Pub Date : 2009-06-20DOI: 10.1109/CVPR.2009.5206791
Yimeng Zhang, Tsuhan Chen
Higher order spatial features, such as doublets or triplets have been used to incorporate spatial information into the bag-of-local-features model. Due to computational limits, researchers have only been using features up to the 3rd order, i.e., triplets, since the number of features increases exponentially with the order. We propose an algorithm for identifying high-order spatial features efficiently. The algorithm directly evaluates the inner product of the feature vectors from two images to be compared, identifying all high-order features automatically. The algorithm hence serves as a kernel for any kernel-based learning algorithms. The algorithm is based on the idea that if a high-order spatial feature co-occurs in both images, the occurrence of the feature in one image would be a translation from the occurrence of the same feature in the other image. This enables us to compute the kernel in time that is linear to the number of local features in an image (same as the bag of local features approach), regardless of the order. Therefore, our algorithm does not limit the upper bound of the order as in previous work. The experiment results on the object categorization task show that high order features can be calculated efficiently and provide significant improvement in object categorization performance.
{"title":"Efficient Kernels for identifying unbounded-order spatial features","authors":"Yimeng Zhang, Tsuhan Chen","doi":"10.1109/CVPR.2009.5206791","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206791","url":null,"abstract":"Higher order spatial features, such as doublets or triplets have been used to incorporate spatial information into the bag-of-local-features model. Due to computational limits, researchers have only been using features up to the 3rd order, i.e., triplets, since the number of features increases exponentially with the order. We propose an algorithm for identifying high-order spatial features efficiently. The algorithm directly evaluates the inner product of the feature vectors from two images to be compared, identifying all high-order features automatically. The algorithm hence serves as a kernel for any kernel-based learning algorithms. The algorithm is based on the idea that if a high-order spatial feature co-occurs in both images, the occurrence of the feature in one image would be a translation from the occurrence of the same feature in the other image. This enables us to compute the kernel in time that is linear to the number of local features in an image (same as the bag of local features approach), regardless of the order. Therefore, our algorithm does not limit the upper bound of the order as in previous work. The experiment results on the object categorization task show that high order features can be calculated efficiently and provide significant improvement in object categorization performance.","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":"116060066","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.2009.5206774
Kegan G. G. Samuel, M. Tappen
We present a new approach for the discriminative training of continuous-valued Markov Random Field (MRF) model parameters. In our approach we train the MRF model by optimizing the parameters so that the minimum energy solution of the model is as similar as possible to the ground-truth. This leads to parameters which are directly optimized to increase the quality of the MAP estimates during inference. Our proposed technique allows us to develop a framework that is flexible and intuitively easy to understand and implement, which makes it an attractive alternative to learn the parameters of a continuous-valued MRF model. We demonstrate the effectiveness of our technique by applying it to the problems of image denoising and in-painting using the Field of Experts model. In our experiments, the performance of our system compares favourably to the Field of Experts model trained using contrastive divergence when applied to the denoising and in-painting tasks.
{"title":"Learning optimized MAP estimates in continuously-valued MRF models","authors":"Kegan G. G. Samuel, M. Tappen","doi":"10.1109/CVPR.2009.5206774","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206774","url":null,"abstract":"We present a new approach for the discriminative training of continuous-valued Markov Random Field (MRF) model parameters. In our approach we train the MRF model by optimizing the parameters so that the minimum energy solution of the model is as similar as possible to the ground-truth. This leads to parameters which are directly optimized to increase the quality of the MAP estimates during inference. Our proposed technique allows us to develop a framework that is flexible and intuitively easy to understand and implement, which makes it an attractive alternative to learn the parameters of a continuous-valued MRF model. We demonstrate the effectiveness of our technique by applying it to the problems of image denoising and in-painting using the Field of Experts model. In our experiments, the performance of our system compares favourably to the Field of Experts model trained using contrastive divergence when applied to the denoising and in-painting tasks.","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":"116088711","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.2009.5206739
C. Rother, Pushmeet Kohli, Wei Feng, Jiaya Jia
Higher order energy functions have the ability to encode high level structural dependencies between pixels, which have been shown to be extremely powerful for image labeling problems. Their use, however, is severely hampered in practice by the intractable complexity of representing and minimizing such functions. We observed that higher order functions encountered in computer vision are very often “sparse”, i.e. many labelings of a higher order clique are equally unlikely and hence have the same high cost. In this paper, we address the problem of minimizing such sparse higher order energy functions. Our method works by transforming the problem into an equivalent quadratic function minimization problem. The resulting quadratic function can be minimized using popular message passing or graph cut based algorithms for MAP inference. Although this is primarily a theoretical paper, it also shows how higher order functions can be used to obtain impressive results for the binary texture restoration problem.
{"title":"Minimizing sparse higher order energy functions of discrete variables","authors":"C. Rother, Pushmeet Kohli, Wei Feng, Jiaya Jia","doi":"10.1109/CVPR.2009.5206739","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206739","url":null,"abstract":"Higher order energy functions have the ability to encode high level structural dependencies between pixels, which have been shown to be extremely powerful for image labeling problems. Their use, however, is severely hampered in practice by the intractable complexity of representing and minimizing such functions. We observed that higher order functions encountered in computer vision are very often “sparse”, i.e. many labelings of a higher order clique are equally unlikely and hence have the same high cost. In this paper, we address the problem of minimizing such sparse higher order energy functions. Our method works by transforming the problem into an equivalent quadratic function minimization problem. The resulting quadratic function can be minimized using popular message passing or graph cut based algorithms for MAP inference. Although this is primarily a theoretical paper, it also shows how higher order functions can be used to obtain impressive results for the binary texture restoration problem.","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":"116422024","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.2009.5206711
Jian-Feng Cai, Hui Ji, Chaoqiang Liu, Zuowei Shen
One promising approach to remove motion deblurring is to recover one clear image using an image pair. Existing dual-image methods require an accurate image alignment between the image pair, which could be very challenging even with the help of user interactions. Based on the observation that typical motion-blur kernels will have an extremely sparse representation in the redundant curvelet system, we propose a new minimization model to recover a clear image from the blurred image pair by enhancing the sparsity of blur kernels in the curvelet system. The sparsity prior on the motion-blur kernels improves the robustness of our algorithm to image alignment errors and image formation noise. Also, a numerical method is presented to efficiently solve the resulted minimization problem. The experiments showed that our proposed algorithm is capable of accurately estimating the blur kernels of complex camera motions with low requirement on the accuracy of image alignment, which in turn led to a high-quality recovered image from the blurred image pair.
{"title":"High-quality curvelet-based motion deblurring from an image pair","authors":"Jian-Feng Cai, Hui Ji, Chaoqiang Liu, Zuowei Shen","doi":"10.1109/CVPR.2009.5206711","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206711","url":null,"abstract":"One promising approach to remove motion deblurring is to recover one clear image using an image pair. Existing dual-image methods require an accurate image alignment between the image pair, which could be very challenging even with the help of user interactions. Based on the observation that typical motion-blur kernels will have an extremely sparse representation in the redundant curvelet system, we propose a new minimization model to recover a clear image from the blurred image pair by enhancing the sparsity of blur kernels in the curvelet system. The sparsity prior on the motion-blur kernels improves the robustness of our algorithm to image alignment errors and image formation noise. Also, a numerical method is presented to efficiently solve the resulted minimization problem. The experiments showed that our proposed algorithm is capable of accurately estimating the blur kernels of complex camera motions with low requirement on the accuracy of image alignment, which in turn led to a high-quality recovered image from the blurred image pair.","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":"116583901","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.2009.5206826
Nikhil Rasiwasia, N. Vasconcelos
We present a simple framework to model contextual relationships between visual concepts. The new framework combines ideas from previous object-centric methods (which model contextual relationships between objects in an image, such as their co-occurrence patterns) and scene-centric methods (which learn a holistic context model from the entire image, known as its “gist”). This is accomplished without demarcating individual concepts or regions in the image. First, using the output of a generic appearance based concept detection system, a semantic space is formulated, where each axis represents a semantic feature. Next, context models are learned for each of the concepts in the semantic space, using mixtures of Dirichlet distributions. Finally, an image is represented as a vector of posterior concept probabilities under these contextual concept models. It is shown that these posterior probabilities are remarkably noise-free, and an effective model of the contextual relationships between semantic concepts in natural images. This is further demonstrated through an experimental evaluation with respect to two vision tasks, viz. scene classification and image annotation, on benchmark datasets. The results show that, besides quite simple to compute, the proposed context models attain superior performance than state of the art systems in both tasks.
{"title":"Holistic context modeling using semantic co-occurrences","authors":"Nikhil Rasiwasia, N. Vasconcelos","doi":"10.1109/CVPR.2009.5206826","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206826","url":null,"abstract":"We present a simple framework to model contextual relationships between visual concepts. The new framework combines ideas from previous object-centric methods (which model contextual relationships between objects in an image, such as their co-occurrence patterns) and scene-centric methods (which learn a holistic context model from the entire image, known as its “gist”). This is accomplished without demarcating individual concepts or regions in the image. First, using the output of a generic appearance based concept detection system, a semantic space is formulated, where each axis represents a semantic feature. Next, context models are learned for each of the concepts in the semantic space, using mixtures of Dirichlet distributions. Finally, an image is represented as a vector of posterior concept probabilities under these contextual concept models. It is shown that these posterior probabilities are remarkably noise-free, and an effective model of the contextual relationships between semantic concepts in natural images. This is further demonstrated through an experimental evaluation with respect to two vision tasks, viz. scene classification and image annotation, on benchmark datasets. The results show that, besides quite simple to compute, the proposed context models attain superior performance than state of the art systems in both tasks.","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":"122519314","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.2009.5206697
T. Brox, C. Bregler, Jitendra Malik
The literature currently provides two ways to establish point correspondences between images with moving objects. On one side, there are energy minimization methods that yield very accurate, dense flow fields, but fail as displacements get too large. On the other side, there is descriptor matching that allows for large displacements, but correspondences are very sparse, have limited accuracy, and due to missing regularity constraints there are many outliers. In this paper we propose a method that can combine the advantages of both matching strategies. A region hierarchy is established for both images. Descriptor matching on these regions provides a sparse set of hypotheses for correspondences. These are integrated into a variational approach and guide the local optimization to large displacement solutions. The variational optimization selects among the hypotheses and provides dense and subpixel accurate estimates, making use of geometric constraints and all available image information.
{"title":"Large displacement optical flow","authors":"T. Brox, C. Bregler, Jitendra Malik","doi":"10.1109/CVPR.2009.5206697","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206697","url":null,"abstract":"The literature currently provides two ways to establish point correspondences between images with moving objects. On one side, there are energy minimization methods that yield very accurate, dense flow fields, but fail as displacements get too large. On the other side, there is descriptor matching that allows for large displacements, but correspondences are very sparse, have limited accuracy, and due to missing regularity constraints there are many outliers. In this paper we propose a method that can combine the advantages of both matching strategies. A region hierarchy is established for both images. Descriptor matching on these regions provides a sparse set of hypotheses for correspondences. These are integrated into a variational approach and guide the local optimization to large displacement solutions. The variational optimization selects among the hypotheses and provides dense and subpixel accurate estimates, making use of geometric constraints and all available image information.","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":"122594783","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.2009.5206569
Jaechul Kim, K. Grauman
We propose a space-time Markov random field (MRF) model to detect abnormal activities in video. The nodes in the MRF graph correspond to a grid of local regions in the video frames, and neighboring nodes in both space and time are associated with links. To learn normal patterns of activity at each local node, we capture the distribution of its typical optical flow with a mixture of probabilistic principal component analyzers. For any new optical flow patterns detected in incoming video clips, we use the learned model and MRF graph to compute a maximum a posteriori estimate of the degree of normality at each local node. Further, we show how to incrementally update the current model parameters as new video observations stream in, so that the model can efficiently adapt to visual context changes over a long period of time. Experimental results on surveillance videos show that our space-time MRF model robustly detects abnormal activities both in a local and global sense: not only does it accurately localize the atomic abnormal activities in a crowded video, but at the same time it captures the global-level abnormalities caused by irregular interactions between local activities.
{"title":"Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates","authors":"Jaechul Kim, K. Grauman","doi":"10.1109/CVPR.2009.5206569","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206569","url":null,"abstract":"We propose a space-time Markov random field (MRF) model to detect abnormal activities in video. The nodes in the MRF graph correspond to a grid of local regions in the video frames, and neighboring nodes in both space and time are associated with links. To learn normal patterns of activity at each local node, we capture the distribution of its typical optical flow with a mixture of probabilistic principal component analyzers. For any new optical flow patterns detected in incoming video clips, we use the learned model and MRF graph to compute a maximum a posteriori estimate of the degree of normality at each local node. Further, we show how to incrementally update the current model parameters as new video observations stream in, so that the model can efficiently adapt to visual context changes over a long period of time. Experimental results on surveillance videos show that our space-time MRF model robustly detects abnormal activities both in a local and global sense: not only does it accurately localize the atomic abnormal activities in a crowded video, but at the same time it captures the global-level abnormalities caused by irregular interactions between local activities.","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":"114176137","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.2009.5206489
A. Fossati, M. Salzmann, P. Fua
The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. The true range of motion can therefore be represented by latent variables that span a low-dimensional space. This has often been used to make motion tracking easier. However, learning the latent space in a problem- independent way makes it non trivial to initialize the tracking process by picking appropriate initial values for the latent variables, and thus for the pose. In this paper, we show that by directly using observable quantities as our latent variables, we eliminate this problem and achieve full automation given only modest amounts of training data. More specifically, we exploit the fact that the trajectory of a person's feet or hands strongly constrains body pose in motions such as skating, skiing, or golfing. These trajectories are easy to compute and to parameterize using a few variables. We treat these as our latent variables and learn a mapping between them and sequences of body poses. In this manner, by simply tracking the feet or the hands, we can reliably guess initial poses over whole sequences and, then, refine them.
{"title":"Observable subspaces for 3D human motion recovery","authors":"A. Fossati, M. Salzmann, P. Fua","doi":"10.1109/CVPR.2009.5206489","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206489","url":null,"abstract":"The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. The true range of motion can therefore be represented by latent variables that span a low-dimensional space. This has often been used to make motion tracking easier. However, learning the latent space in a problem- independent way makes it non trivial to initialize the tracking process by picking appropriate initial values for the latent variables, and thus for the pose. In this paper, we show that by directly using observable quantities as our latent variables, we eliminate this problem and achieve full automation given only modest amounts of training data. More specifically, we exploit the fact that the trajectory of a person's feet or hands strongly constrains body pose in motions such as skating, skiing, or golfing. These trajectories are easy to compute and to parameterize using a few variables. We treat these as our latent variables and learn a mapping between them and sequences of body poses. In this manner, by simply tracking the feet or the hands, we can reliably guess initial poses over whole sequences and, then, refine them.","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":"117261755","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.2009.5206781
F. Perronnin, Yan Liu
A state-of-the-art approach to measure the similarity of two images is to model each image by a continuous distribution, generally a Gaussian mixture model (GMM), and to compute a probabilistic similarity between the GMMs. One limitation of traditional measures such as the Kullback-Leibler (KL) divergence and the probability product kernel (PPK) is that they measure a global match of distributions. This paper introduces a novel image representation. We propose to approximate an image, modeled by a GMM, as a convex combination of K reference image GMMs, and then to describe the image as the K-dimensional vector of mixture weights. The computed weights encode a similarity that favors local matches (i.e. matches of individual Gaussians) and is therefore fundamentally different from the KL or PPK. Although the computation of the mixture weights is a convex optimization problem, its direct optimization is difficult. We propose two approximate optimization algorithms: the first one based on traditional sampling methods, the second one based on a variational bound approximation of the true objective function. We apply this novel representation to the image categorization problem and compare its performance to traditional kernel-based methods. We demonstrate on the PASCAL VOC 2007 dataset a consistent increase in classification accuracy.
{"title":"Modeling images as mixtures of reference images","authors":"F. Perronnin, Yan Liu","doi":"10.1109/CVPR.2009.5206781","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206781","url":null,"abstract":"A state-of-the-art approach to measure the similarity of two images is to model each image by a continuous distribution, generally a Gaussian mixture model (GMM), and to compute a probabilistic similarity between the GMMs. One limitation of traditional measures such as the Kullback-Leibler (KL) divergence and the probability product kernel (PPK) is that they measure a global match of distributions. This paper introduces a novel image representation. We propose to approximate an image, modeled by a GMM, as a convex combination of K reference image GMMs, and then to describe the image as the K-dimensional vector of mixture weights. The computed weights encode a similarity that favors local matches (i.e. matches of individual Gaussians) and is therefore fundamentally different from the KL or PPK. Although the computation of the mixture weights is a convex optimization problem, its direct optimization is difficult. We propose two approximate optimization algorithms: the first one based on traditional sampling methods, the second one based on a variational bound approximation of the true objective function. We apply this novel representation to the image categorization problem and compare its performance to traditional kernel-based methods. We demonstrate on the PASCAL VOC 2007 dataset a consistent increase in classification accuracy.","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":"128384560","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.2009.5206539
Andrew Mastin, J. Kepner, John W. Fisher III
Fusion of 3D laser radar (LIDAR) imagery and aerial optical imagery is an efficient method for constructing 3D virtual reality models. One difficult aspect of creating such models is registering the optical image with the LIDAR point cloud, which is characterized as a camera pose estimation problem. We propose a novel application of mutual information registration methods, which exploits the statistical dependency in urban scenes of optical appearance with measured LIDAR elevation. We utilize the well known downhill simplex optimization to infer camera pose parameters. We discuss three methods for measuring mutual information between LIDAR imagery and optical imagery. Utilization of OpenGL and graphics hardware in the optimization process yields registration times dramatically lower than previous methods. Using an initial registration comparable to GPS/INS accuracy, we demonstrate the utility of our algorithm with a collection of urban images and present 3D models created with the fused imagery.
{"title":"Automatic registration of LIDAR and optical images of urban scenes","authors":"Andrew Mastin, J. Kepner, John W. Fisher III","doi":"10.1109/CVPR.2009.5206539","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206539","url":null,"abstract":"Fusion of 3D laser radar (LIDAR) imagery and aerial optical imagery is an efficient method for constructing 3D virtual reality models. One difficult aspect of creating such models is registering the optical image with the LIDAR point cloud, which is characterized as a camera pose estimation problem. We propose a novel application of mutual information registration methods, which exploits the statistical dependency in urban scenes of optical appearance with measured LIDAR elevation. We utilize the well known downhill simplex optimization to infer camera pose parameters. We discuss three methods for measuring mutual information between LIDAR imagery and optical imagery. Utilization of OpenGL and graphics hardware in the optimization process yields registration times dramatically lower than previous methods. Using an initial registration comparable to GPS/INS accuracy, we demonstrate the utility of our algorithm with a collection of urban images and present 3D models created with the fused imagery.","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":"124621624","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}