{"title":"Research on Localization of Apples Based on Binocular Stereo Vision Marked by Cancroids Matching","authors":"Jian Li, S. Cui, Chengyan Zhang, Haifeng Chen","doi":"10.1109/ICDMA.2012.161","DOIUrl":null,"url":null,"abstract":"In order to enhance the localization accuracy of apple-picking robots' vision system, a method based on binocular stereo vision technology marked by cancroids matching was proposed. Key problems such as camera calibration, characteristics extraction and 3D coordinate's calculation were analyzed. The distances between apples and cameras were measured with the proposed method under different circumstances. Experimental results showed that the average relative error was about 3.54% with the help of matched cancroids when the working distance ranged between 300-1000mm. This can meet the needs of vision system of apple picking robot in most picking environments.","PeriodicalId":393655,"journal":{"name":"International Conference on Digital Manufacturing and Automation","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Digital Manufacturing and Automation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICDMA.2012.161","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
In order to enhance the localization accuracy of apple-picking robots' vision system, a method based on binocular stereo vision technology marked by cancroids matching was proposed. Key problems such as camera calibration, characteristics extraction and 3D coordinate's calculation were analyzed. The distances between apples and cameras were measured with the proposed method under different circumstances. Experimental results showed that the average relative error was about 3.54% with the help of matched cancroids when the working distance ranged between 300-1000mm. This can meet the needs of vision system of apple picking robot in most picking environments.