Pub Date : 2005-10-15DOI: 10.1109/VSPETS.2005.1570923
D. Thirde, M. Borg, V. Valentin, F. Fusier, J. Aguilera, J. Ferryman, F. Brémond, M. Thonnat, M. Kampel
This paper presents a visual surveillance system for the automatic scene interpretation of airport aprons. The system comprises two modules - scene tracking and scene understanding. The scene tracking module, comprising a bottom-up methodology, and the scene understanding module, comprising a video event representation and recognition scheme, have been demonstrated to be a valid approach for apron monitoring
{"title":"Visual Surveillance for Aircraft Activity Monitoring","authors":"D. Thirde, M. Borg, V. Valentin, F. Fusier, J. Aguilera, J. Ferryman, F. Brémond, M. Thonnat, M. Kampel","doi":"10.1109/VSPETS.2005.1570923","DOIUrl":"https://doi.org/10.1109/VSPETS.2005.1570923","url":null,"abstract":"This paper presents a visual surveillance system for the automatic scene interpretation of airport aprons. The system comprises two modules - scene tracking and scene understanding. The scene tracking module, comprising a bottom-up methodology, and the scene understanding module, comprising a video event representation and recognition scheme, have been demonstrated to be a valid approach for apron monitoring","PeriodicalId":435841,"journal":{"name":"2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115821315","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 : 2005-10-15DOI: 10.1109/VSPETS.2005.1570913
F. Qureshi, Demetri Terzopoulos
The goals of this paper are two-fold: (i) to present our initial efforts towards the realization of a fully autonomous sensor network of dynamic video cameras capable of providing perceptive coverage of a large public space, and (ii) to further the cause of exploiting visually and behaviorally realistic virtual environments in the development and testing of machine vision systems. In particular, our proposed sensor network employs techniques that enable a collection of active (pan-tilt-zoom) cameras to collaborate in performing various visual surveillance tasks, such as keeping one or more pedestrians within view, with minimal reliance on a human operator. The network features local and global autonomy and lacks any central controller, which entails robustness and scalability. Its functionality is the result of local decision-making capabilities at each camera node and communication between the nodes. We demonstrate our surveillance system in a virtual train station environment populated by autonomous, lifelike virtual pedestrians. Our readily reconfigurable virtual cameras generate synthetic video feeds that emulate those generated by real surveillance cameras monitoring public spaces. This type of research would be difficult in the real world given the costs of deploying and experimenting with an appropriately complex camera network in a large public space the size of a train station.
{"title":"Towards intelligent camera networks: a virtual vision approach","authors":"F. Qureshi, Demetri Terzopoulos","doi":"10.1109/VSPETS.2005.1570913","DOIUrl":"https://doi.org/10.1109/VSPETS.2005.1570913","url":null,"abstract":"The goals of this paper are two-fold: (i) to present our initial efforts towards the realization of a fully autonomous sensor network of dynamic video cameras capable of providing perceptive coverage of a large public space, and (ii) to further the cause of exploiting visually and behaviorally realistic virtual environments in the development and testing of machine vision systems. In particular, our proposed sensor network employs techniques that enable a collection of active (pan-tilt-zoom) cameras to collaborate in performing various visual surveillance tasks, such as keeping one or more pedestrians within view, with minimal reliance on a human operator. The network features local and global autonomy and lacks any central controller, which entails robustness and scalability. Its functionality is the result of local decision-making capabilities at each camera node and communication between the nodes. We demonstrate our surveillance system in a virtual train station environment populated by autonomous, lifelike virtual pedestrians. Our readily reconfigurable virtual cameras generate synthetic video feeds that emulate those generated by real surveillance cameras monitoring public spaces. This type of research would be difficult in the real world given the costs of deploying and experimenting with an appropriately complex camera network in a large public space the size of a train station.","PeriodicalId":435841,"journal":{"name":"2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122604104","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 : 2005-10-15DOI: 10.1109/VSPETS.2005.1570927
Dongjin Han, Matthew J. Leotta, D. Cooper, J. Mundy
A new approach is presented to vehicle-class recognition from a video clip. Two new concepts introduced are: probes consisting of local 3D curve-groups which when projected into video frames are features for recognizing vehicle classes in video clips; and Bayesian recognition based on class probability densities for groups of 3D distances between pairs of 3D probes. The most stable image features for vehicle class recognition appear to be image curves associate with 3D ridges on the vehicle surface. These ridges are mostly those occurring at metal/glass interfaces, two-surface intersections such as back and side, and self occluding contours such as wheel wells or vehicle-body apparent contours, i.e., silhouettes. There are other detectable surface curves, but most do not provide useful discriminatory features, and many of these are clutter, i.e., due to reflections from the somewhat shiny vehicle surface. Models are built and used for the considerable variability that exists in the features used. A Bayesian recognizer is then used for vehicle class recognition from a sequence of frames. The ultimate goal is a recognizer to deal with essentially all classes of civilian vehicles seen from arbitrary directions, at a broad range of distances and under the broad range of lighting ranging from sunny to cloudy. Experiments are run with a small set of classes to prove feasibility. This work uses estimated knowledge of the motion and position of the vehicle. We briefly indicate one way of inferring that information which uses ID projectivity invariance.
{"title":"Vehicle Class Recognition from Video-Based on 3D Curve Probes","authors":"Dongjin Han, Matthew J. Leotta, D. Cooper, J. Mundy","doi":"10.1109/VSPETS.2005.1570927","DOIUrl":"https://doi.org/10.1109/VSPETS.2005.1570927","url":null,"abstract":"A new approach is presented to vehicle-class recognition from a video clip. Two new concepts introduced are: probes consisting of local 3D curve-groups which when projected into video frames are features for recognizing vehicle classes in video clips; and Bayesian recognition based on class probability densities for groups of 3D distances between pairs of 3D probes. The most stable image features for vehicle class recognition appear to be image curves associate with 3D ridges on the vehicle surface. These ridges are mostly those occurring at metal/glass interfaces, two-surface intersections such as back and side, and self occluding contours such as wheel wells or vehicle-body apparent contours, i.e., silhouettes. There are other detectable surface curves, but most do not provide useful discriminatory features, and many of these are clutter, i.e., due to reflections from the somewhat shiny vehicle surface. Models are built and used for the considerable variability that exists in the features used. A Bayesian recognizer is then used for vehicle class recognition from a sequence of frames. The ultimate goal is a recognizer to deal with essentially all classes of civilian vehicles seen from arbitrary directions, at a broad range of distances and under the broad range of lighting ranging from sunny to cloudy. Experiments are run with a small set of classes to prove feasibility. This work uses estimated knowledge of the motion and position of the vehicle. We briefly indicate one way of inferring that information which uses ID projectivity invariance.","PeriodicalId":435841,"journal":{"name":"2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114465437","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 : 2005-10-15DOI: 10.1109/VSPETS.2005.1570910
Hanzi Wang, D. Suter
Initializing a background model requires robust statistical methods as the task should be robust against random occurrences of foreground objects, as well as against general image noise. The median has been employed for the problem of background initialization. However, the median has only a breakdown point of 50%. In this paper, we propose a new robust method which can tolerate more than 50% of noise and foreground pixels in the background initialization process. We compare our new method with five others and give quantitative evaluations on background initialization. Experiments show that the proposed method achieves very promising results in background initialization.
{"title":"Background initialization with a new robust statistical approach","authors":"Hanzi Wang, D. Suter","doi":"10.1109/VSPETS.2005.1570910","DOIUrl":"https://doi.org/10.1109/VSPETS.2005.1570910","url":null,"abstract":"Initializing a background model requires robust statistical methods as the task should be robust against random occurrences of foreground objects, as well as against general image noise. The median has been employed for the problem of background initialization. However, the median has only a breakdown point of 50%. In this paper, we propose a new robust method which can tolerate more than 50% of noise and foreground pixels in the background initialization process. We compare our new method with five others and give quantitative evaluations on background initialization. Experiments show that the proposed method achieves very promising results in background initialization.","PeriodicalId":435841,"journal":{"name":"2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126692031","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 : 2005-10-15DOI: 10.1109/VSPETS.2005.1570911
Weiqiang Wang, Datong Chen, Wen Gao, Jie Yang
Background models have been widely used for video surveillance and other applications. Methods for constructing background models and associated application algorithms are mainly studied in the spatial domain (pixel level). Many video sources, however, are in a compressed format before processing. In this paper, we propose an approach to construct background models directly from compressed video. The proposed approach utilizes the information from DCT coefficients at block level to construct accurate background models at pixel level. We implemented three representative algorithms of background models in the compressed domain, and theoretically explored their properties and the relationship with their counterparts in the spatial domain. We also present some general technical improvements to make them more capable for a wide range of applications. The proposed method can achieve the same accuracy as the methods that construct background models from the spatial domain with much lower computational cost (50% on average) and more compact storages.
{"title":"Modeling background from compressed video","authors":"Weiqiang Wang, Datong Chen, Wen Gao, Jie Yang","doi":"10.1109/VSPETS.2005.1570911","DOIUrl":"https://doi.org/10.1109/VSPETS.2005.1570911","url":null,"abstract":"Background models have been widely used for video surveillance and other applications. Methods for constructing background models and associated application algorithms are mainly studied in the spatial domain (pixel level). Many video sources, however, are in a compressed format before processing. In this paper, we propose an approach to construct background models directly from compressed video. The proposed approach utilizes the information from DCT coefficients at block level to construct accurate background models at pixel level. We implemented three representative algorithms of background models in the compressed domain, and theoretically explored their properties and the relationship with their counterparts in the spatial domain. We also present some general technical improvements to make them more capable for a wide range of applications. The proposed method can achieve the same accuracy as the methods that construct background models from the spatial domain with much lower computational cost (50% on average) and more compact storages.","PeriodicalId":435841,"journal":{"name":"2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance","volume":"82 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132325153","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 : 2005-10-15DOI: 10.1109/VSPETS.2005.1570924
Qi Zhao, Hai Tao
Color histogram based representations have been widely used for blob tracking. In this paper, a new color histogram based approach for object representation is proposed. By using a simplified version of color correlogram as object feature, spatial information is incorporated into object representation, which allows variations of rotation to be detected throughout the tracking therefore rotational objects can be more accurately tracked. The gradient decent method mean shift algorithm is adopted as the central computational module and further extended to a 3D domain to find the mostprobable target position and orientation simultaneously. The capability of the tracker to tolerate appearance changes like orientation changes, small scale changes, partial occlusions and background scene changes is demonstrated using real image sequences.
{"title":"Object Tracking using Color Correlogram","authors":"Qi Zhao, Hai Tao","doi":"10.1109/VSPETS.2005.1570924","DOIUrl":"https://doi.org/10.1109/VSPETS.2005.1570924","url":null,"abstract":"Color histogram based representations have been widely used for blob tracking. In this paper, a new color histogram based approach for object representation is proposed. By using a simplified version of color correlogram as object feature, spatial information is incorporated into object representation, which allows variations of rotation to be detected throughout the tracking therefore rotational objects can be more accurately tracked. The gradient decent method mean shift algorithm is adopted as the central computational module and further extended to a 3D domain to find the mostprobable target position and orientation simultaneously. The capability of the tracker to tolerate appearance changes like orientation changes, small scale changes, partial occlusions and background scene changes is demonstrated using real image sequences.","PeriodicalId":435841,"journal":{"name":"2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130126178","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 : 2005-10-15DOI: 10.1109/VSPETS.2005.1570902
K. Sato, J. Aggarwal
This paper presents a methodology for tracking moving objects in an occluded environment when occlusion occurs. We analyze sequences in which physical obstacles such as fences and trees divide an object into several blobs, both spatially and temporally. Our system successfully tracks the divided blobs as one object and reconstructs the whole object. We use the temporal spatio-velocity (TSV) transform and a cylinder model of object trajectories. The TSV transform extracts pixels with stable velocities and removes noisy pixels with unstable velocities. The cylinder model connects several blobs into one object and associates blobs that are occluded for a long period of time. We present results in which moving persons and vehicles occluded by fences and trees are successfully tracked even when the occlusion lasts for as long as 100 frames.
{"title":"Tracking objects in occluding environments using temporal spatio-velocity transform","authors":"K. Sato, J. Aggarwal","doi":"10.1109/VSPETS.2005.1570902","DOIUrl":"https://doi.org/10.1109/VSPETS.2005.1570902","url":null,"abstract":"This paper presents a methodology for tracking moving objects in an occluded environment when occlusion occurs. We analyze sequences in which physical obstacles such as fences and trees divide an object into several blobs, both spatially and temporally. Our system successfully tracks the divided blobs as one object and reconstructs the whole object. We use the temporal spatio-velocity (TSV) transform and a cylinder model of object trajectories. The TSV transform extracts pixels with stable velocities and removes noisy pixels with unstable velocities. The cylinder model connects several blobs into one object and associates blobs that are occluded for a long period of time. We present results in which moving persons and vehicles occluded by fences and trees are successfully tracked even when the occlusion lasts for as long as 100 frames.","PeriodicalId":435841,"journal":{"name":"2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125847415","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 : 2005-10-15DOI: 10.1109/VSPETS.2005.1570897
P. Guha, A. Mukerjee, K. Venkatesh
Tracking multiple agents in a monocular visual surveillance system is often challenged by the phenomenon of occlusions. Agents entering the field of view can undergo two different forms of occlusions, either caused by crowding or due to obstructions by background objects at finite distances from the camera. The agents are primarily detected as foreground blobs and are characterized by their motion history and weighted color histograms. These features are further used for localizing them in subsequent frames through motion prediction assisted mean shift tracking. A number of Boolean predicates are evaluated based on the fractional overlaps between the localized regions and foreground blobs. We construct predicates describing a comprehensive set of possible surveillance event primitives including entry/exit, partial or complete occlusions by background objects, crowding, splitting of agents and algorithm failures resulting from track loss. Instantiation of these event primitives followed by selective feature updates enables us to develop an effective scheme for tracking multiple agents in relatively unconstrained environments.
{"title":"Efficient occlusion handling for multiple agent tracking by reasoning with surveillance event primitives","authors":"P. Guha, A. Mukerjee, K. Venkatesh","doi":"10.1109/VSPETS.2005.1570897","DOIUrl":"https://doi.org/10.1109/VSPETS.2005.1570897","url":null,"abstract":"Tracking multiple agents in a monocular visual surveillance system is often challenged by the phenomenon of occlusions. Agents entering the field of view can undergo two different forms of occlusions, either caused by crowding or due to obstructions by background objects at finite distances from the camera. The agents are primarily detected as foreground blobs and are characterized by their motion history and weighted color histograms. These features are further used for localizing them in subsequent frames through motion prediction assisted mean shift tracking. A number of Boolean predicates are evaluated based on the fractional overlaps between the localized regions and foreground blobs. We construct predicates describing a comprehensive set of possible surveillance event primitives including entry/exit, partial or complete occlusions by background objects, crowding, splitting of agents and algorithm failures resulting from track loss. Instantiation of these event primitives followed by selective feature updates enables us to develop an effective scheme for tracking multiple agents in relatively unconstrained environments.","PeriodicalId":435841,"journal":{"name":"2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131498386","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 : 2005-10-15DOI: 10.1109/VSPETS.2005.1570894
Feng Tang, Hai Tao
Two major problems for model-based object tracking are: 1) how to represent an object so that it can effectively be discriminated with background and other objects; 2) how to dynamically update the model to accommodate the object appearance and structure changes. Traditional appearance based representations (like color histogram) fails when the object has rich texture. In this paper, we present a novel feature based object representation attributed relational graph (ARG) for reliable object tracking. The object is modeled with invariant features (SIFT) and their relationship is encoded in the form of an ARG that can effectively distinguish itself from background and other objects. We adopt a competitive and efficient dynamic model to adoptively update the object model by adding new stable features as well as deleting inactive features. A relaxation labeling method is used to match the model graph with the observation to gel the best object position. Experiments show that our method can get reliable track even under dramatic appearance changes, occlusions, etc.
{"title":"Object tracking with dynamic feature graph","authors":"Feng Tang, Hai Tao","doi":"10.1109/VSPETS.2005.1570894","DOIUrl":"https://doi.org/10.1109/VSPETS.2005.1570894","url":null,"abstract":"Two major problems for model-based object tracking are: 1) how to represent an object so that it can effectively be discriminated with background and other objects; 2) how to dynamically update the model to accommodate the object appearance and structure changes. Traditional appearance based representations (like color histogram) fails when the object has rich texture. In this paper, we present a novel feature based object representation attributed relational graph (ARG) for reliable object tracking. The object is modeled with invariant features (SIFT) and their relationship is encoded in the form of an ARG that can effectively distinguish itself from background and other objects. We adopt a competitive and efficient dynamic model to adoptively update the object model by adding new stable features as well as deleting inactive features. A relaxation labeling method is used to match the model graph with the observation to gel the best object position. Experiments show that our method can get reliable track even under dramatic appearance changes, occlusions, etc.","PeriodicalId":435841,"journal":{"name":"2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance","volume":"159 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115301007","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 : 2005-10-15DOI: 10.1109/VSPETS.2005.1570917
Hung-Son Le, Haibo Li
This paper presents an approach for face recognition across pose variations when only one sample image per person is available. From a near frontal face sample image, virtual views at different off-frontal angles were generated and used for the system training task. The manual work and computation burden, thus, are put on the offline training process, that makes it possible to build a real-time face recognition surveillance system. Our work exploited the inherent advantages of "single" HMM scheme, which is based on an ID discrete hidden Markov model (ID-DHMM) and is designed to avoid the need of retraining the system whenever it is provided new image(s). Experiment results on the CMU PIE face database demonstrate that the proposed scheme improves significantly the recognition performance
{"title":"Can the Surveillance System Run Pose Variant Face Recognition in Real Time?","authors":"Hung-Son Le, Haibo Li","doi":"10.1109/VSPETS.2005.1570917","DOIUrl":"https://doi.org/10.1109/VSPETS.2005.1570917","url":null,"abstract":"This paper presents an approach for face recognition across pose variations when only one sample image per person is available. From a near frontal face sample image, virtual views at different off-frontal angles were generated and used for the system training task. The manual work and computation burden, thus, are put on the offline training process, that makes it possible to build a real-time face recognition surveillance system. Our work exploited the inherent advantages of \"single\" HMM scheme, which is based on an ID discrete hidden Markov model (ID-DHMM) and is designed to avoid the need of retraining the system whenever it is provided new image(s). Experiment results on the CMU PIE face database demonstrate that the proposed scheme improves significantly the recognition performance","PeriodicalId":435841,"journal":{"name":"2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129268252","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：