Pub Date : 2009-12-16DOI: 10.1109/CVPR.2007.383232
Omer Rotem, H. Greenspan, J. Goldberger
In this paper we propose a new segmentation algorithm which combines patch-based information with edge cues under a probabilistic framework. We use a mixture of multiple Gaussians for building the statistical model with color and spatial features, and we incorporate edge information based on texture, color and brightness differences into the EM algorithm. We evaluate our results qualitatively and quantitatively on a large data-set of natural images and compare our results to other state-of-the-art methods.
{"title":"Combining Region and Edge Cues for Image Segmentation in a Probabilistic Gaussian Mixture Framework","authors":"Omer Rotem, H. Greenspan, J. Goldberger","doi":"10.1109/CVPR.2007.383232","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383232","url":null,"abstract":"In this paper we propose a new segmentation algorithm which combines patch-based information with edge cues under a probabilistic framework. We use a mixture of multiple Gaussians for building the statistical model with color and spatial features, and we incorporate edge information based on texture, color and brightness differences into the EM algorithm. We evaluate our results qualitatively and quantitatively on a large data-set of natural images and compare our results to other state-of-the-art methods.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"176 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115100294","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 : 2007-12-05DOI: 10.1109/CVPR.2007.383129
A. Bissacco, Ming-Hsuan Yang, Stefano Soatto
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.
{"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":"https://doi.org/10.1109/CVPR.2007.383129","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":0.0,"publicationDate":"2007-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115857158","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 : 2007-06-17DOI: 10.1109/CVPR.2007.383479
S. Kim, W. Winchester, Yun-Bum Choi, J. Lee
The rate of obese has been increasing and obesity has emerged as a significant threat not only to the health but also in society. Obesity has adverse effects such as physical appearance, psychosocial consequences and metabolic disturbances. One of reasons causing these phenomena is most games have static and stationary user interfaces as input devices. These kinds of interfaces hold users at their computers and cause not only decreases of the strength of their health, but also blocks communications between family members. In this paper, we propose physical activity based interactive exercise called Punch Punch, which is played with virtual objects displaying on a large screen. The informal study revealed that the Punch Punch enhanced physical and social activities while playing games. The goal of this study is finding embodied user interfaces to increase physical and social activities.
{"title":"An Embodied User Interface for Increasing Physical Activities in Game","authors":"S. Kim, W. Winchester, Yun-Bum Choi, J. Lee","doi":"10.1109/CVPR.2007.383479","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383479","url":null,"abstract":"The rate of obese has been increasing and obesity has emerged as a significant threat not only to the health but also in society. Obesity has adverse effects such as physical appearance, psychosocial consequences and metabolic disturbances. One of reasons causing these phenomena is most games have static and stationary user interfaces as input devices. These kinds of interfaces hold users at their computers and cause not only decreases of the strength of their health, but also blocks communications between family members. In this paper, we propose physical activity based interactive exercise called Punch Punch, which is played with virtual objects displaying on a large screen. The informal study revealed that the Punch Punch enhanced physical and social activities while playing games. The goal of this study is finding embodied user interfaces to increase physical and social activities.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"435 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115603875","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 : 2007-06-17DOI: 10.1109/CVPR.2007.383181
F. Dufrenois, J. Colliez, D. Hamad
Support Vector Regression (SVR) is now a well-established method for estimating real-valued functions. However, the standard SVR is not effective to deal with outliers and structured outliers in training data sets commonly encountered in computer vision applications. In this paper, we present a weighted version of SVM for regression. The proposed approach introduces an adaptive binary function that allows a dominant model from a degraded training dataset to be extracted. This binary function progressively separates inliers from outliers following a one-against-all decomposition. Experimental tests show the high robustness of the proposed approach against outliers and residual structured outliers. Next, we validate our algorithm for object tracking and for optic flow estimation.
{"title":"Crisp Weighted Support Vector Regression for robust single model estimation : application to object tracking in image sequences","authors":"F. Dufrenois, J. Colliez, D. Hamad","doi":"10.1109/CVPR.2007.383181","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383181","url":null,"abstract":"Support Vector Regression (SVR) is now a well-established method for estimating real-valued functions. However, the standard SVR is not effective to deal with outliers and structured outliers in training data sets commonly encountered in computer vision applications. In this paper, we present a weighted version of SVM for regression. The proposed approach introduces an adaptive binary function that allows a dominant model from a degraded training dataset to be extracted. This binary function progressively separates inliers from outliers following a one-against-all decomposition. Experimental tests show the high robustness of the proposed approach against outliers and residual structured outliers. Next, we validate our algorithm for object tracking and for optic flow estimation.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"287 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123121482","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 : 2007-06-17DOI: 10.1109/CVPR.2007.383463
Niranjan Damera-Venkata, Nelson L. Chang
We consider the problem of rendering high-resolution images on a display composed of multiple superimposed lower-resolution projectors. A theoretical analysis of this problem in the literature previously concluded that the multi-projector superimposition of low resolution projectors cannot produce high resolution images. In our recent work, we showed to the contrary that super-resolution via multiple superimposed projectors is indeed theoretically achievable. This paper derives practical algorithms for real multi-projector systems that account for the intra- and inter-projector variations and that render high-quality, high-resolution content at real-time interactive frame rates. A camera is used to estimate the geometric, photometric, and color properties of each component projector in a calibration step. Given this parameter information, we demonstrate novel methods for efficiently generating optimal sub-frames so that the resulting projected image is as close as possible to the given high resolution images.
{"title":"Realizing Super-Resolution with Superimposed Projection","authors":"Niranjan Damera-Venkata, Nelson L. Chang","doi":"10.1109/CVPR.2007.383463","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383463","url":null,"abstract":"We consider the problem of rendering high-resolution images on a display composed of multiple superimposed lower-resolution projectors. A theoretical analysis of this problem in the literature previously concluded that the multi-projector superimposition of low resolution projectors cannot produce high resolution images. In our recent work, we showed to the contrary that super-resolution via multiple superimposed projectors is indeed theoretically achievable. This paper derives practical algorithms for real multi-projector systems that account for the intra- and inter-projector variations and that render high-quality, high-resolution content at real-time interactive frame rates. A camera is used to estimate the geometric, photometric, and color properties of each component projector in a calibration step. Given this parameter information, we demonstrate novel methods for efficiently generating optimal sub-frames so that the resulting projected image is as close as possible to the given high resolution images.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116786390","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 : 2007-06-17DOI: 10.1109/CVPR.2007.382975
Hongdong Li
This paper studies the problem of multibody motion segmentation, which is an important, but challenging problem due to its well-known chicken-and-egg-type recursive character. We propose a new mixture-of-fundamental-matrices model to describe the multibody motions from two views. Based on the maximum likelihood estimation, in conjunction with a random sampling scheme, we show that the problem can be naturally formulated as a linear programming (LP) problem. Consequently, the motion segmentation problem can be solved efficiently by linear program relaxation. Experiments demonstrate that: without assuming the actual number of motions our method produces accurate segmentation result. This LP formulation has also other advantages, such as easy to handle outliers and easy to enforce prior knowledge etc.
{"title":"Two-View Motion Segmentation from Linear Programming Relaxation","authors":"Hongdong Li","doi":"10.1109/CVPR.2007.382975","DOIUrl":"https://doi.org/10.1109/CVPR.2007.382975","url":null,"abstract":"This paper studies the problem of multibody motion segmentation, which is an important, but challenging problem due to its well-known chicken-and-egg-type recursive character. We propose a new mixture-of-fundamental-matrices model to describe the multibody motions from two views. Based on the maximum likelihood estimation, in conjunction with a random sampling scheme, we show that the problem can be naturally formulated as a linear programming (LP) problem. Consequently, the motion segmentation problem can be solved efficiently by linear program relaxation. Experiments demonstrate that: without assuming the actual number of motions our method produces accurate segmentation result. This LP formulation has also other advantages, such as easy to handle outliers and easy to enforce prior knowledge etc.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116866357","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 : 2007-06-17DOI: 10.1109/CVPR.2007.383482
T. Molinier, D. Fofi, P. Gorria, J. Salvi
We propose a full automatic technique to project virtual texture on a real textureless 3D object. Our system is composed of cameras and projector and are used to determine the pose of the object in the real world with the projector as reference and then estimate the image seen by the projector if it would be a camera.
{"title":"Automatic texture mapping on real 3D model","authors":"T. Molinier, D. Fofi, P. Gorria, J. Salvi","doi":"10.1109/CVPR.2007.383482","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383482","url":null,"abstract":"We propose a full automatic technique to project virtual texture on a real textureless 3D object. Our system is composed of cameras and projector and are used to determine the pose of the object in the real world with the projector as reference and then estimate the image seen by the projector if it would be a camera.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"27 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120998183","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 : 2007-06-17DOI: 10.1109/CVPR.2007.383161
Li Yi, D. Jacobs
Volume intersection is a frequently used technique to solve the Shape-From-Silhouette problem, which constructs a 3D object estimate from a set of silhouettes taken with calibrated cameras. It is natural to develop an efficient algorithm to determine the consistency of a set of silhouettes before performing time-consuming reconstruction, so that inaccurate silhouettes can be omitted. In this paper we first present a fast algorithm to determine the consistency of three silhouettes from known (but arbitrary) viewing directions, assuming the projection is scaled orthographic. The temporal complexity of the algorithm is linear in the number of points of the silhouette boundaries. We further prove that a set of more than three convex silhouettes are consistent if and only if any three of them are consistent. Another possible application of our approach is to determine the miscalibrated cameras in a large camera system. A consistent subset of cameras can be determined on the fly and miscalibrated cameras can also be recalibrated at a coarse scale. Real and synthesized data are used to demonstrate our results.
{"title":"Efficiently Determining Silhouette Consistency","authors":"Li Yi, D. Jacobs","doi":"10.1109/CVPR.2007.383161","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383161","url":null,"abstract":"Volume intersection is a frequently used technique to solve the Shape-From-Silhouette problem, which constructs a 3D object estimate from a set of silhouettes taken with calibrated cameras. It is natural to develop an efficient algorithm to determine the consistency of a set of silhouettes before performing time-consuming reconstruction, so that inaccurate silhouettes can be omitted. In this paper we first present a fast algorithm to determine the consistency of three silhouettes from known (but arbitrary) viewing directions, assuming the projection is scaled orthographic. The temporal complexity of the algorithm is linear in the number of points of the silhouette boundaries. We further prove that a set of more than three convex silhouettes are consistent if and only if any three of them are consistent. Another possible application of our approach is to determine the miscalibrated cameras in a large camera system. A consistent subset of cameras can be determined on the fly and miscalibrated cameras can also be recalibrated at a coarse scale. Real and synthesized data are used to demonstrate our results.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127252811","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 : 2007-06-17DOI: 10.1109/CVPR.2007.383233
G. Tsechpenakis, Dimitris N. Metaxas
We present a topology independent solution for segmenting objects with texture patterns of any scale, using an implicit deformable model driven by conditional random fields (CRFs). Our model integrates region and edge information as image driven terms, whereas the probabilistic shape and internal (smoothness) terms use representations similar to the level-set based methods. The evolution of the model is solved as a MAP estimation problem, where the target conditional probability is decomposed into the internal term and the image-driven term. For the later, we use discriminative CRFs in two scales, pixel- and patch-based, to obtain smooth probability fields based on the corresponding image features. The advantages and novelties of our approach are (i) the integration of CRFs with implicit deformable models in a tightly coupled scheme, (ii) the use of CRFs which avoids ambiguities in the probability fields, (iii) the handling of local feature variations by updating the model interior statistics and processing at different spatial scales, and (v) the independence from the topology. We demonstrate the performance of our method in a wide variety of images, from the zebra and cheetah examples to the left and right ventricles in cardiac images.
{"title":"CRF-driven Implicit Deformable Model","authors":"G. Tsechpenakis, Dimitris N. Metaxas","doi":"10.1109/CVPR.2007.383233","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383233","url":null,"abstract":"We present a topology independent solution for segmenting objects with texture patterns of any scale, using an implicit deformable model driven by conditional random fields (CRFs). Our model integrates region and edge information as image driven terms, whereas the probabilistic shape and internal (smoothness) terms use representations similar to the level-set based methods. The evolution of the model is solved as a MAP estimation problem, where the target conditional probability is decomposed into the internal term and the image-driven term. For the later, we use discriminative CRFs in two scales, pixel- and patch-based, to obtain smooth probability fields based on the corresponding image features. The advantages and novelties of our approach are (i) the integration of CRFs with implicit deformable models in a tightly coupled scheme, (ii) the use of CRFs which avoids ambiguities in the probability fields, (iii) the handling of local feature variations by updating the model interior statistics and processing at different spatial scales, and (v) the independence from the topology. We demonstrate the performance of our method in a wide variety of images, from the zebra and cheetah examples to the left and right ventricles in cardiac images.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127357869","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 : 2007-06-17DOI: 10.1109/CVPR.2007.383206
A. Gijsenij, T. Gevers
Although many color constancy methods exist, they are all based on specific assumptions such as the set of possible light sources, or the spatial and spectral characteristics of images. As a consequence, no algorithm can be considered as universal. However, with the large variety of available methods, the question is how to select the method that induces equivalent classes for different image characteristics. Furthermore, the subsequent question is how to combine the different algorithms in a proper way. To achieve selection and combining of color constancy algorithms, in this paper, natural image statistics are used to identify the most important characteristics of color images. Then, based on these image characteristics, the proper color constancy algorithm (or best combination of algorithms) is selected for a specific image. To capture the image characteristics, the Weibull parameterization (e.g. texture and contrast) is used. Experiments show that, on a large data set of 11,000 images, our approach outperforms current state-of-the-art single algorithms, as well as simple alternatives for combining several algorithms.
{"title":"Color Constancy using Natural Image Statistics","authors":"A. Gijsenij, T. Gevers","doi":"10.1109/CVPR.2007.383206","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383206","url":null,"abstract":"Although many color constancy methods exist, they are all based on specific assumptions such as the set of possible light sources, or the spatial and spectral characteristics of images. As a consequence, no algorithm can be considered as universal. However, with the large variety of available methods, the question is how to select the method that induces equivalent classes for different image characteristics. Furthermore, the subsequent question is how to combine the different algorithms in a proper way. To achieve selection and combining of color constancy algorithms, in this paper, natural image statistics are used to identify the most important characteristics of color images. Then, based on these image characteristics, the proper color constancy algorithm (or best combination of algorithms) is selected for a specific image. To capture the image characteristics, the Weibull parameterization (e.g. texture and contrast) is used. Experiments show that, on a large data set of 11,000 images, our approach outperforms current state-of-the-art single algorithms, as well as simple alternatives for combining several algorithms.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127493361","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：