G. Raja, K. Dev, Nisha Deborah Philips, S. Suhaib, M. Deepakraj, R. Ramasamy
{"title":"DA-WDGN:基于GLCM-M特征和NDIRT指数的无人机辅助杂草检测","authors":"G. Raja, K. Dev, Nisha Deborah Philips, S. Suhaib, M. Deepakraj, R. Ramasamy","doi":"10.1109/INFOCOMWKSHPS51825.2021.9484598","DOIUrl":null,"url":null,"abstract":"The exponential growth of drone technology and its computational methods has led to a surge in agricultural applications employing drones. In this paper, a Drone-Assisted Weed Detection using a Modified multichannel Gray Level Co-Occurrence Matrix (GLCM-M) and Normalised Difference Index with Red Threshold (NDIRT) indices (DA-WDGN) is proposed to aid in the process of weed detection. In DA-WDGN, the drones combine both information and communication technologies for the far-field data acquisition and precise detection of weeds. Accurate detection of weeds limits the need for pesticides and helps to protect the environment. Traditional systems use an object-oriented classification system for weed detection, which suffer from the issue of close similarities between the shape features of crop plants and weeds, making it impossible to uniquely distinguish the weeds. Therefore in the DA-WDGN system, shape, texture, and spectral features are integrated to establish a unique pattern for every plant. These patterns are then used to differentiate between crops and weeds. The proposed DA-WDGN system improves the accuracy of weed detection to 99.4% thereby establishing its supremacy over other conventional weed detection algorithms.","PeriodicalId":109588,"journal":{"name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"DA-WDGN: Drone-Assisted Weed Detection using GLCM-M features and NDIRT indices\",\"authors\":\"G. Raja, K. Dev, Nisha Deborah Philips, S. Suhaib, M. Deepakraj, R. Ramasamy\",\"doi\":\"10.1109/INFOCOMWKSHPS51825.2021.9484598\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The exponential growth of drone technology and its computational methods has led to a surge in agricultural applications employing drones. In this paper, a Drone-Assisted Weed Detection using a Modified multichannel Gray Level Co-Occurrence Matrix (GLCM-M) and Normalised Difference Index with Red Threshold (NDIRT) indices (DA-WDGN) is proposed to aid in the process of weed detection. In DA-WDGN, the drones combine both information and communication technologies for the far-field data acquisition and precise detection of weeds. Accurate detection of weeds limits the need for pesticides and helps to protect the environment. Traditional systems use an object-oriented classification system for weed detection, which suffer from the issue of close similarities between the shape features of crop plants and weeds, making it impossible to uniquely distinguish the weeds. Therefore in the DA-WDGN system, shape, texture, and spectral features are integrated to establish a unique pattern for every plant. These patterns are then used to differentiate between crops and weeds. The proposed DA-WDGN system improves the accuracy of weed detection to 99.4% thereby establishing its supremacy over other conventional weed detection algorithms.\",\"PeriodicalId\":109588,\"journal\":{\"name\":\"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)\",\"volume\":\"15 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-05-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/INFOCOMWKSHPS51825.2021.9484598\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INFOCOMWKSHPS51825.2021.9484598","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
DA-WDGN: Drone-Assisted Weed Detection using GLCM-M features and NDIRT indices
The exponential growth of drone technology and its computational methods has led to a surge in agricultural applications employing drones. In this paper, a Drone-Assisted Weed Detection using a Modified multichannel Gray Level Co-Occurrence Matrix (GLCM-M) and Normalised Difference Index with Red Threshold (NDIRT) indices (DA-WDGN) is proposed to aid in the process of weed detection. In DA-WDGN, the drones combine both information and communication technologies for the far-field data acquisition and precise detection of weeds. Accurate detection of weeds limits the need for pesticides and helps to protect the environment. Traditional systems use an object-oriented classification system for weed detection, which suffer from the issue of close similarities between the shape features of crop plants and weeds, making it impossible to uniquely distinguish the weeds. Therefore in the DA-WDGN system, shape, texture, and spectral features are integrated to establish a unique pattern for every plant. These patterns are then used to differentiate between crops and weeds. The proposed DA-WDGN system improves the accuracy of weed detection to 99.4% thereby establishing its supremacy over other conventional weed detection algorithms.