{"title":"一个家庭摄像机的3D重建","authors":"Yehu Shen, Peng Peng, Wei Gao","doi":"10.1109/ICACI.2012.6463131","DOIUrl":null,"url":null,"abstract":"Traditional 3D models are often built around specialized hardware, such as laser range finders and stereo rigs, which are expensive and complex to manipulate. In this paper, a method that achieves 3D reconstruction just using one consumer grade family camera is proposed. First, two images of the same scene from different viewing positions are captured without any strict constraints; Second, extrinsic parameters of the camera are estimated and refined; Then, image rectification is achieved to align epipolar lines of both images with scan lines; Finally, 3D model reconstruction is completed with the disparity map and the geometry of cameras. The proposed method is convenient even for amateurs and can produce vivid 3D models in a variety of different environments.","PeriodicalId":404759,"journal":{"name":"2012 IEEE Fifth International Conference on Advanced Computational Intelligence (ICACI)","volume":"17 15","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"3D reconstruction from a single family camera\",\"authors\":\"Yehu Shen, Peng Peng, Wei Gao\",\"doi\":\"10.1109/ICACI.2012.6463131\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Traditional 3D models are often built around specialized hardware, such as laser range finders and stereo rigs, which are expensive and complex to manipulate. In this paper, a method that achieves 3D reconstruction just using one consumer grade family camera is proposed. First, two images of the same scene from different viewing positions are captured without any strict constraints; Second, extrinsic parameters of the camera are estimated and refined; Then, image rectification is achieved to align epipolar lines of both images with scan lines; Finally, 3D model reconstruction is completed with the disparity map and the geometry of cameras. The proposed method is convenient even for amateurs and can produce vivid 3D models in a variety of different environments.\",\"PeriodicalId\":404759,\"journal\":{\"name\":\"2012 IEEE Fifth International Conference on Advanced Computational Intelligence (ICACI)\",\"volume\":\"17 15\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2012-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2012 IEEE Fifth International Conference on Advanced Computational Intelligence (ICACI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICACI.2012.6463131\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 IEEE Fifth International Conference on Advanced Computational Intelligence (ICACI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICACI.2012.6463131","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Traditional 3D models are often built around specialized hardware, such as laser range finders and stereo rigs, which are expensive and complex to manipulate. In this paper, a method that achieves 3D reconstruction just using one consumer grade family camera is proposed. First, two images of the same scene from different viewing positions are captured without any strict constraints; Second, extrinsic parameters of the camera are estimated and refined; Then, image rectification is achieved to align epipolar lines of both images with scan lines; Finally, 3D model reconstruction is completed with the disparity map and the geometry of cameras. The proposed method is convenient even for amateurs and can produce vivid 3D models in a variety of different environments.