Pub Date : 2009-06-20DOI: 10.1109/CVPR.2009.5206553
Chunming Li, Chris Gatenby, Li Wang, J. Gore
This paper proposes a new energy minimization framework for simultaneous estimation of the bias field and segmentation of tissues for magnetic resonance images. The bias field is modeled as a linear combination of a set of basis functions, and thereby parameterized by the coefficients of the basis functions. We define an energy that depends on the coefficients of the basis functions, the membership functions of the tissues in the image, and the constants approximating the true signal from the corresponding tissues. This energy is convex in each of its variables. Bias field estimation and image segmentation are simultaneously achieved as the result of minimizing this energy. We provide an efficient iterative algorithm for energy minimization, which converges to the optimal solution at a fast rate. A salient advantage of our method is that its result is independent of initialization, which allows robust and fully automated application. The proposed method has been successfully applied to 3-Tesla MR images with desirable results. Comparisons with other approaches demonstrate the superior performance of this algorithm.
{"title":"A robust parametric method for bias field estimation and segmentation of MR images","authors":"Chunming Li, Chris Gatenby, Li Wang, J. Gore","doi":"10.1109/CVPR.2009.5206553","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206553","url":null,"abstract":"This paper proposes a new energy minimization framework for simultaneous estimation of the bias field and segmentation of tissues for magnetic resonance images. The bias field is modeled as a linear combination of a set of basis functions, and thereby parameterized by the coefficients of the basis functions. We define an energy that depends on the coefficients of the basis functions, the membership functions of the tissues in the image, and the constants approximating the true signal from the corresponding tissues. This energy is convex in each of its variables. Bias field estimation and image segmentation are simultaneously achieved as the result of minimizing this energy. We provide an efficient iterative algorithm for energy minimization, which converges to the optimal solution at a fast rate. A salient advantage of our method is that its result is independent of initialization, which allows robust and fully automated application. The proposed method has been successfully applied to 3-Tesla MR images with desirable results. Comparisons with other approaches demonstrate the superior performance of this algorithm.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127544805","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206527
Shaolei Feng, S. Zhou, Sara Good, D. Comaniciu
3D ultrasound imaging has been increasingly used in clinics for fetal examination. However, manually searching for the optimal view of the fetal face in 3D ultrasound volumes is cumbersome and time-consuming even for expert physicians and sonographers. In this paper we propose a learning-based approach which combines both 3D and 2D information for automatic and fast fetal face detection from 3D ultrasound volumes. Our approach applies a new technique - constrained marginal space learning - for 3D face mesh detection, and combines a boosting-based 2D profile detection to refine 3D face pose. To enhance the rendering of the fetal face, an automatic carving algorithm is proposed to remove all obstructions in front of the face based on the detected face mesh. Experiments are performed on a challenging 3D ultrasound data set containing 1010 fetal volumes. The results show that our system not only achieves excellent detection accuracy but also runs very fast - it can detect the fetal face from the 3D data in 1 second on a dual-core 2.0 GHz computer.
{"title":"Automatic fetal face detection from ultrasound volumes via learning 3D and 2D information","authors":"Shaolei Feng, S. Zhou, Sara Good, D. Comaniciu","doi":"10.1109/CVPR.2009.5206527","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206527","url":null,"abstract":"3D ultrasound imaging has been increasingly used in clinics for fetal examination. However, manually searching for the optimal view of the fetal face in 3D ultrasound volumes is cumbersome and time-consuming even for expert physicians and sonographers. In this paper we propose a learning-based approach which combines both 3D and 2D information for automatic and fast fetal face detection from 3D ultrasound volumes. Our approach applies a new technique - constrained marginal space learning - for 3D face mesh detection, and combines a boosting-based 2D profile detection to refine 3D face pose. To enhance the rendering of the fetal face, an automatic carving algorithm is proposed to remove all obstructions in front of the face based on the detected face mesh. Experiments are performed on a challenging 3D ultrasound data set containing 1010 fetal volumes. The results show that our system not only achieves excellent detection accuracy but also runs very fast - it can detect the fetal face from the 3D data in 1 second on a dual-core 2.0 GHz computer.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129973997","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206809
Tianzhu Zhang, Hanqing Lu, S. Li
Activity analysis is a basic task in video surveillance and has become an active research area. However, due to the diversity of moving objects category and their motion patterns, developing robust semantic scene models for activity analysis remains a challenging problem in traffic scenarios. This paper proposes a novel framework to learn semantic scene models. In this framework, the detected moving objects are first classified as pedestrians or vehicles via a co-trained classifier which takes advantage of the multiview information of objects. As a result, the framework can automatically learn motion patterns respectively for pedestrians and vehicles. Then, a graph is proposed to learn and cluster the motion patterns. To this end, trajectory is parameterized and the image is cut into multiple blocks which are taken as the nodes in the graph. Based on the parameters of trajectories, the primary motion patterns in each node (block) are extracted via Gaussian mixture model (GMM), and supplied to this graph. The graph cut algorithm is finally employed to group the motion patterns together, and trajectories are clustered to learn semantic scene models. Experimental results and applications to real world scenes show the validity of our proposed method.
{"title":"Learning semantic scene models by object classification and trajectory clustering","authors":"Tianzhu Zhang, Hanqing Lu, S. Li","doi":"10.1109/CVPR.2009.5206809","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206809","url":null,"abstract":"Activity analysis is a basic task in video surveillance and has become an active research area. However, due to the diversity of moving objects category and their motion patterns, developing robust semantic scene models for activity analysis remains a challenging problem in traffic scenarios. This paper proposes a novel framework to learn semantic scene models. In this framework, the detected moving objects are first classified as pedestrians or vehicles via a co-trained classifier which takes advantage of the multiview information of objects. As a result, the framework can automatically learn motion patterns respectively for pedestrians and vehicles. Then, a graph is proposed to learn and cluster the motion patterns. To this end, trajectory is parameterized and the image is cut into multiple blocks which are taken as the nodes in the graph. Based on the parameters of trajectories, the primary motion patterns in each node (block) are extracted via Gaussian mixture model (GMM), and supplied to this graph. The graph cut algorithm is finally employed to group the motion patterns together, and trajectories are clustered to learn semantic scene models. Experimental results and applications to real world scenes show the validity of our proposed method.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129134467","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206507
Y. S. Heo, Kyoung Mu Lee, Sang Uk Lee
Radiometric variations between input images can seriously degrade the performance of stereo matching algorithms. In this situation, mutual information is a very popular and powerful measure which can find any global relationship of intensities between two input images taken from unknown sources. The mutual information-based method, however, is still ambiguous or erroneous as regards local radiometric variations, since it only accounts for global variation between images, and does not contain spatial information properly. In this paper, we present a new method based on mutual information combined with SIFT descriptor to find correspondence for images which undergo local as well as global radiometric variations. We transform the input color images to log-chromaticity color space from which a linear relationship can be established. To incorporate spatial information in mutual information, we utilize the SIFT descriptor which includes near pixel gradient histogram to construct a joint probability in log-chromaticity color space. By combining the mutual information as an appearance measure and the SIFT descriptor as a geometric measure, we devise a robust and accurate stereo system. Experimental results show that our method is superior to the state-of-the art algorithms including conventional mutual information-based methods and window correlation methods under various radiometric changes.
{"title":"Mutual information-based stereo matching combined with SIFT descriptor in log-chromaticity color space","authors":"Y. S. Heo, Kyoung Mu Lee, Sang Uk Lee","doi":"10.1109/CVPR.2009.5206507","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206507","url":null,"abstract":"Radiometric variations between input images can seriously degrade the performance of stereo matching algorithms. In this situation, mutual information is a very popular and powerful measure which can find any global relationship of intensities between two input images taken from unknown sources. The mutual information-based method, however, is still ambiguous or erroneous as regards local radiometric variations, since it only accounts for global variation between images, and does not contain spatial information properly. In this paper, we present a new method based on mutual information combined with SIFT descriptor to find correspondence for images which undergo local as well as global radiometric variations. We transform the input color images to log-chromaticity color space from which a linear relationship can be established. To incorporate spatial information in mutual information, we utilize the SIFT descriptor which includes near pixel gradient histogram to construct a joint probability in log-chromaticity color space. By combining the mutual information as an appearance measure and the SIFT descriptor as a geometric measure, we devise a robust and accurate stereo system. Experimental results show that our method is superior to the state-of-the art algorithms including conventional mutual information-based methods and window correlation methods under various radiometric changes.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132861938","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206666
Jun-Seong Kim, Jin-Hwan Kim, Chang-Su Kim
An adaptive image and video retargeting algorithm based on Fourier analysis is proposed in this work. We first divide an input image into several strips using the gradient information so that each strip consists of textures of similar complexities. Then, we scale each strip adaptively according to its importance measure. More specifically, the distortions, generated by the scaling procedure, are formulated in the frequency domain using the Fourier transform. Then, the objective is to determine the sizes of scaled strips to minimize the sum of distortions, subject to the constraint that the sum of their sizes should equal the size of the target output image. We solve this constrained optimization problem using the Lagrangian multiplier technique. Moreover, we extend the approach to the retargeting of video sequences. Simulation results demonstrate that the proposed algorithm provides reliable retargeting performance efficiently.
{"title":"Adaptive image and video retargeting technique based on Fourier analysis","authors":"Jun-Seong Kim, Jin-Hwan Kim, Chang-Su Kim","doi":"10.1109/CVPR.2009.5206666","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206666","url":null,"abstract":"An adaptive image and video retargeting algorithm based on Fourier analysis is proposed in this work. We first divide an input image into several strips using the gradient information so that each strip consists of textures of similar complexities. Then, we scale each strip adaptively according to its importance measure. More specifically, the distortions, generated by the scaling procedure, are formulated in the frequency domain using the Fourier transform. Then, the objective is to determine the sizes of scaled strips to minimize the sum of distortions, subject to the constraint that the sum of their sizes should equal the size of the target output image. We solve this constrained optimization problem using the Lagrangian multiplier technique. Moreover, we extend the approach to the retargeting of video sequences. Simulation results demonstrate that the proposed algorithm provides reliable retargeting performance efficiently.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126228766","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206664
H. Ackermann, B. Rosenhahn
The problem of reconstructing a 3D scene from a moving camera can be solved by means of the so-called Factorization method. It directly computes a global solution without the need to merge several partial reconstructions. However, if the trajectories are not complete, i.e. not every feature point could be observed in all the images, this method cannot be used. We use a Factorization-style algorithm for recovering the unobserved feature positions in a non-incremental way. This method uniformly utilizes all data and finds a global solution without any need of sequential or hierarchical merging. Two contributions are made in this work: Firstly, partially known trajectories are completed by minimizing the distance between the subspace and the trajectory within an affine subspace associated with the trajectory. This amounts to imposing a global constraint on the data. Secondly, we propose to further include local constraints derived from epipolar geometry into the estimation. It is shown how to simultaneously optimize both constraints. By using simulated and real image sequences we show the improvements achieved with our algorithm.
{"title":"Trajectory reconstruction for affine structure-from-motion by global and local constraints","authors":"H. Ackermann, B. Rosenhahn","doi":"10.1109/CVPR.2009.5206664","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206664","url":null,"abstract":"The problem of reconstructing a 3D scene from a moving camera can be solved by means of the so-called Factorization method. It directly computes a global solution without the need to merge several partial reconstructions. However, if the trajectories are not complete, i.e. not every feature point could be observed in all the images, this method cannot be used. We use a Factorization-style algorithm for recovering the unobserved feature positions in a non-incremental way. This method uniformly utilizes all data and finds a global solution without any need of sequential or hierarchical merging. Two contributions are made in this work: Firstly, partially known trajectories are completed by minimizing the distance between the subspace and the trajectory within an affine subspace associated with the trajectory. This amounts to imposing a global constraint on the data. Secondly, we propose to further include local constraints derived from epipolar geometry into the estimation. It is shown how to simultaneously optimize both constraints. By using simulated and real image sequences we show the improvements achieved with our algorithm.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126403555","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206836
Li Zhang, Sundeep Vaddadi, Hailin Jin, S. Nayar
We present a novel multi-view denoising algorithm. Our algorithm takes noisy images taken from different viewpoints as input and groups similar patches in the input images using depth estimation. We model intensity-dependent noise in low-light conditions and use the principal component analysis and tensor analysis to remove such noise. The dimensionalities for both PCA and tensor analysis are automatically computed in a way that is adaptive to the complexity of image structures in the patches. Our method is based on a probabilistic formulation that marginalizes depth maps as hidden variables and therefore does not require perfect depth estimation. We validate our algorithm on both synthetic and real images with different content. Our algorithm compares favorably against several state-of-the-art denoising algorithms.
{"title":"Multiple view image denoising","authors":"Li Zhang, Sundeep Vaddadi, Hailin Jin, S. Nayar","doi":"10.1109/CVPR.2009.5206836","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206836","url":null,"abstract":"We present a novel multi-view denoising algorithm. Our algorithm takes noisy images taken from different viewpoints as input and groups similar patches in the input images using depth estimation. We model intensity-dependent noise in low-light conditions and use the principal component analysis and tensor analysis to remove such noise. The dimensionalities for both PCA and tensor analysis are automatically computed in a way that is adaptive to the complexity of image structures in the patches. Our method is based on a probabilistic formulation that marginalizes depth maps as hidden variables and therefore does not require perfect depth estimation. We validate our algorithm on both synthetic and real images with different content. Our algorithm compares favorably against several state-of-the-art denoising algorithms.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114176214","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206557
Marcin Marszalek, I. Laptev, C. Schmid
This paper exploits the context of natural dynamic scenes for human action recognition in video. Human actions are frequently constrained by the purpose and the physical properties of scenes and demonstrate high correlation with particular scene classes. For example, eating often happens in a kitchen while running is more common outdoors. The contribution of this paper is three-fold: (a) we automatically discover relevant scene classes and their correlation with human actions, (b) we show how to learn selected scene classes from video without manual supervision and (c) we develop a joint framework for action and scene recognition and demonstrate improved recognition of both in natural video. We use movie scripts as a means of automatic supervision for training. For selected action classes we identify correlated scene classes in text and then retrieve video samples of actions and scenes for training using script-to-video alignment. Our visual models for scenes and actions are formulated within the bag-of-features framework and are combined in a joint scene-action SVM-based classifier. We report experimental results and validate the method on a new large dataset with twelve action classes and ten scene classes acquired from 69 movies.
{"title":"Actions in context","authors":"Marcin Marszalek, I. Laptev, C. Schmid","doi":"10.1109/CVPR.2009.5206557","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206557","url":null,"abstract":"This paper exploits the context of natural dynamic scenes for human action recognition in video. Human actions are frequently constrained by the purpose and the physical properties of scenes and demonstrate high correlation with particular scene classes. For example, eating often happens in a kitchen while running is more common outdoors. The contribution of this paper is three-fold: (a) we automatically discover relevant scene classes and their correlation with human actions, (b) we show how to learn selected scene classes from video without manual supervision and (c) we develop a joint framework for action and scene recognition and demonstrate improved recognition of both in natural video. We use movie scripts as a means of automatic supervision for training. For selected action classes we identify correlated scene classes in text and then retrieve video samples of actions and scenes for training using script-to-video alignment. Our visual models for scenes and actions are formulated within the bag-of-features framework and are combined in a joint scene-action SVM-based classifier. We report experimental results and validate the method on a new large dataset with twelve action classes and ten scene classes acquired from 69 movies.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121072092","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206545
K. Kavukcuoglu, Marc'Aurelio Ranzato, R. Fergus, Yann LeCun
Several recently-proposed architectures for high-performance object recognition are composed of two main stages: a feature extraction stage that extracts locally-invariant feature vectors from regularly spaced image patches, and a somewhat generic supervised classifier. The first stage is often composed of three main modules: (1) a bank of filters (often oriented edge detectors); (2) a non-linear transform, such as a point-wise squashing functions, quantization, or normalization; (3) a spatial pooling operation which combines the outputs of similar filters over neighboring regions. We propose a method that automatically learns such feature extractors in an unsupervised fashion by simultaneously learning the filters and the pooling units that combine multiple filter outputs together. The method automatically generates topographic maps of similar filters that extract features of orientations, scales, and positions. These similar filters are pooled together, producing locally-invariant outputs. The learned feature descriptors give comparable results as SIFT on image recognition tasks for which SIFT is well suited, and better results than SIFT on tasks for which SIFT is less well suited.
{"title":"Learning invariant features through topographic filter maps","authors":"K. Kavukcuoglu, Marc'Aurelio Ranzato, R. Fergus, Yann LeCun","doi":"10.1109/CVPR.2009.5206545","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206545","url":null,"abstract":"Several recently-proposed architectures for high-performance object recognition are composed of two main stages: a feature extraction stage that extracts locally-invariant feature vectors from regularly spaced image patches, and a somewhat generic supervised classifier. The first stage is often composed of three main modules: (1) a bank of filters (often oriented edge detectors); (2) a non-linear transform, such as a point-wise squashing functions, quantization, or normalization; (3) a spatial pooling operation which combines the outputs of similar filters over neighboring regions. We propose a method that automatically learns such feature extractors in an unsupervised fashion by simultaneously learning the filters and the pooling units that combine multiple filter outputs together. The method automatically generates topographic maps of similar filters that extract features of orientations, scales, and positions. These similar filters are pooled together, producing locally-invariant outputs. The learned feature descriptors give comparable results as SIFT on image recognition tasks for which SIFT is well suited, and better results than SIFT on tasks for which SIFT is less well suited.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121089634","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206710
P. Turaga, R. Chellappa
Human activity analysis is an important problem in computer vision with applications in surveillance and summarization and indexing of consumer content. Complex human activities are characterized by non-linear dynamics that make learning, inference and recognition hard. In this paper, we consider the problem of modeling and recognizing complex activities which exhibit time-varying dynamics. To this end, we describe activities as outputs of linear dynamic systems (LDS) whose parameters vary with time, or a time-varying linear dynamic system (TV-LDS). We discuss parameter estimation methods for this class of models by assuming that the parameters are locally time-invariant. Then, we represent the space of LDS models as a Grassmann manifold. Then, the TV-LDS model is defined as a trajectory on the Grassmann manifold. We show how trajectories on the Grassmannian can be characterized using appropriate distance metrics and statistical methods that reflect the underlying geometry of the manifold. This results in more expressive and powerful models for complex human activities. We demonstrate the strength of the framework for activity-based summarization of long videos and recognition of complex human actions on two datasets.
{"title":"Locally time-invariant models of human activities using trajectories on the grassmannian","authors":"P. Turaga, R. Chellappa","doi":"10.1109/CVPR.2009.5206710","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206710","url":null,"abstract":"Human activity analysis is an important problem in computer vision with applications in surveillance and summarization and indexing of consumer content. Complex human activities are characterized by non-linear dynamics that make learning, inference and recognition hard. In this paper, we consider the problem of modeling and recognizing complex activities which exhibit time-varying dynamics. To this end, we describe activities as outputs of linear dynamic systems (LDS) whose parameters vary with time, or a time-varying linear dynamic system (TV-LDS). We discuss parameter estimation methods for this class of models by assuming that the parameters are locally time-invariant. Then, we represent the space of LDS models as a Grassmann manifold. Then, the TV-LDS model is defined as a trajectory on the Grassmann manifold. We show how trajectories on the Grassmannian can be characterized using appropriate distance metrics and statistical methods that reflect the underlying geometry of the manifold. This results in more expressive and powerful models for complex human activities. We demonstrate the strength of the framework for activity-based summarization of long videos and recognition of complex human actions on two datasets.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115315126","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：