{"title":"基于外观和运动的多维增强回归快速人体姿态估计","authors":"A. Bissacco, Ming-Hsuan Yang, Stefano Soatto","doi":"10.1109/CVPR.2007.383129","DOIUrl":null,"url":null,"abstract":"We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitable features of an image and its temporal neighbors, and learning a regression map to the parameters of a model of the human body using boosting techniques. Our algorithm can be viewed as a fast initialization step for human body trackers, or as a tracker itself. We extend gradient boosting techniques to learn a multi-dimensional map from (rotated and scaled) Haar features to the entire set of joint angles representing the full body pose. We test our approach by learning a map from image patches to body joint angles from synchronized video and motion capture walking data. We show how our technique enables learning an efficient real-time pose estimator, validated on publicly available datasets.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"136","resultStr":"{\"title\":\"Fast Human Pose Estimation using Appearance and Motion via Multi-Dimensional Boosting Regression\",\"authors\":\"A. Bissacco, Ming-Hsuan Yang, Stefano Soatto\",\"doi\":\"10.1109/CVPR.2007.383129\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitable features of an image and its temporal neighbors, and learning a regression map to the parameters of a model of the human body using boosting techniques. Our algorithm can be viewed as a fast initialization step for human body trackers, or as a tracker itself. We extend gradient boosting techniques to learn a multi-dimensional map from (rotated and scaled) Haar features to the entire set of joint angles representing the full body pose. We test our approach by learning a map from image patches to body joint angles from synchronized video and motion capture walking data. We show how our technique enables learning an efficient real-time pose estimator, validated on publicly available datasets.\",\"PeriodicalId\":351008,\"journal\":{\"name\":\"2007 IEEE Conference on Computer Vision and Pattern Recognition\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-12-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"136\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 IEEE Conference on Computer Vision and Pattern Recognition\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CVPR.2007.383129\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 IEEE Conference on Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CVPR.2007.383129","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Fast Human Pose Estimation using Appearance and Motion via Multi-Dimensional Boosting Regression
We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitable features of an image and its temporal neighbors, and learning a regression map to the parameters of a model of the human body using boosting techniques. Our algorithm can be viewed as a fast initialization step for human body trackers, or as a tracker itself. We extend gradient boosting techniques to learn a multi-dimensional map from (rotated and scaled) Haar features to the entire set of joint angles representing the full body pose. We test our approach by learning a map from image patches to body joint angles from synchronized video and motion capture walking data. We show how our technique enables learning an efficient real-time pose estimator, validated on publicly available datasets.