Pub Date : 2009-06-20DOI: 10.1109/CVPRW.2009.5204089
M. W. Koch, C. Giron, Hung D. Nguyen
We have developed algorithms for a virtual presence and extended defense (VPED) system that automatically learns the detection map of a deployed sensor field without a-priori knowledge of the local terrain. The VPED system is a network of sensor pods, with each pod containing acoustic and seismic sensors. Each pod has a limited detection range, but a network of pods can form a virtual perimeter. The site's geography and soil conditions can affect the detection performance of the pods. Thus a network in the field may not have the same performance as a network designed in the lab. To solve this problem we automatically estimate a network's detection performance as it is being constructed. We demonstrate results using simulated and real data.
{"title":"A rapidly deployable virtual presence extended defense system","authors":"M. W. Koch, C. Giron, Hung D. Nguyen","doi":"10.1109/CVPRW.2009.5204089","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204089","url":null,"abstract":"We have developed algorithms for a virtual presence and extended defense (VPED) system that automatically learns the detection map of a deployed sensor field without a-priori knowledge of the local terrain. The VPED system is a network of sensor pods, with each pod containing acoustic and seismic sensors. Each pod has a limited detection range, but a network of pods can form a virtual perimeter. The site's geography and soil conditions can affect the detection performance of the pods. Thus a network in the field may not have the same performance as a network designed in the lab. To solve this problem we automatically estimate a network's detection performance as it is being constructed. We demonstrate results using simulated and real data.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"34 7 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":"125720149","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.2009.5204042
Naixiang Lian, C. Davatzikos
The field of computational anatomy has developed rigorous frameworks for analyzing anatomical shape, based on diffeomorphic transformations of a template. However, differences in algorithms used for template warping, in regularization parameters, and in the template itself, lead to different representations of the same anatomy. Variations of these parameters are considered as confounding factors as they give rise to non-unique representation. Recently, extensions of the conventional computational anatomy framework to account for such confounding variations have shown that learning the equivalence class derived from the multitude of representations can lead to improved and more stable morphological descriptors. Herein, we follow that approach, estimating the morphological appearance manifold obtained by varying parameters of the template warping procedure. Our approach parallels work in the computer vision field, in which variations lighting, pose and other parameters leads to image appearancemanifolds representing the exact same figure in different ways. The proposed framework is then used for groupwise registration and statistical analysis of biomedical images, by employing a minimum variance criterion on selected complete morphological descriptor to perform manifold-constrained optimization, i.e. to traverse each individual's morphological appearance manifold until group variance is minimal. Effectively, this process removes the aforementioned confounding effects and potentially leads to morphological representations reflecting purely biological variations, instead of variations introduced by modeling assumptions and parameter settings. The nonlinearity of a morphological appearancemanifold is treated via local approximations of the manifold via PCA.
{"title":"Groupwise morphometric analysis based on morphological appearance manifold","authors":"Naixiang Lian, C. Davatzikos","doi":"10.1109/CVPRW.2009.5204042","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204042","url":null,"abstract":"The field of computational anatomy has developed rigorous frameworks for analyzing anatomical shape, based on diffeomorphic transformations of a template. However, differences in algorithms used for template warping, in regularization parameters, and in the template itself, lead to different representations of the same anatomy. Variations of these parameters are considered as confounding factors as they give rise to non-unique representation. Recently, extensions of the conventional computational anatomy framework to account for such confounding variations have shown that learning the equivalence class derived from the multitude of representations can lead to improved and more stable morphological descriptors. Herein, we follow that approach, estimating the morphological appearance manifold obtained by varying parameters of the template warping procedure. Our approach parallels work in the computer vision field, in which variations lighting, pose and other parameters leads to image appearancemanifolds representing the exact same figure in different ways. The proposed framework is then used for groupwise registration and statistical analysis of biomedical images, by employing a minimum variance criterion on selected complete morphological descriptor to perform manifold-constrained optimization, i.e. to traverse each individual's morphological appearance manifold until group variance is minimal. Effectively, this process removes the aforementioned confounding effects and potentially leads to morphological representations reflecting purely biological variations, instead of variations introduced by modeling assumptions and parameter settings. The nonlinearity of a morphological appearancemanifold is treated via local approximations of the manifold via PCA.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"126 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":"128046984","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.2009.5204260
J. Cohn
Significant efforts have been made in the analysis and understanding of naturally occurring behavior. Active Appearance Models (AAM) are an especially exciting approach to this task for facial behavior. They may be used both to measure naturally occurring behavior and to synthesize photo-realistic real-time avatars with which to test hypotheses made possible by those measurements. We have used both of these capabilities, analysis and synthesis, to investigate the influence of depression on face-to-face interaction. With AAMs we have investigated large datasets of clinical interviews and successfully modeled and perturbed communicative behavior in a video conference paradigm to test causal hypotheses. These advances have lead to new understanding of the social functions of depression and dampened affect in dyadic interaction. Key challenges remain. These include automated detection and synthesis of subtle facial actions; hybrid methods that optimally integrate automated and manual processing; computational modeling of subjective states from multimodal input; and dynamic models of social and affective behavior.
{"title":"Use of Active Appearance Models for analysis and synthesis of naturally occurring behavior","authors":"J. Cohn","doi":"10.1109/CVPRW.2009.5204260","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204260","url":null,"abstract":"Significant efforts have been made in the analysis and understanding of naturally occurring behavior. Active Appearance Models (AAM) are an especially exciting approach to this task for facial behavior. They may be used both to measure naturally occurring behavior and to synthesize photo-realistic real-time avatars with which to test hypotheses made possible by those measurements. We have used both of these capabilities, analysis and synthesis, to investigate the influence of depression on face-to-face interaction. With AAMs we have investigated large datasets of clinical interviews and successfully modeled and perturbed communicative behavior in a video conference paradigm to test causal hypotheses. These advances have lead to new understanding of the social functions of depression and dampened affect in dyadic interaction. Key challenges remain. These include automated detection and synthesis of subtle facial actions; hybrid methods that optimally integrate automated and manual processing; computational modeling of subjective states from multimodal input; and dynamic models of social and affective behavior.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"17 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":"120888014","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.2009.5204317
Jamil Draréni, S. Roy, P. Sturm
In this paper we address the problem of geometric calibration of video projectors. Like in most previous methods we also use a camera that observes the projection on a planar surface. Contrary to those previous methods, we neither require the camera to be calibrated nor the presence of a calibration grid or other metric information about the scene. We thus speak of geometric auto-calibration of projectors (GAP). The fact that camera calibration is not needed increases the usability of the method and at the same time eliminates one potential source of inaccuracy, since errors in the camera calibration would otherwise inevitably propagate through to the projector calibration. Our method enjoys a good stability and gives good results when compared against existing methods as depicted by our experiments.
{"title":"Geometric video projector auto-calibration","authors":"Jamil Draréni, S. Roy, P. Sturm","doi":"10.1109/CVPRW.2009.5204317","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204317","url":null,"abstract":"In this paper we address the problem of geometric calibration of video projectors. Like in most previous methods we also use a camera that observes the projection on a planar surface. Contrary to those previous methods, we neither require the camera to be calibrated nor the presence of a calibration grid or other metric information about the scene. We thus speak of geometric auto-calibration of projectors (GAP). The fact that camera calibration is not needed increases the usability of the method and at the same time eliminates one potential source of inaccuracy, since errors in the camera calibration would otherwise inevitably propagate through to the projector calibration. Our method enjoys a good stability and gives good results when compared against existing methods as depicted by our experiments.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"34 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":"123356447","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}
We often come across photographs with content whose identity we can no longer recall. For instance, we may have a picture from a football game we went to, but do not remember the name of the team in the photograph. A natural instinct may be to query an image search engine with related general terms, such as `football' or `football teams' in this case. This would lead to many irrelevant retrievals, and the user would have to manually examine several pages of retrieval results before he can hope to find other images containing the same team players and look at the text associated with these images to identify the team. With the growing popularity of global image matching techniques, one may consider matching the query image to other images on the Web. However, this does not allow for ways to focus on the object-of-interest while matching, and may cause the background to overwhelm the matching results, especially when the object-of-interest is small and can occur in varying backgrounds, again, leading to irrelevant retrievals. We propose Cutout-Search, where a user employs an interactive segmentation tool to cut out the object-of-interest from the image, and use this Cutout-Query to retrieve images. As our experiments show, this leads to retrieval of more relevant images when compared to global image matching leading to more specific identification of the object-of-interest in the query image.
{"title":"Cutout-search: Putting a name to the picture","authors":"Dhruv Batra, Adarsh Kowdle, Devi Parikh, Tsuhan Chen","doi":"10.1109/CVPRW.2009.5204195","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204195","url":null,"abstract":"We often come across photographs with content whose identity we can no longer recall. For instance, we may have a picture from a football game we went to, but do not remember the name of the team in the photograph. A natural instinct may be to query an image search engine with related general terms, such as `football' or `football teams' in this case. This would lead to many irrelevant retrievals, and the user would have to manually examine several pages of retrieval results before he can hope to find other images containing the same team players and look at the text associated with these images to identify the team. With the growing popularity of global image matching techniques, one may consider matching the query image to other images on the Web. However, this does not allow for ways to focus on the object-of-interest while matching, and may cause the background to overwhelm the matching results, especially when the object-of-interest is small and can occur in varying backgrounds, again, leading to irrelevant retrievals. We propose Cutout-Search, where a user employs an interactive segmentation tool to cut out the object-of-interest from the image, and use this Cutout-Query to retrieve images. As our experiments show, this leads to retrieval of more relevant images when compared to global image matching leading to more specific identification of the object-of-interest in the query image.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"230 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":"123364018","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.2009.5204306
Vivek Kanhangad, Ajay Kumar, David Zhang
Traditional hand geometry based personal verification systems offer limited performance and therefore suitable only for small scale applications. This paper investigates a new approach to achieve performance improvement for hand geometry systems by simultaneously acquiring three dimensional features from the presented hands. The proposed system utilizes a laser based 3D digitizer to acquire registered intensity and range images of the presented hands in a completely contact-free manner, without using any hand position restricting mechanism. Two new representations that characterize the local features on the finger surface are extracted from the acquired range images and are matched using the proposed matching metrics. The proposed approach is evaluated on a database of 177 users, with 10 hand images for each user acquired in two sessions. Our experimental results suggest that the proposed 3D hand geometry features have significant discriminatory information to reliably authenticate individuals. Our experimental results also demonstrate that the combination of 3D hand geometry features with 2D geometry features can be employed to significantly improve the performance from 2D hand geometry features alone.
{"title":"Combining 2D and 3D hand geometry features for biometric verification","authors":"Vivek Kanhangad, Ajay Kumar, David Zhang","doi":"10.1109/CVPRW.2009.5204306","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204306","url":null,"abstract":"Traditional hand geometry based personal verification systems offer limited performance and therefore suitable only for small scale applications. This paper investigates a new approach to achieve performance improvement for hand geometry systems by simultaneously acquiring three dimensional features from the presented hands. The proposed system utilizes a laser based 3D digitizer to acquire registered intensity and range images of the presented hands in a completely contact-free manner, without using any hand position restricting mechanism. Two new representations that characterize the local features on the finger surface are extracted from the acquired range images and are matched using the proposed matching metrics. The proposed approach is evaluated on a database of 177 users, with 10 hand images for each user acquired in two sessions. Our experimental results suggest that the proposed 3D hand geometry features have significant discriminatory information to reliably authenticate individuals. Our experimental results also demonstrate that the combination of 3D hand geometry features with 2D geometry features can be employed to significantly improve the performance from 2D hand geometry features alone.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"67 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":"124015391","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.2009.5204358
Li Sun, Ulrich Klank, M. Beetz
This paper investigates the “inside-out” recognition of everyday manipulation tasks using a gaze-directed camera, which is a camera that actively directs at the visual attention focus of the person wearing the camera. We present EYEWATCHME, an integrated vision and state estimation system that at the same time tracks the positions and the poses of the acting hands, the pose that the manipulated object, and the pose of the observing camera. Taken together, EYEWATCHME provides comprehensive data for learning predictive models of vision-guided manipulation that include the objects people are attending, the interaction of attention and reaching/grasping, and the segmentation of reaching and grasping using visual attention as evidence. Key technical contributions of this paper include an ego view hand tracking system that estimates 27 DOF hand poses. The hand tracking system is capable of detecting hands and estimating their poses despite substantial self-occlusion caused by the hand and occlusions caused by the manipulated object. EYEWATCHME can also cope with blurred images that are caused by rapid eye movements. The second key contribution is the of the integrated activity recognition system that simultaneously tracks the attention of the person, the hand poses, and the poses of the manipulated objects in terms of a global scene coordinates. We demonstrate the operation of EYEWATCHME in the context of kitchen tasks including filling a cup with water.
{"title":"EYEWATCHME—3D Hand and object tracking for inside out activity analysis","authors":"Li Sun, Ulrich Klank, M. Beetz","doi":"10.1109/CVPRW.2009.5204358","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204358","url":null,"abstract":"This paper investigates the “inside-out” recognition of everyday manipulation tasks using a gaze-directed camera, which is a camera that actively directs at the visual attention focus of the person wearing the camera. We present EYEWATCHME, an integrated vision and state estimation system that at the same time tracks the positions and the poses of the acting hands, the pose that the manipulated object, and the pose of the observing camera. Taken together, EYEWATCHME provides comprehensive data for learning predictive models of vision-guided manipulation that include the objects people are attending, the interaction of attention and reaching/grasping, and the segmentation of reaching and grasping using visual attention as evidence. Key technical contributions of this paper include an ego view hand tracking system that estimates 27 DOF hand poses. The hand tracking system is capable of detecting hands and estimating their poses despite substantial self-occlusion caused by the hand and occlusions caused by the manipulated object. EYEWATCHME can also cope with blurred images that are caused by rapid eye movements. The second key contribution is the of the integrated activity recognition system that simultaneously tracks the attention of the person, the hand poses, and the poses of the manipulated objects in terms of a global scene coordinates. We demonstrate the operation of EYEWATCHME in the context of kitchen tasks including filling a cup with water.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"994 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":"123096857","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.2009.5204313
M. Ebrahimi, W. Mayol-Cuevas
There has been significant research into the development of visual feature detectors and descriptors that are robust to a number of image deformations. Some of these methods have emphasized the need to improve on computational speed and compact representations so that they can enable a range of real-time applications with reduced computational requirements. In this paper we present modified detectors and descriptors based on the recently introduced CenSurE [1], and show experimental results that aim to highlight the computational savings that can be made with limited reduction in performance. The developed methods are based on exploiting the concept of sparse sampling which may be of interest to a range of other existing approaches.
{"title":"SUSurE: Speeded Up Surround Extrema feature detector and descriptor for realtime applications","authors":"M. Ebrahimi, W. Mayol-Cuevas","doi":"10.1109/CVPRW.2009.5204313","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204313","url":null,"abstract":"There has been significant research into the development of visual feature detectors and descriptors that are robust to a number of image deformations. Some of these methods have emphasized the need to improve on computational speed and compact representations so that they can enable a range of real-time applications with reduced computational requirements. In this paper we present modified detectors and descriptors based on the recently introduced CenSurE [1], and show experimental results that aim to highlight the computational savings that can be made with limited reduction in performance. The developed methods are based on exploiting the concept of sparse sampling which may be of interest to a range of other existing approaches.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"72 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":"127344808","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.2009.5204261
Caifeng Shan, Wei Chen
In this paper, we investigate a recently proposed efficient subspace learning method, Spectral Regression Discriminant Analysis (SRDA), and its kernel version SRKDA for head pose estimation. One important unsolved issue of SRDA is how to automatically determine an appropriate regularization parameter. The parameter, which was empirically set in the existing work, has great impact on its performance. By formulating it as a constrained optimization problem, we present a method to estimate the optimal regularization parameter in SRDA and SRKDA. Our experiments on two databases illustrate that SRDA, especially SRKDA, is promising for head pose estimation. Moreover, our approach for estimating the regularization parameter is shown to be effective in head pose estimation and face recognition experiments.
{"title":"Head pose estimation using Spectral Regression Discriminant Analysis","authors":"Caifeng Shan, Wei Chen","doi":"10.1109/CVPRW.2009.5204261","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204261","url":null,"abstract":"In this paper, we investigate a recently proposed efficient subspace learning method, Spectral Regression Discriminant Analysis (SRDA), and its kernel version SRKDA for head pose estimation. One important unsolved issue of SRDA is how to automatically determine an appropriate regularization parameter. The parameter, which was empirically set in the existing work, has great impact on its performance. By formulating it as a constrained optimization problem, we present a method to estimate the optimal regularization parameter in SRDA and SRKDA. Our experiments on two databases illustrate that SRDA, especially SRKDA, is promising for head pose estimation. Moreover, our approach for estimating the regularization parameter is shown to be effective in head pose estimation and face recognition experiments.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"16 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":"124359175","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.2009.5204356
A. Flint, I. Reid, D. W. Murray
We present a new model for scene context based on the distribution of textons within images. Our approach provides continuous, consistent scene gist throughout a video sequence and is suitable for applications in which the camera regularly views uninformative parts of the scene. We show that our model outperforms the state-of-the-art for place recognition. We further show how to deduce the camera orientation from our scene gist and finally show how our system can be applied to active object search.
{"title":"Learning texton models for real-time scene context","authors":"A. Flint, I. Reid, D. W. Murray","doi":"10.1109/CVPRW.2009.5204356","DOIUrl":"https://doi.org/10.1109/CVPRW.2009.5204356","url":null,"abstract":"We present a new model for scene context based on the distribution of textons within images. Our approach provides continuous, consistent scene gist throughout a video sequence and is suitable for applications in which the camera regularly views uninformative parts of the scene. We show that our model outperforms the state-of-the-art for place recognition. We further show how to deduce the camera orientation from our scene gist and finally show how our system can be applied to active object search.","PeriodicalId":431981,"journal":{"name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","volume":"54 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":"115883505","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：