Jong Hun Lee, Yong Hwi Kim, Yong Yi Lee, Kwan H. Lee
{"title":"[POSTER] Geometric Mapping for Color Compensation Using Scene Adaptive Patches","authors":"Jong Hun Lee, Yong Hwi Kim, Yong Yi Lee, Kwan H. Lee","doi":"10.1109/ISMAR.2015.67","DOIUrl":null,"url":null,"abstract":"The SAR technique using a projector-camera system allows us to make various effect on a real scene without physical reconstitution. In order to project contents on a textured scene without color imperfections, geometric and radiometric compensation of a projection image should be conducted as preprocessing. In this paper, we present a new geometric mapping method for color compensation in the projector-camera system. We capture the scene and segment it into adaptive patch according to the scene structure using the SLIC segmentation. The piece-wise polynomial function is evaluated for each patch to find pixel-to-pixel correspondences between the measured and projection images. Finally, color compensation is performed by using a color mixing matrix. Experimental results show that our geometric mapping method establishes accurate correspondences and color compensation alleviates the color imperfections which is caused by texture of a general scene.","PeriodicalId":240196,"journal":{"name":"2015 IEEE International Symposium on Mixed and Augmented Reality","volume":"52 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 IEEE International Symposium on Mixed and Augmented Reality","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISMAR.2015.67","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
The SAR technique using a projector-camera system allows us to make various effect on a real scene without physical reconstitution. In order to project contents on a textured scene without color imperfections, geometric and radiometric compensation of a projection image should be conducted as preprocessing. In this paper, we present a new geometric mapping method for color compensation in the projector-camera system. We capture the scene and segment it into adaptive patch according to the scene structure using the SLIC segmentation. The piece-wise polynomial function is evaluated for each patch to find pixel-to-pixel correspondences between the measured and projection images. Finally, color compensation is performed by using a color mixing matrix. Experimental results show that our geometric mapping method establishes accurate correspondences and color compensation alleviates the color imperfections which is caused by texture of a general scene.