Pub Date : 2009-06-20DOI: 10.1109/CVPRW.2009.5204202
S. Gupta, R. Mooney
Recognizing activities in real-world videos is a difficult problem exacerbated by background clutter, changes in camera angle & zoom, rapid camera movements etc. Large corpora of labeled videos can be used to train automated activity recognition systems, but this requires expensive human labor and time. This paper explores how closed captions that naturally accompany many videos can act as weak supervision that allows automatically collecting `labeled' data for activity recognition. We show that such an approach can improve activity retrieval in soccer videos. Our system requires no manual labeling of video clips and needs minimal human supervision. We also present a novel caption classifier that uses additional linguistic information to determine whether a specific comment refers to an on-going activity. We demonstrate that combining linguistic analysis and automatically trained activity recognizers can significantly improve the precision of video retrieval.
{"title":"Using closed captions to train activity recognizers that improve video retrieval","authors":"S. Gupta, R. Mooney","doi":"10.1109/CVPRW.2009.5204202","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204202","url":null,"abstract":"Recognizing activities in real-world videos is a difficult problem exacerbated by background clutter, changes in camera angle & zoom, rapid camera movements etc. Large corpora of labeled videos can be used to train automated activity recognition systems, but this requires expensive human labor and time. This paper explores how closed captions that naturally accompany many videos can act as weak supervision that allows automatically collecting `labeled' data for activity recognition. We show that such an approach can improve activity retrieval in soccer videos. Our system requires no manual labeling of video clips and needs minimal human supervision. We also present a novel caption classifier that uses additional linguistic information to determine whether a specific comment refers to an on-going activity. We demonstrate that combining linguistic analysis and automatically trained activity recognizers can significantly improve the precision of video retrieval.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134622836","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/CVPRW.2009.5204262
A. Oikonomopoulos, I. Patras, M. Pantic
In this paper we address the problem of localisation and recognition of human activities in unsegmented image sequences. The main contribution of the proposed method is the use of an implicit representation of the spatiotemporal shape of the activity which relies on the spatiotemporal localization of characteristic, sparse, `visual words' and `visual verbs'. Evidence for the spatiotemporal localization of the activity are accumulated in a probabilistic spatiotemporal voting scheme. The local nature of our voting framework allows us to recover multiple activities that take place in the same scene, as well as activities in the presence of clutter and occlusions. We construct class-specific codebooks using the descriptors in the training set, where we take the spatial co-occurrences of pairs of codewords into account. The positions of the codeword pairs with respect to the object centre, as well as the frame in the training set in which they occur are subsequently stored in order to create a spatiotemporal model of codeword co-occurrences. During the testing phase, we use mean shift mode estimation in order to spatially segment the subject that performs the activities in every frame, and the Radon transform in order to extract the most probable hypotheses concerning the temporal segmentation of the activities within the continuous stream.
{"title":"An implicit spatiotemporal shape model for human activity localization and recognition","authors":"A. Oikonomopoulos, I. Patras, M. Pantic","doi":"10.1109/CVPRW.2009.5204262","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204262","url":null,"abstract":"In this paper we address the problem of localisation and recognition of human activities in unsegmented image sequences. The main contribution of the proposed method is the use of an implicit representation of the spatiotemporal shape of the activity which relies on the spatiotemporal localization of characteristic, sparse, `visual words' and `visual verbs'. Evidence for the spatiotemporal localization of the activity are accumulated in a probabilistic spatiotemporal voting scheme. The local nature of our voting framework allows us to recover multiple activities that take place in the same scene, as well as activities in the presence of clutter and occlusions. We construct class-specific codebooks using the descriptors in the training set, where we take the spatial co-occurrences of pairs of codewords into account. The positions of the codeword pairs with respect to the object centre, as well as the frame in the training set in which they occur are subsequently stored in order to create a spatiotemporal model of codeword co-occurrences. During the testing phase, we use mean shift mode estimation in order to spatially segment the subject that performs the activities in every frame, and the Radon transform in order to extract the most probable hypotheses concerning the temporal segmentation of the activities within the continuous stream.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133820322","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/CVPRW.2009.5204314
S. Taylor, E. Rosten, T. Drummond
In this paper we present a robust feature matching scheme in which features can be matched in 2.3µs. For a typical task involving 150 features per image, this results in a processing time of 500µs for feature extraction and matching. In order to achieve very fast matching we use simple features based on histograms of pixel intensities and an indexing scheme based on their joint distribution. The features are stored with a novel bit mask representation which requires only 44 bytes of memory per feature and allows computation of a dissimilarity score in 20ns. A training phase gives the patch-based features invariance to small viewpoint variations. Larger viewpoint variations are handled by training entirely independent sets of features from different viewpoints. A complete system is presented where a database of around 13,000 features is used to robustly localise a single planar target in just over a millisecond, including all steps from feature detection to model fitting. The resulting system shows comparable robustness to SIFT [8] and Ferns [14] while using a tiny fraction of the processing time, and in the latter case a fraction of the memory as well.
{"title":"Robust feature matching in 2.3µs","authors":"S. Taylor, E. Rosten, T. Drummond","doi":"10.1109/CVPRW.2009.5204314","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204314","url":null,"abstract":"In this paper we present a robust feature matching scheme in which features can be matched in 2.3µs. For a typical task involving 150 features per image, this results in a processing time of 500µs for feature extraction and matching. In order to achieve very fast matching we use simple features based on histograms of pixel intensities and an indexing scheme based on their joint distribution. The features are stored with a novel bit mask representation which requires only 44 bytes of memory per feature and allows computation of a dissimilarity score in 20ns. A training phase gives the patch-based features invariance to small viewpoint variations. Larger viewpoint variations are handled by training entirely independent sets of features from different viewpoints. A complete system is presented where a database of around 13,000 features is used to robustly localise a single planar target in just over a millisecond, including all steps from feature detection to model fitting. The resulting system shows comparable robustness to SIFT [8] and Ferns [14] while using a tiny fraction of the processing time, and in the latter case a fraction of the memory as well.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125116364","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/CVPRW.2009.5204332
A. Leonardis
Summary form only given. Visual categorization, recognition, and detection of objects has been an area of active research in the vision community for decades. Ultimately, the goal is to recognize and detect a large number of object classes in images within an acceptable time frame. This problem entangles three highly interconnected issues: the internal object representation which should expand sublinearly with the number of classes, means to learn the representation from a set of images, and an effective inference algorithm that matches the object representation against the representation produced from the scene. In the main part of the talk I will present our framework for learning a hierarchical compositional representation of multiple object classes. Learning is unsupervised, statistical, and is performed bottom-up. The approach takes simple contour fragments and learns their frequent spatial configurations which recursively combine into increasingly more complex and class-specific contour compositions.
{"title":"Learning a hierarchical compositional representation of multiple object classes","authors":"A. Leonardis","doi":"10.1109/CVPRW.2009.5204332","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204332","url":null,"abstract":"Summary form only given. Visual categorization, recognition, and detection of objects has been an area of active research in the vision community for decades. Ultimately, the goal is to recognize and detect a large number of object classes in images within an acceptable time frame. This problem entangles three highly interconnected issues: the internal object representation which should expand sublinearly with the number of classes, means to learn the representation from a set of images, and an effective inference algorithm that matches the object representation against the representation produced from the scene. In the main part of the talk I will present our framework for learning a hierarchical compositional representation of multiple object classes. Learning is unsupervised, statistical, and is performed bottom-up. The approach takes simple contour fragments and learns their frequent spatial configurations which recursively combine into increasingly more complex and class-specific contour compositions.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134256524","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/CVPRW.2009.5204177
M. Aly, P. Welinder, Mario E. Munich, P. Perona
Gathering large collections of images is quite easy nowadays with the advent of image sharing Web sites, such as flickr.com. However, such collections inevitably contain duplicates and highly similar images, what we refer to as image families. Automatic discovery and cataloguing of such similar images in large collections is important for many applications, e.g. image search, image collection visualization, and research purposes among others. In this work, we investigate this problem by thoroughly comparing two broad approaches for measuring image similarity: global vs. local features. We assess their performance as the image collection scales up to over 11,000 images with over 6,300 families. We present our results on three datasets with different statistics, including two new challenging datasets. Moreover, we present a new algorithm to automatically determine the number of families in the collection with promising results.
{"title":"Towards automated large scale discovery of image families","authors":"M. Aly, P. Welinder, Mario E. Munich, P. Perona","doi":"10.1109/CVPRW.2009.5204177","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204177","url":null,"abstract":"Gathering large collections of images is quite easy nowadays with the advent of image sharing Web sites, such as flickr.com. However, such collections inevitably contain duplicates and highly similar images, what we refer to as image families. Automatic discovery and cataloguing of such similar images in large collections is important for many applications, e.g. image search, image collection visualization, and research purposes among others. In this work, we investigate this problem by thoroughly comparing two broad approaches for measuring image similarity: global vs. local features. We assess their performance as the image collection scales up to over 11,000 images with over 6,300 families. We present our results on three datasets with different statistics, including two new challenging datasets. Moreover, we present a new algorithm to automatically determine the number of families in the collection with promising results.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132552108","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/CVPRW.2009.5204085
K. Jüngling, Michael Arens
One of the main challenges in computer vision is the automatic detection of specific object classes in images. Recent advances of object detection performance in the visible spectrum encourage the application of these approaches to data beyond the visible spectrum. In this paper, we show the applicability of a well known, local-feature based object detector for the case of people detection in thermal data. We adapt the detector to the special conditions of infrared data and show the specifics relevant for feature based object detection. For that, we employ the SURF feature detector and descriptor that is well suited for infrared data. We evaluate the performance of our adapted object detector in the task of person detection in different real-world scenarios where people occur at multiple scales. Finally, we show how this local-feature based detector can be used to recognize specific object parts, i.e., body parts of detected people.
{"title":"Feature based person detection beyond the visible spectrum","authors":"K. Jüngling, Michael Arens","doi":"10.1109/CVPRW.2009.5204085","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204085","url":null,"abstract":"One of the main challenges in computer vision is the automatic detection of specific object classes in images. Recent advances of object detection performance in the visible spectrum encourage the application of these approaches to data beyond the visible spectrum. In this paper, we show the applicability of a well known, local-feature based object detector for the case of people detection in thermal data. We adapt the detector to the special conditions of infrared data and show the specifics relevant for feature based object detection. For that, we employ the SURF feature detector and descriptor that is well suited for infrared data. We evaluate the performance of our adapted object detector in the task of person detection in different real-world scenarios where people occur at multiple scales. Finally, we show how this local-feature based detector can be used to recognize specific object parts, i.e., body parts of detected people.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131565552","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/CVPRW.2009.5204050
Yuanjie Zheng, C. Kambhamettu, T. Bauer, K. Steiner
We propose a new tumor growth measure for pulmonary nodules in CT images, which can account for the tumor deformation caused by the inspiration level's difference. It is accomplished with a new nonrigid lung registration process, which can handle the tumor expanding/shrinking problem occurring in many conventional nonrigid registration methods. The accurate nonrigid registration is performed by weighting the matching cost of each voxel, based on the result of a new nodule detection approach and a powerful nodule segmentation algorithm. Comprehensive experiments show the high accuracy of our algorithms and the promising results of our new tumor growth measure.
{"title":"Accurate estimation of pulmonary nodule's growth rate in CT images with nonrigid registration and precise nodule detection and segmentation","authors":"Yuanjie Zheng, C. Kambhamettu, T. Bauer, K. Steiner","doi":"10.1109/CVPRW.2009.5204050","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204050","url":null,"abstract":"We propose a new tumor growth measure for pulmonary nodules in CT images, which can account for the tumor deformation caused by the inspiration level's difference. It is accomplished with a new nonrigid lung registration process, which can handle the tumor expanding/shrinking problem occurring in many conventional nonrigid registration methods. The accurate nonrigid registration is performed by weighting the matching cost of each voxel, based on the result of a new nodule detection approach and a powerful nodule segmentation algorithm. Comprehensive experiments show the high accuracy of our algorithms and the promising results of our new tumor growth measure.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132241863","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/CVPRW.2009.5204297
Juwei Lu, K. Plataniotis
The paper presents a study on color to gray image conversion from a novel point of view: face detection. To the best knowledge of the authors, research in such a specific topic has not been conducted before. Our work reveals that the standard NTSC conversion is not optimal for face detection tasks, although it may be the best for use to display pictures on monochrome televisions. It is further found experimentally with two AdaBoost-based face detection systems that the detect rates may vary up to 10% by simply changing the parameters of the RGB to Gray conversion. On the other hand, the change has little influence on the false positive rates. Compared to the standard NTSC conversion, the detect rate with the best found parameter setting is 2.85% and 3.58% higher for the two evaluated face detection systems. Promisingly, the work suggests a new solution to the color to gray conversion. It could be extremely easy to be incorporated into most existing face detection systems for accuracy improvement without introduction of any extra cost in computational complexity.
{"title":"On conversion from color to gray-scale images for face detection","authors":"Juwei Lu, K. Plataniotis","doi":"10.1109/CVPRW.2009.5204297","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204297","url":null,"abstract":"The paper presents a study on color to gray image conversion from a novel point of view: face detection. To the best knowledge of the authors, research in such a specific topic has not been conducted before. Our work reveals that the standard NTSC conversion is not optimal for face detection tasks, although it may be the best for use to display pictures on monochrome televisions. It is further found experimentally with two AdaBoost-based face detection systems that the detect rates may vary up to 10% by simply changing the parameters of the RGB to Gray conversion. On the other hand, the change has little influence on the false positive rates. Compared to the standard NTSC conversion, the detect rate with the best found parameter setting is 2.85% and 3.58% higher for the two evaluated face detection systems. Promisingly, the work suggests a new solution to the color to gray conversion. It could be extremely easy to be incorporated into most existing face detection systems for accuracy improvement without introduction of any extra cost in computational complexity.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132508637","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/CVPRW.2009.5204337
N. Ahuja
We consider one of the most basic questions in computer vision, that of finding a low-level image representation that could be used to seed diverse, subsequent computations of image understanding. Can we define a relatively general purpose image representation which would serve as the syntax for diverse needs of image understanding? What makes good image syntax? How do we evaluate it? We pose a series of such questions and evolve a set of answers to them, which in turn help evolve an image representation. For concreteness, we first perform this exercise in the specific context of the following problem.
{"title":"A syntax for image understanding","authors":"N. Ahuja","doi":"10.1109/CVPRW.2009.5204337","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204337","url":null,"abstract":"We consider one of the most basic questions in computer vision, that of finding a low-level image representation that could be used to seed diverse, subsequent computations of image understanding. Can we define a relatively general purpose image representation which would serve as the syntax for diverse needs of image understanding? What makes good image syntax? How do we evaluate it? We pose a series of such questions and evolve a set of answers to them, which in turn help evolve an image representation. For concreteness, we first perform this exercise in the specific context of the following problem.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"148 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133419770","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/CVPRW.2009.5204318
Furukawa Ryo, K. Inose, Hiroshi Kawasaki
Range scanners using projector-camera systems have been studied actively in recent years as methods for measuring 3D shapes accurately and cost-effectively. To acquire an entire 3D shape of an object with such systems, the shape of the object should be captured from multiple directions and the set of captured shapes should be aligned using algorithms such as ICPs. Then, the aligned shapes are integrated into a single 3D shape model. However, the captured shapes are often distorted due to errors of intrinsic or extrinsic parameters of the camera and the projector. Because of these distortions, gaps between overlapped surfaces remain even after aligning the 3D shapes. In this paper, we propose a new method to capture an entire shape with high precision using an active stereo range scanner which consists of a projector and a camera with fixed relative positions. In the proposed method, minimization of calibration errors of the projector-camera pair and registration errors between 3D shapes from different viewpoints are simultaneously achieved. The proposed method can be considered as a variation of bundle adjustment techniques adapted to projector-camera systems. Since acquisition of correspondences between different views is not easy for projector-camera systems, a solution for the problem is also presented.
{"title":"Multi-view reconstruction for projector camera systems based on bundle adjustment","authors":"Furukawa Ryo, K. Inose, Hiroshi Kawasaki","doi":"10.1109/CVPRW.2009.5204318","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204318","url":null,"abstract":"Range scanners using projector-camera systems have been studied actively in recent years as methods for measuring 3D shapes accurately and cost-effectively. To acquire an entire 3D shape of an object with such systems, the shape of the object should be captured from multiple directions and the set of captured shapes should be aligned using algorithms such as ICPs. Then, the aligned shapes are integrated into a single 3D shape model. However, the captured shapes are often distorted due to errors of intrinsic or extrinsic parameters of the camera and the projector. Because of these distortions, gaps between overlapped surfaces remain even after aligning the 3D shapes. In this paper, we propose a new method to capture an entire shape with high precision using an active stereo range scanner which consists of a projector and a camera with fixed relative positions. In the proposed method, minimization of calibration errors of the projector-camera pair and registration errors between 3D shapes from different viewpoints are simultaneously achieved. The proposed method can be considered as a variation of bundle adjustment techniques adapted to projector-camera systems. Since acquisition of correspondences between different views is not easy for projector-camera systems, a solution for the problem is also presented.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132854845","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：