Pub Date : 1999-09-20DOI: 10.1109/PEOPLE.1999.798350
M. Walter, S. Gong, A. Psarrou
Human activities are characterised by the spatio-temporal structure of their motion pattern. Such structures are probabilistic and often rather ambiguous. Modelling such spatio-temporal structures as static templates can be very sensitive to noise and cannot capture variations in observation measurements caused by different subjects performing the same act. In this paper we introduce the concept of modelling temporal structures by statistical dynamic systems using first-order Markov process descriptions. Prior knowledge is learned from training sequences and recognition is performed through continuous propagation of density distributions. Taking current observations into account to temporarily augment the learned prior leads to more accurate recognition with less computational costs.
{"title":"Stochastic temporal models of human activities","authors":"M. Walter, S. Gong, A. Psarrou","doi":"10.1109/PEOPLE.1999.798350","DOIUrl":"https://doi.org/10.1109/PEOPLE.1999.798350","url":null,"abstract":"Human activities are characterised by the spatio-temporal structure of their motion pattern. Such structures are probabilistic and often rather ambiguous. Modelling such spatio-temporal structures as static templates can be very sensitive to noise and cannot capture variations in observation measurements caused by different subjects performing the same act. In this paper we introduce the concept of modelling temporal structures by statistical dynamic systems using first-order Markov process descriptions. Prior knowledge is learned from training sequences and recognition is performed through continuous propagation of density distributions. Taking current observations into account to temporarily augment the learned prior leads to more accurate recognition with less computational costs.","PeriodicalId":237701,"journal":{"name":"Proceedings IEEE International Workshop on Modelling People. MPeople'99","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114326226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1999-09-20DOI: 10.1109/PEOPLE.1999.798340
Shoichiro Iwasawa, Jun Ohya, Kazuhiko Takahashi, T. Sakaguchi, S. Kawato, K. Ebihara, Shigeo Morishima
This paper proposes a new real-time method for estimating human postures in 3D from trinocular images. In this method, an upper body orientation detection and a heuristic contour analysis are performed on the human silhouettes extracted from the trinocular images so that representative points such as the top of the head can be located. The major joint positions are estimated based on a genetic algorithm based learning procedure. 3D coordinates of the representative points and joints are then obtained from the two views by evaluating the appropriateness of the three views. The proposed method implemented on a personal computer runs in real-time (30 frames/second). Experimental results show high estimation accuracies and the effectiveness of the view selection process.
{"title":"Real-time, 3D estimation of human body postures from trinocular images","authors":"Shoichiro Iwasawa, Jun Ohya, Kazuhiko Takahashi, T. Sakaguchi, S. Kawato, K. Ebihara, Shigeo Morishima","doi":"10.1109/PEOPLE.1999.798340","DOIUrl":"https://doi.org/10.1109/PEOPLE.1999.798340","url":null,"abstract":"This paper proposes a new real-time method for estimating human postures in 3D from trinocular images. In this method, an upper body orientation detection and a heuristic contour analysis are performed on the human silhouettes extracted from the trinocular images so that representative points such as the top of the head can be located. The major joint positions are estimated based on a genetic algorithm based learning procedure. 3D coordinates of the representative points and joints are then obtained from the two views by evaluating the appropriateness of the three views. The proposed method implemented on a personal computer runs in real-time (30 frames/second). Experimental results show high estimation accuracies and the effectiveness of the view selection process.","PeriodicalId":237701,"journal":{"name":"Proceedings IEEE International Workshop on Modelling People. MPeople'99","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123732005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：