Pub Date : 2003-06-16DOI: 10.1109/CVPRW.2003.10047
Selene Mota, Rosalind W. Picard
This paper presents a system for recognizing naturally occurring postures and associated affective states related to a child's interest level while performing a learning task on a computer. Postures are gathered using two matrices of pressure sensors mounted on the seat and back of a chair. Subsequently, posture features are extracted using a mixture of four gaussians, and input to a 3-layer feed-forward neural network. The neural network classifies nine postures in real time and achieves an overall accuracy of 87.6% when tested with postures coming from new subjects. A set of independent Hidden Markov Models (HMMs) is used to analyze temporal patterns among these posture sequences in order to determine three categories related to a child's level of interest, as rated by human observers. The system reaches an overall performance of 82.3% with posture sequences coming from known subjects and 76.5% with unknown subjects.
{"title":"Automated Posture Analysis for Detecting Learner's Interest Level","authors":"Selene Mota, Rosalind W. Picard","doi":"10.1109/CVPRW.2003.10047","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10047","url":null,"abstract":"This paper presents a system for recognizing naturally occurring postures and associated affective states related to a child's interest level while performing a learning task on a computer. Postures are gathered using two matrices of pressure sensors mounted on the seat and back of a chair. Subsequently, posture features are extracted using a mixture of four gaussians, and input to a 3-layer feed-forward neural network. The neural network classifies nine postures in real time and achieves an overall accuracy of 87.6% when tested with postures coming from new subjects. A set of independent Hidden Markov Models (HMMs) is used to analyze temporal patterns among these posture sequences in order to determine three categories related to a child's level of interest, as rated by human observers. The system reaches an overall performance of 82.3% with posture sequences coming from known subjects and 76.5% with unknown subjects.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"172 1 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":"116698491","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.2003.10089
S. Fidler, A. Leonardis
In this paper we present a new method which enables a robust calculation of the LDA classification rule, thus making the recognition of objects under non-ideal conditions possible, i.e., in situations when objects are occluded or they appear on a varying background, or when their images are corrupted by outliers. The main idea behind the method is to translate the task of calculating the LDA classification rule into the problem of determining the coefficients of an augmented generative model (PCA). Specifically, we construct an augmented PCA basis which, on the one hand, contains information necessary for the classification (in the LDA sense), and, on the other hand, enables us to calculate the necessary coefficients by means of a subsampling approach resulting in a high breakdown point classification. The theoretical results are evaluated on the ORL face database showing that the proposed method significantly outperforms the standard LDA.
{"title":"Robust LDA Classification by Subsampling","authors":"S. Fidler, A. Leonardis","doi":"10.1109/CVPRW.2003.10089","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10089","url":null,"abstract":"In this paper we present a new method which enables a robust calculation of the LDA classification rule, thus making the recognition of objects under non-ideal conditions possible, i.e., in situations when objects are occluded or they appear on a varying background, or when their images are corrupted by outliers. The main idea behind the method is to translate the task of calculating the LDA classification rule into the problem of determining the coefficients of an augmented generative model (PCA). Specifically, we construct an augmented PCA basis which, on the one hand, contains information necessary for the classification (in the LDA sense), and, on the other hand, enables us to calculate the necessary coefficients by means of a subsampling approach resulting in a high breakdown point classification. The theoretical results are evaluated on the ORL face database showing that the proposed method significantly outperforms the standard LDA.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"28 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":"124941330","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.2003.10101
D. Demirdjian
A novel approach for tracking 3D articulated human bodies in stereo images is presented. We present a projection-based method for enforcing articulated constraints. We define the articulated motion space as the space in which the motions of the limbs of a body belong. We show that around the origin, the articulated motion space can be approximated by a linear space estimated directly from the previous body pose. Articulated constraints are enforced by projecting unconstrained motions onto the linearized articulated motion space in an optimal way. Our paper also addresses the problem of accounting for other constraints on body pose and dynamics (e.g. joint angle bounds, maximum speed). We present here an approach to guarantee these constraints while tracking people.
{"title":"Enforcing Constraints for Human Body Tracking","authors":"D. Demirdjian","doi":"10.1109/CVPRW.2003.10101","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10101","url":null,"abstract":"A novel approach for tracking 3D articulated human bodies in stereo images is presented. We present a projection-based method for enforcing articulated constraints. We define the articulated motion space as the space in which the motions of the limbs of a body belong. We show that around the origin, the articulated motion space can be approximated by a linear space estimated directly from the previous body pose. Articulated constraints are enforced by projecting unconstrained motions onto the linearized articulated motion space in an optimal way. Our paper also addresses the problem of accounting for other constraints on body pose and dynamics (e.g. joint angle bounds, maximum speed). We present here an approach to guarantee these constraints while tracking people.","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":"125360759","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.2003.10088
G. Givens, Ross Beveridge, B. Draper, D. Bolme
Some people's faces are easier to recognize than others, but it is not obvious what subject-specific factors make individual faces easy or difficult to recognize. This study considers 11 factors that might make recognition easy or difficult for 1,072 human subjects in the FERET dataset. The specific factors are: race (white, Asian, African-American, or other), gender, age (young or old), glasses (present or absent), facial hair (present or absent), bangs (present or absent), mouth (closed or other), eyes (open or other), complexion (clear or other), makeup (present or absent), and expression (neutral or other). An ANOVA is used to determine the relationship between these subject covariates and the distance between pairs of images of the same subject in a standard Eigenfaces subspace. Some results are not terribly surprising. For example, the distance between pairs of images of the same subject increases for people who change their appearance, e.g., open and close their eyes, open and close their mouth or change expression. Thus changing appearance makes recognition harder. Other findings are surprising. Distance between pairs of images for subjects decreases for people who consistently wear glasses, so wearing glasses makes subjects more recognizable. Pairwise distance also decreases for people who are either Asian or African-American rather than white. A possible shortcoming of our analysis is that minority classifications such as African-Americans and wearers-of-glasses are underrepresented in training. Followup experiments with balanced training addresses this concern and corroborates the original findings. Another possible shortcoming of this analysis is the novel use of pairwise distance between images of a single person as the predictor of recognition difficulty. A separate experiment confirms that larger distances between pairs of subject images implies a larger recognition rank for that same pair of images, thus confirming that the subject is harder to recognize.
{"title":"A Statistical Assessment of Subject Factors in the PCA Recognition of Human Faces","authors":"G. Givens, Ross Beveridge, B. Draper, D. Bolme","doi":"10.1109/CVPRW.2003.10088","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10088","url":null,"abstract":"Some people's faces are easier to recognize than others, but it is not obvious what subject-specific factors make individual faces easy or difficult to recognize. This study considers 11 factors that might make recognition easy or difficult for 1,072 human subjects in the FERET dataset. The specific factors are: race (white, Asian, African-American, or other), gender, age (young or old), glasses (present or absent), facial hair (present or absent), bangs (present or absent), mouth (closed or other), eyes (open or other), complexion (clear or other), makeup (present or absent), and expression (neutral or other). An ANOVA is used to determine the relationship between these subject covariates and the distance between pairs of images of the same subject in a standard Eigenfaces subspace. Some results are not terribly surprising. For example, the distance between pairs of images of the same subject increases for people who change their appearance, e.g., open and close their eyes, open and close their mouth or change expression. Thus changing appearance makes recognition harder. Other findings are surprising. Distance between pairs of images for subjects decreases for people who consistently wear glasses, so wearing glasses makes subjects more recognizable. Pairwise distance also decreases for people who are either Asian or African-American rather than white. A possible shortcoming of our analysis is that minority classifications such as African-Americans and wearers-of-glasses are underrepresented in training. Followup experiments with balanced training addresses this concern and corroborates the original findings. Another possible shortcoming of this analysis is the novel use of pairwise distance between images of a single person as the predictor of recognition difficulty. A separate experiment confirms that larger distances between pairs of subject images implies a larger recognition rank for that same pair of images, thus confirming that the subject is harder to recognize.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"14 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":"123861541","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.2003.10009
Kevin Cain, Philippe Martinez
Here we consider optical triangulation scanning as a means of creating permanent architectural archives in the form of accurate ground plans and other orthographic views. We present plan drawings created with laser scan data and use these documents to make comparisons with existing documents. Finally, we present a new technique for decreasing the laser scanning field time required to create plans and other views.
{"title":"Drawing Accurate Ground Plans Using Optical Triangulation Data","authors":"Kevin Cain, Philippe Martinez","doi":"10.1109/CVPRW.2003.10009","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10009","url":null,"abstract":"Here we consider optical triangulation scanning as a means of creating permanent architectural archives in the form of accurate ground plans and other orthographic views. We present plan drawings created with laser scan data and use these documents to make comparisons with existing documents. Finally, we present a new technique for decreasing the laser scanning field time required to create plans and other views.","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":"125452577","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.2003.10100
Y. Boers, J. Driessen, F. Verschure, W. Heemels, A. Juloski
This paper deals with a radar track before detect application in a multi target setting. Track before detect is a method to track weak objects (targets) on the basis raw radar measurements, e.g. the reflected target power. In classical target tracking, the tracking process is performed on the basis of pre-processed measurements, that are constructed from the original measurement data every time step. In this way no integration over time takes place and information is lost. In this paper we will give a modelling setup and a particle filter based algorithm to deal with a multiple target track before detect situation. In simulations we show that, using this method, it is possible to track multiple, closely spaced, (weak) targets.
{"title":"A Multi Target Track Before Detect Application","authors":"Y. Boers, J. Driessen, F. Verschure, W. Heemels, A. Juloski","doi":"10.1109/CVPRW.2003.10100","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10100","url":null,"abstract":"This paper deals with a radar track before detect application in a multi target setting. Track before detect is a method to track weak objects (targets) on the basis raw radar measurements, e.g. the reflected target power. In classical target tracking, the tracking process is performed on the basis of pre-processed measurements, that are constructed from the original measurement data every time step. In this way no integration over time takes place and information is lost. In this paper we will give a modelling setup and a particle filter based algorithm to deal with a multiple target track before detect situation. In simulations we show that, using this method, it is possible to track multiple, closely spaced, (weak) targets.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"39 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":"125482269","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.2003.10006
M. Andreetto, N. Brusco, G. Cortelazzo
A wide-spread use of 3D models in archeology application requires low cost equipment and technically simple modeling procedures. In this context methods for automatic 3D modeling based on fully automatic techniques for 3D views registration will play a central role. This paper proposes a very robust procedure which does not require special equipment or skill in order to make 3D models. The results of this paper, originally conceived to address the costs issues of heritage's modeling, can be profitably exploited also in other modeling applications.
{"title":"Automatic 3D modeling of archaeological objects","authors":"M. Andreetto, N. Brusco, G. Cortelazzo","doi":"10.1109/CVPRW.2003.10006","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10006","url":null,"abstract":"A wide-spread use of 3D models in archeology application requires low cost equipment and technically simple modeling procedures. In this context methods for automatic 3D modeling based on fully automatic techniques for 3D views registration will play a central role. This paper proposes a very robust procedure which does not require special equipment or skill in order to make 3D models. The results of this paper, originally conceived to address the costs issues of heritage's modeling, can be profitably exploited also in other modeling applications.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"28 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":"125756779","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.2003.10040
A. Roy-Chowdhury, R. Chellappa
Understanding activities arising out of the interactions of a configuration of moving objects is an important problem in video understanding, with applications in surveillance and monitoring. A special situation is when the objects are small enough to be represented as points on a 2D plane. In this paper, we introduce a novel method of representing the activity by the deformations of the point configuration in a properly defined shape space. Instead of inferring about the activity directly from the motion tracks of the individual points, we propose to model an activity by the polygonal shape formed by joining the locations of these point masses at any time t, and its deformation as the activity unfolds. Given the locations of the 2D points over a sequence of frames in the video, the factorization theorem for matrices is used to obtain a set of basis shapes for each activity. An unknown activity can now be recognized by projecting onto these basis shapes. Also, once a specific activity is recognized, the deviations from it can be modeled by the deformations from the basis shape. This is used to identify an abnormal activity. We demonstrate the applicability of our algorithm using real-life video sequences in an airport surveillance environment. We are able to identify the major activities that take place in that setting and detect abnormal ones.
{"title":"A Factorization Approach for Activity Recognition","authors":"A. Roy-Chowdhury, R. Chellappa","doi":"10.1109/CVPRW.2003.10040","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10040","url":null,"abstract":"Understanding activities arising out of the interactions of a configuration of moving objects is an important problem in video understanding, with applications in surveillance and monitoring. A special situation is when the objects are small enough to be represented as points on a 2D plane. In this paper, we introduce a novel method of representing the activity by the deformations of the point configuration in a properly defined shape space. Instead of inferring about the activity directly from the motion tracks of the individual points, we propose to model an activity by the polygonal shape formed by joining the locations of these point masses at any time t, and its deformation as the activity unfolds. Given the locations of the 2D points over a sequence of frames in the video, the factorization theorem for matrices is used to obtain a set of basis shapes for each activity. An unknown activity can now be recognized by projecting onto these basis shapes. Also, once a specific activity is recognized, the deviations from it can be modeled by the deformations from the basis shape. This is used to identify an abnormal activity. We demonstrate the applicability of our algorithm using real-life video sequences in an airport surveillance environment. We are able to identify the major activities that take place in that setting and detect abnormal ones.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"24 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113938395","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.2003.10086
F. Huang, Shou-Kang Wei, R. Klette
The calibration of a line-based panoramic camera can be split into two independent subtasks: first calibrate the effective focal length and the principal row, and second, calibrate the off-axis distance and the principal angle. The paper provides solutions for three different methods, and compares these methods based on experiments using a superhigh resolution line-based panoramic camera. It turns out that the second subtask is solved best if a straight-segment based approach is used, compared to point-based or correspondence-based calibration methods, all already known for traditional (planar) pinhole cameras, but not yet previously discussed for panoramic cameras.
{"title":"Comparative Studies of Line-based Panoramic Camera Calibration","authors":"F. Huang, Shou-Kang Wei, R. Klette","doi":"10.1109/CVPRW.2003.10086","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10086","url":null,"abstract":"The calibration of a line-based panoramic camera can be split into two independent subtasks: first calibrate the effective focal length and the principal row, and second, calibrate the off-axis distance and the principal angle. The paper provides solutions for three different methods, and compares these methods based on experiments using a superhigh resolution line-based panoramic camera. It turns out that the second subtask is solved best if a straight-segment based approach is used, compared to point-based or correspondence-based calibration methods, all already known for traditional (planar) pinhole cameras, but not yet previously discussed for panoramic cameras.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"40 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":"114645856","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.2003.10050
Shunguang Wu, L. Hong, Francis K. H. Quek
Traditional image based hand tracking uses a single Kalman filter to estimate and predict the hand state (position, velocity, and acceleration). However, this approach may fail in the case of large maneuvers and cluttered measurements. In this paper we propose to use the interacting multiple model (IMM) filter to catch a maneuver and the probabilistic data association (PDA) method to process noisy measurements and false alarms. A theoretical framework of image based hand tracking by IMM-PDA is set up. Experiment results from several video segments show that IMM-PDA can successfully track hand motions in a natural conversational environment.
{"title":"Image Based Hand Tracking via Interacting Multiple Model and Probabilistic Data Association (IMM-PDA) Algorithm","authors":"Shunguang Wu, L. Hong, Francis K. H. Quek","doi":"10.1109/CVPRW.2003.10050","DOIUrl":"https://doi.org/10.1109/CVPRW.2003.10050","url":null,"abstract":"Traditional image based hand tracking uses a single Kalman filter to estimate and predict the hand state (position, velocity, and acceleration). However, this approach may fail in the case of large maneuvers and cluttered measurements. In this paper we propose to use the interacting multiple model (IMM) filter to catch a maneuver and the probabilistic data association (PDA) method to process noisy measurements and false alarms. A theoretical framework of image based hand tracking by IMM-PDA is set up. Experiment results from several video segments show that IMM-PDA can successfully track hand motions in a natural conversational environment.","PeriodicalId":121249,"journal":{"name":"2003 Conference on Computer Vision and Pattern Recognition Workshop","volume":"257 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120868434","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：