{"title":"A new interaction method for augmented reality based on ARToolKit","authors":"Huibai Wang, Junli Qin, Fengquan Zhang","doi":"10.1109/CISP.2015.7407945","DOIUrl":null,"url":null,"abstract":"In this paper, we implement a new interaction method for the application of augmented reality using ARToolKit and OpenCV SDK. First, on the basis of the exiting marker-based tracking system, this paper achieved the multi-marker tracking that solved the tracking failure problem when the single marker is partially occluded, which greatly improves the robustness of the registration algorithm. In addition, Codebook-based foreground detection model is used to detect the hand region under an unexpected background environment. Moreover, we could recognize the hand gesture by convex hull on the basis of the hand contour. Therefore, a gesture recognition algorithm is presented based on codebook model algorithm and convex hull algorithm for the interaction. In the end, we use several different experiments to show the performance, which can be seen the good interactivity and realistic.","PeriodicalId":167631,"journal":{"name":"2015 8th International Congress on Image and Signal Processing (CISP)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 8th International Congress on Image and Signal Processing (CISP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CISP.2015.7407945","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6
Abstract
In this paper, we implement a new interaction method for the application of augmented reality using ARToolKit and OpenCV SDK. First, on the basis of the exiting marker-based tracking system, this paper achieved the multi-marker tracking that solved the tracking failure problem when the single marker is partially occluded, which greatly improves the robustness of the registration algorithm. In addition, Codebook-based foreground detection model is used to detect the hand region under an unexpected background environment. Moreover, we could recognize the hand gesture by convex hull on the basis of the hand contour. Therefore, a gesture recognition algorithm is presented based on codebook model algorithm and convex hull algorithm for the interaction. In the end, we use several different experiments to show the performance, which can be seen the good interactivity and realistic.