{"title":"在温室中进行视觉指导操作","authors":"G. Sandini, F. Buemi, M. Massa, M. Zucchini","doi":"10.1109/IROS.1990.262398","DOIUrl":null,"url":null,"abstract":"A vision system to operate in a greenhouse environment designed for tomato cultivation is presented. The signals sent by two PAL colour cameras are processed by a graphic workstation using a bit-slice microprocessor card for fast image processing. Cultural operations are examined and the proper vision system specifications are defined. Attention is turned on two aspects: localization of main objects (e.g. flowers, fruits) and navigation. As for localization, an algorithm has been developed based on the colour and particularly on the hue component (extracted 3 times per second from a RGB input) for segmentation and on a stereo processing to find the distance of segmented objects. Results are good enough to demonstrate the feasibility of such an approach.<<ETX>>","PeriodicalId":409624,"journal":{"name":"EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications","volume":"82 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1990-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"20","resultStr":"{\"title\":\"Visually guided operations in green-houses\",\"authors\":\"G. Sandini, F. Buemi, M. Massa, M. Zucchini\",\"doi\":\"10.1109/IROS.1990.262398\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A vision system to operate in a greenhouse environment designed for tomato cultivation is presented. The signals sent by two PAL colour cameras are processed by a graphic workstation using a bit-slice microprocessor card for fast image processing. Cultural operations are examined and the proper vision system specifications are defined. Attention is turned on two aspects: localization of main objects (e.g. flowers, fruits) and navigation. As for localization, an algorithm has been developed based on the colour and particularly on the hue component (extracted 3 times per second from a RGB input) for segmentation and on a stereo processing to find the distance of segmented objects. Results are good enough to demonstrate the feasibility of such an approach.<<ETX>>\",\"PeriodicalId\":409624,\"journal\":{\"name\":\"EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications\",\"volume\":\"82 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1990-07-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"20\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IROS.1990.262398\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IROS.1990.262398","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A vision system to operate in a greenhouse environment designed for tomato cultivation is presented. The signals sent by two PAL colour cameras are processed by a graphic workstation using a bit-slice microprocessor card for fast image processing. Cultural operations are examined and the proper vision system specifications are defined. Attention is turned on two aspects: localization of main objects (e.g. flowers, fruits) and navigation. As for localization, an algorithm has been developed based on the colour and particularly on the hue component (extracted 3 times per second from a RGB input) for segmentation and on a stereo processing to find the distance of segmented objects. Results are good enough to demonstrate the feasibility of such an approach.<>