN":["1687-9619","1687-9600"],"issn-type":[{"type":"electronic","value":"1687-9619"},{"type":"print","value":"1687-9600"}],"subject":[],"published":{"date-parts":[[2021,4,19]]}}}