{"title":"基于RGB图像分析的猪体重估计","authors":"Andras Kárpinszky, Gergely Dobsinszki","doi":"10.18690/agricsci.20.1.6","DOIUrl":null,"url":null,"abstract":"In pig farming, knowing the exact weight of each animal is critical for the owner. Such information can help determine the amount and type of feed that needs to be fed to a specific fattening pig. Weighing pigs has always been problematic, because it is highly time consuming, and herding the pigs on the scale is extremely cumbersome. Moreover, it causes stress to the animals. The aim of our study was to build an RGB-based system that could estimate the daily weight of pigs and individual animal weight. The study was set up in a 100-day rotation in a commercial pig farm where we monitored 32 pigs. We developed a system to identify the features of the pigs, more particularly the head, shoulder, belly, and rump part. Three different modelswere tested, and their main differences were linked to image processing and training data. Using these models, we received higher than 97% accuracy between the predicted and the manually recorded weight of the animals. This system allows owners to manage and monitor their pigs using our web interface, allowing them to make crucial decisions during the farming process.","PeriodicalId":37655,"journal":{"name":"中国农业科学","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Pig Weight Estimation According to RGB Image Analysis\",\"authors\":\"Andras Kárpinszky, Gergely Dobsinszki\",\"doi\":\"10.18690/agricsci.20.1.6\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In pig farming, knowing the exact weight of each animal is critical for the owner. Such information can help determine the amount and type of feed that needs to be fed to a specific fattening pig. Weighing pigs has always been problematic, because it is highly time consuming, and herding the pigs on the scale is extremely cumbersome. Moreover, it causes stress to the animals. The aim of our study was to build an RGB-based system that could estimate the daily weight of pigs and individual animal weight. The study was set up in a 100-day rotation in a commercial pig farm where we monitored 32 pigs. We developed a system to identify the features of the pigs, more particularly the head, shoulder, belly, and rump part. Three different modelswere tested, and their main differences were linked to image processing and training data. Using these models, we received higher than 97% accuracy between the predicted and the manually recorded weight of the animals. This system allows owners to manage and monitor their pigs using our web interface, allowing them to make crucial decisions during the farming process.\",\"PeriodicalId\":37655,\"journal\":{\"name\":\"中国农业科学\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-05-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"中国农业科学\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18690/agricsci.20.1.6\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"中国农业科学","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18690/agricsci.20.1.6","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Pig Weight Estimation According to RGB Image Analysis
In pig farming, knowing the exact weight of each animal is critical for the owner. Such information can help determine the amount and type of feed that needs to be fed to a specific fattening pig. Weighing pigs has always been problematic, because it is highly time consuming, and herding the pigs on the scale is extremely cumbersome. Moreover, it causes stress to the animals. The aim of our study was to build an RGB-based system that could estimate the daily weight of pigs and individual animal weight. The study was set up in a 100-day rotation in a commercial pig farm where we monitored 32 pigs. We developed a system to identify the features of the pigs, more particularly the head, shoulder, belly, and rump part. Three different modelswere tested, and their main differences were linked to image processing and training data. Using these models, we received higher than 97% accuracy between the predicted and the manually recorded weight of the animals. This system allows owners to manage and monitor their pigs using our web interface, allowing them to make crucial decisions during the farming process.
中国农业科学Agricultural and Biological Sciences-Agricultural and Biological Sciences (all)
CiteScore
1.90
自引率
0.00%
发文量
17516
期刊介绍:
Scientia Agricultura Sinica seeks to publish those papers that are influential and will significantly advance scientific understanding in agriculture fields worldwide. Scientia Agricultura Sinica publishes manuscripts in the categories focusing on the core subjects listed below. -Review describes new development and highlight future directions of a specialized or interdisciplinary significance in agricultural sciences. They should be focused on providing insights and summary/context on the published findings and introducing new concepts or viewpoints for solving the important unresolved questions by presenting the research background, approach, and outlook of the field. Most Reviews are solicited by the editors, but unsolicited submissions may also be considered. -Research Article presents important new research results through reproducible experimental design, using genetic, biochemical, cell and molecular biological methods, statistical analyses, and other scientific methods. -Research Notes is for a concise, but independent report representing a significant contribution to agricultural sciences. It is intended to publish these results that are exceptional interest and particularly topical and relevant, but the preliminary results. Core Subjects: -Crop Genetics & Breeding·GermplasmResources·Molecular Genetics -Tillage & Cultivation·Physiology & Biochemistry -Plant Protection -Soil & Fertilizer·Water-Saving Irrigation·Agro-Ecology & Environment -Horticulture -Storage·Fresh-Keeping·Processing -Animal Science·Veterinary Science -Agricultural Ecology -Research Notes