Pub Date : 2003-06-16DOI: 10.1109/CVPRW.2003.10014
A. Willis, Xavier Orriols, D. Cooper
This paper deals with the problem of precise automatic estimation of the surface geometry of pot sherds uncovered at archaeological excavation sites using dense 3D laser-scan data. Critical to ceramic fragment analysis is the ability to geometrically classify excavated sherds, and, if possible, reconstruct the original pots using the sherd fragments. To do this, archaelogists must estimate the pot geometry in terms of an axis and associated profile curve from the discovered fragments. In this paper, we discuss an automatic method for accurately estimating an axis/profile curve pair for each archeological sherd (even when they are small) based on axially symmetric implicit polynomial surface models. Our method estimates the axis/profile curve for a sherd by finding the axially symmetric algebraic surface which best fits the measured set of dense 3D points and associated normals. We note that this method will work on 3D point data alone and does not require any local surface computations such as differentiation. Axis/profile curve estimates are accompanied by a detailed statistical error analysis. Estimation and error analysis are illustrated with application to a number of sherds. These fragments, excavated from Petra, Jordan, are chosen as exemplars of the families of geometrically diverse sherds commonly found on an archeological excavation site. We then briefly discuss how the estimation results may be integrated into a larger pot reconstruction program.
{"title":"Accurately Estimating Sherd 3D Surface Geometry with Application to Pot Reconstruction","authors":"A. Willis, Xavier Orriols, D. Cooper","doi":"10.1109/CVPRW.2003.10014","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10014","url":null,"abstract":"This paper deals with the problem of precise automatic estimation of the surface geometry of pot sherds uncovered at archaeological excavation sites using dense 3D laser-scan data. Critical to ceramic fragment analysis is the ability to geometrically classify excavated sherds, and, if possible, reconstruct the original pots using the sherd fragments. To do this, archaelogists must estimate the pot geometry in terms of an axis and associated profile curve from the discovered fragments. In this paper, we discuss an automatic method for accurately estimating an axis/profile curve pair for each archeological sherd (even when they are small) based on axially symmetric implicit polynomial surface models. Our method estimates the axis/profile curve for a sherd by finding the axially symmetric algebraic surface which best fits the measured set of dense 3D points and associated normals. We note that this method will work on 3D point data alone and does not require any local surface computations such as differentiation. Axis/profile curve estimates are accompanied by a detailed statistical error analysis. Estimation and error analysis are illustrated with application to a number of sherds. These fragments, excavated from Petra, Jordan, are chosen as exemplars of the families of geometrically diverse sherds commonly found on an archeological excavation site. We then briefly discuss how the estimation results may be integrated into a larger pot reconstruction program.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126347237","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 : 2003-06-16DOI: 10.1109/CVPRW.2003.10081
S. Ieng, R. Benosman, J. Devars
A new efficient matching algorithm dedicated to catadioptric sensors is proposed in this paper. The presented approach is designed to overcome the varying resolution of the mirror. The aim of this work is to provide a matcher that gives reliable results similar to the ones obtained by classical operators on planar projection images. The matching is based on a dynamical size windows extraction, computed from the viewing angular aperture of the neighborhood around the points of interest. An angular scaling of this angular aperture provides a certain number of different neighborhood resolution around the same considered point. A combinatory cost method is introduced in order to determine the best match between the different angular neighborhood patches of two interest points. Results are presented on sparse matched corner points, that can be used to estimate the epipolar geometry of the scene in order to provide a dense 3D map of the observed environment.
{"title":"An Efficient Dynamic Multi-Angular Feature Points Matcher for Catadioptric Views","authors":"S. Ieng, R. Benosman, J. Devars","doi":"10.1109/CVPRW.2003.10081","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10081","url":null,"abstract":"A new efficient matching algorithm dedicated to catadioptric sensors is proposed in this paper. The presented approach is designed to overcome the varying resolution of the mirror. The aim of this work is to provide a matcher that gives reliable results similar to the ones obtained by classical operators on planar projection images. The matching is based on a dynamical size windows extraction, computed from the viewing angular aperture of the neighborhood around the points of interest. An angular scaling of this angular aperture provides a certain number of different neighborhood resolution around the same considered point. A combinatory cost method is introduced in order to determine the best match between the different angular neighborhood patches of two interest points. Results are presented on sparse matched corner points, that can be used to estimate the epipolar geometry of the scene in order to provide a dense 3D map of the observed environment.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124589494","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 : 2003-06-16DOI: 10.1109/CVPRW.2003.10037
Yifan Shi, A. Bobick
In this paper, we devise a Propagation Net (P-Net) as a new mechanism for the representation and recognition of multi-stream activity. Most of daily activities can be represented by temporally partial ordered intervals where each interval has not only temporal constraint, i.e., before/after/duration, but also a logical relationship such as a and b both must happen. P-Net associates a node for each interval that is probabilistically triggered function dependent upon the state of its parent nodes. Each node is also associated with an observation distribution function that associates perceptual evidence. This evidence, generated by lower level vision modules, is a positive indicator of the elemental action. Using this architecture, we devise an iterative temporal sequencing algorithm that interprets a multi-dimensional observation sequence of visual evidence as a multi-stream propagation through the P-Net. Simple vision and motion-capture data experiments demonstrate the capabilities of our algorithm.
{"title":"P-Net: A Representation for Partially-Sequenced, Multi-stream Activity","authors":"Yifan Shi, A. Bobick","doi":"10.1109/CVPRW.2003.10037","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10037","url":null,"abstract":"In this paper, we devise a Propagation Net (P-Net) as a new mechanism for the representation and recognition of multi-stream activity. Most of daily activities can be represented by temporally partial ordered intervals where each interval has not only temporal constraint, i.e., before/after/duration, but also a logical relationship such as a and b both must happen. P-Net associates a node for each interval that is probabilistically triggered function dependent upon the state of its parent nodes. Each node is also associated with an observation distribution function that associates perceptual evidence. This evidence, generated by lower level vision modules, is a positive indicator of the elemental action. Using this architecture, we devise an iterative temporal sequencing algorithm that interprets a multi-dimensional observation sequence of visual evidence as a multi-stream propagation through the P-Net. Simple vision and motion-capture data experiments demonstrate the capabilities of our algorithm.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123132338","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 : 2003-06-16DOI: 10.1109/CVPRW.2003.10048
Andrew D. Wilson, Nuria Oliver
Perceptual user interfaces promise modes of fluid computer-human interaction that complement the mouse and keyboard, and have been especially motivated in non-desktop scenarios, such as kiosks or smart rooms. Such interfaces, however, have been slow to see use for a variety of reasons, including the computational burden they impose, a lack of robustness outside the laboratory, unreasonable calibration demands, and a shortage of sufficiently compelling applications. We have tackled some of these difficulties by using a fast stereo vision algorithm for recognizing hand positions and gestures. Our system uses two inexpensive video cameras to extract depth information. This depth information enhances automatic object detection and tracking robustness, and may also be used in applications. We demonstrate the algorithm in combination with speech recognition to perform several basic window management tasks, report on a user study probing the ease of using the system, and discuss the implications of such a system for future user interfaces.
{"title":"GWINDOWS: Towards Robust Perception-Based UI","authors":"Andrew D. Wilson, Nuria Oliver","doi":"10.1109/CVPRW.2003.10048","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10048","url":null,"abstract":"Perceptual user interfaces promise modes of fluid computer-human interaction that complement the mouse and keyboard, and have been especially motivated in non-desktop scenarios, such as kiosks or smart rooms. Such interfaces, however, have been slow to see use for a variety of reasons, including the computational burden they impose, a lack of robustness outside the laboratory, unreasonable calibration demands, and a shortage of sufficiently compelling applications. We have tackled some of these difficulties by using a fast stereo vision algorithm for recognizing hand positions and gestures. Our system uses two inexpensive video cameras to extract depth information. This depth information enhances automatic object detection and tracking robustness, and may also be used in applications. We demonstrate the algorithm in combination with speech recognition to perform several basic window management tasks, report on a user study probing the ease of using the system, and discuss the implications of such a system for future user interfaces.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125345014","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 : 2003-06-16DOI: 10.1109/CVPRW.2003.10005
H. Rushmeier, José Gomes, F. Giordano, H. El-Shishiny, Karen A. Magerlein, F. Bernardini
We describe the design and use of a 3D scanning system currently installed in Cairo's Egyptian Museum.The primary purpose of the system is to capture objects for display on a web site communicating Egyptian culture. The system is designed to capture both the geometry and photometry of the museum artifacts. We describe special features of the system and the calibration procedures designed for it. We also present resulting scans and examples of how they will be used on the web site.
{"title":"Design and Use of an In-Museum System for Artifact Capture","authors":"H. Rushmeier, José Gomes, F. Giordano, H. El-Shishiny, Karen A. Magerlein, F. Bernardini","doi":"10.1109/CVPRW.2003.10005","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10005","url":null,"abstract":"We describe the design and use of a 3D scanning system currently installed in Cairo's Egyptian Museum.The primary purpose of the system is to capture objects for display on a web site communicating Egyptian culture. The system is designed to capture both the geometry and photometry of the museum artifacts. We describe special features of the system and the calibration procedures designed for it. We also present resulting scans and examples of how they will be used on the web site.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125309201","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 : 2003-06-16DOI: 10.1109/CVPRW.2003.10053
T. Poggio
The ill-posed problem of learning is one of the main gateways to making intelligent machines and to understanding how the brain works. In this talk I will give an up-to-date outline of some of our recent efforts in developing machines that learn, especially in the context of visual interfaces. Our work on statistical learning theory is being applied to classification (and regression) in various domains -- and in particular to applications in computer vision and computer graphics. In this talk, I will summarize our work on trainable, hierarchical classifiers for problems in object recognition and especially for face and person detection. I will also describe how we used the same learning techniques to synthesize a photorealistic animation of a talking human face. Finally, I will speculate briefly on the implication of our research on how visual cortex learns to recognize and perceive objects and on related work on brain-machines interfaces.
{"title":"Learning and Perceptual Interfaces","authors":"T. Poggio","doi":"10.1109/CVPRW.2003.10053","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10053","url":null,"abstract":"The ill-posed problem of learning is one of the main gateways to making intelligent machines and to understanding how the brain works. In this talk I will give an up-to-date outline of some of our recent efforts in developing machines that learn, especially in the context of visual interfaces. Our work on statistical learning theory is being applied to classification (and regression) in various domains -- and in particular to applications in computer vision and computer graphics. In this talk, I will summarize our work on trainable, hierarchical classifiers for problems in object recognition and especially for face and person detection. I will also describe how we used the same learning techniques to synthesize a photorealistic animation of a talking human face. Finally, I will speculate briefly on the implication of our research on how visual cortex learns to recognize and perceive objects and on related work on brain-machines interfaces.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114580143","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 : 2003-06-16DOI: 10.1109/CVPRW.2003.10084
R. Orghidan, J. Salvi, E. Mouaddib
Catadioptric sensors are combinations of mirrors and lenses made in order to obtain a wide field of view. In this paper we propose a new sensor that has omnidirectional viewing ability and it also provides depth information about the nearby surrounding. The sensor is based on a conventional camera coupled with a laser emitter and two hyperbolic mirrors. Mathematical formulation and precise specifications of the intrinsic and extrinsic parameters of the sensor are discussed. Our approach overcomes limitations of the existing omni-directional sensors and eventually leads to reduced costs of production.
{"title":"Calibration of A Structured Light-Based Stereo Catadioptric Sensor","authors":"R. Orghidan, J. Salvi, E. Mouaddib","doi":"10.1109/CVPRW.2003.10084","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10084","url":null,"abstract":"Catadioptric sensors are combinations of mirrors and lenses made in order to obtain a wide field of view. In this paper we propose a new sensor that has omnidirectional viewing ability and it also provides depth information about the nearby surrounding. The sensor is based on a conventional camera coupled with a laser emitter and two hyperbolic mirrors. Mathematical formulation and precise specifications of the intrinsic and extrinsic parameters of the sensor are discussed. Our approach overcomes limitations of the existing omni-directional sensors and eventually leads to reduced costs of production.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123847285","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 : 2003-06-16DOI: 10.1109/CVPRW.2003.10026
K. Dennis, G. Michler, G. Schneider, M. Suzuki
In this article we describe new methods for the automatic recognition of the bibliographical data of cited articles in retrodigitized mathematical journal articles and their use for the automatic production of links to their respective reviews in MathSciNet an Zentralblatt MATH. Thus whenever one of these two review journals has a permanent link from the review to the digital full text of the cited article, the full text can automatically be retrieved, searched and printed. The new links from a digital document to the Mathematics Databases help enlarging the existing distributed digital Mathematics library. Examples of retrodigitized articles with automatic links in PDF and also in DjVu format are presented.
{"title":"Automatic reference linking in distributed digital libraries","authors":"K. Dennis, G. Michler, G. Schneider, M. Suzuki","doi":"10.1109/CVPRW.2003.10026","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10026","url":null,"abstract":"In this article we describe new methods for the automatic recognition of the bibliographical data of cited articles in retrodigitized mathematical journal articles and their use for the automatic production of links to their respective reviews in MathSciNet an Zentralblatt MATH. Thus whenever one of these two review journals has a permanent link from the review to the digital full text of the cited article, the full text can automatically be retrieved, searched and printed. The new links from a digital document to the Mathematics Databases help enlarging the existing distributed digital Mathematics library. Examples of retrodigitized articles with automatic links in PDF and also in DjVu format are presented.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121641920","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 : 2003-06-16DOI: 10.1109/CVPRW.2003.10066
Andrew J. Marek, W. Smart, Martin C. Martin
In this paper, we describe the use of Genetic Programming (GP) techniques to learn a visual feature detection for a mobile robot navigation task. We provide experimental results across a number of different environments, each with different characteristics, and draw conclusions about the performance of the learned feature detector. We also explore the utility of seeding the initial population with a previously evolved individual, and discuss the performance of the resulting individuals.
{"title":"Learning Visual Feature Detectors for Obstacle Avoidance using Genetic Programming","authors":"Andrew J. Marek, W. Smart, Martin C. Martin","doi":"10.1109/CVPRW.2003.10066","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10066","url":null,"abstract":"In this paper, we describe the use of Genetic Programming (GP) techniques to learn a visual feature detection for a mobile robot navigation task. We provide experimental results across a number of different environments, each with different characteristics, and draw conclusions about the performance of the learned feature detector. We also explore the utility of seeding the initial population with a previously evolved individual, and discuss the performance of the resulting individuals.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"690 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115117888","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 : 2003-06-16DOI: 10.1109/CVPRW.2003.10039
Raffay Hamid, Yan Huang, Irfan Essa
This paper presents a new framework for tracking and recognizing complex multi-agent activities using probabilistic tracking coupled with graphical models for recognition. We employ statistical feature based particle filter to robustly track multiple objects in cluttered environments. Both color and shape characteristics are used to differentiate and track different objects so that low level visual information can be reliably extracted for recognition of complex activities. Such extracted spatio-temporal features are then used to build temporal graphical models for characterization of these activities. We demonstrate through examples in different scenarios, the generalizability and robustness of our framework.
{"title":"ARGMode - Activity Recognition using Graphical Models","authors":"Raffay Hamid, Yan Huang, Irfan Essa","doi":"10.1109/CVPRW.2003.10039","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10039","url":null,"abstract":"This paper presents a new framework for tracking and recognizing complex multi-agent activities using probabilistic tracking coupled with graphical models for recognition. We employ statistical feature based particle filter to robustly track multiple objects in cluttered environments. Both color and shape characteristics are used to differentiate and track different objects so that low level visual information can be reliably extracted for recognition of complex activities. Such extracted spatio-temporal features are then used to build temporal graphical models for characterization of these activities. We demonstrate through examples in different scenarios, the generalizability and robustness of our framework.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123135389","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：