This paper presents an original framework for evolving a vision-based mobile robot controller using genetic programming. This framework is built on the Open BEAGLE framework for the evolutionary computations, and on OpenGL for simulating the visual environment of a physical mobile robot. The feasibility of this framework is demonstrated through a simple, yet non-trivial, line following problem.
{"title":"Evolving a Vision-Based Line-Following Robot Controller","authors":"J. Dupuis, M. Parizeau","doi":"10.1109/CRV.2006.32","DOIUrl":"https://doi.org/10.1109/CRV.2006.32","url":null,"abstract":"This paper presents an original framework for evolving a vision-based mobile robot controller using genetic programming. This framework is built on the Open BEAGLE framework for the evolutionary computations, and on OpenGL for simulating the visual environment of a physical mobile robot. The feasibility of this framework is demonstrated through a simple, yet non-trivial, line following problem.","PeriodicalId":369170,"journal":{"name":"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114604529","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}
The present paper proposes an authentication scheme which relies on face biometrics and one-class Support Vector Machines. The proposed recognition procedures are based on both a global approach and on a combination of a global and a component-based approaches. Two different features extraction methods and three light compensation algorithms are tested. The combined system outperforms the global system and yields a significant performance enhancement with respect to the prior results obtained with the one-class Support Vector Machines approach for face recognition.
{"title":"User Authentication based on Face Recognition with Support Vector Machines","authors":"Paolo Abeni, M. Baltatu, Rosalia D'Alessandro","doi":"10.1109/CRV.2006.83","DOIUrl":"https://doi.org/10.1109/CRV.2006.83","url":null,"abstract":"The present paper proposes an authentication scheme which relies on face biometrics and one-class Support Vector Machines. The proposed recognition procedures are based on both a global approach and on a combination of a global and a component-based approaches. Two different features extraction methods and three light compensation algorithms are tested. The combined system outperforms the global system and yields a significant performance enhancement with respect to the prior results obtained with the one-class Support Vector Machines approach for face recognition.","PeriodicalId":369170,"journal":{"name":"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116363071","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}
Real-time 3D geometry and motion estimation has many important applications in areas such as robot navigation and dynamic image-based rendering. A novel algorithm is proposed in this paper for estimating 3D geometry and motion of dynamic scenes based on captured stereo sequences. All computations are conducted in the 2D image space of the center view and the results are represented in forms of disparity maps and disparity flow maps. A dynamic programming based technique is used for searching global optimal disparity maps and disparity flow maps under an energy minimization framework. To achieve high processing speed, most operations are implemented on the Graphics Processing Units (GPU) of programmable graphics hardware. As a result, the derived algorithm is capable of producing both 3D geometry and motion information for dynamic scenes in near real-time. Experiments on two trinocular stereo sequences demonstrate that the proposed algorithm can handle scenes that contain non-rigid motion as well as those captured by moving cameras.
{"title":"A GPU-based Algorithm for Estimating 3D Geometry and Motion in Near Real-time","authors":"Minglun Gong","doi":"10.1109/CRV.2006.4","DOIUrl":"https://doi.org/10.1109/CRV.2006.4","url":null,"abstract":"Real-time 3D geometry and motion estimation has many important applications in areas such as robot navigation and dynamic image-based rendering. A novel algorithm is proposed in this paper for estimating 3D geometry and motion of dynamic scenes based on captured stereo sequences. All computations are conducted in the 2D image space of the center view and the results are represented in forms of disparity maps and disparity flow maps. A dynamic programming based technique is used for searching global optimal disparity maps and disparity flow maps under an energy minimization framework. To achieve high processing speed, most operations are implemented on the Graphics Processing Units (GPU) of programmable graphics hardware. As a result, the derived algorithm is capable of producing both 3D geometry and motion information for dynamic scenes in near real-time. Experiments on two trinocular stereo sequences demonstrate that the proposed algorithm can handle scenes that contain non-rigid motion as well as those captured by moving cameras.","PeriodicalId":369170,"journal":{"name":"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128193888","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}
In this paper we discuss landmark based absolute localization of tiny autonomous mobile robots in a known environment. Landmark features are naturally occurring as it is not allowed to modify the environment with special navigational aids. These features are sparse in our application domain and are frequently occluded by other robots. This makes simultaneous acquisition of two or more landmarks difficult. Therefore, we propose a system that requires a single landmark feature. The algorithm is based on range measurement of a single landmark from two arbitrary points whose displacement can be measured using dead-reckoning sensors. Range estimation is done with a stereo vision system. Simulation results show that the robot can localize itself if it can estimates range of the same landmark from two different position and if the displacement between the two position is known.
{"title":"Single landmark based self-localization of mobile robots","authors":"Abdul Bais, Robert Sablatnig, J. Gu","doi":"10.1109/CRV.2006.67","DOIUrl":"https://doi.org/10.1109/CRV.2006.67","url":null,"abstract":"In this paper we discuss landmark based absolute localization of tiny autonomous mobile robots in a known environment. Landmark features are naturally occurring as it is not allowed to modify the environment with special navigational aids. These features are sparse in our application domain and are frequently occluded by other robots. This makes simultaneous acquisition of two or more landmarks difficult. Therefore, we propose a system that requires a single landmark feature. The algorithm is based on range measurement of a single landmark from two arbitrary points whose displacement can be measured using dead-reckoning sensors. Range estimation is done with a stereo vision system. Simulation results show that the robot can localize itself if it can estimates range of the same landmark from two different position and if the displacement between the two position is known.","PeriodicalId":369170,"journal":{"name":"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)","volume":"4020 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127539176","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}
The power of Markov random field formulations of lowlevel vision problems, such as stereo, has been known for some time. However, recent advances, both algorithmic and in processing power, have made their application practical. This paper presents a novel implementation of Bayesian belief propagation for graphics processing units found in most modern desktop and notebook computers, and applies it to the stereo problem. The stereo problem is used for comparison to other BP algorithms.
{"title":"Belief Propagation on the GPU for Stereo Vision","authors":"A. Brunton, Chang Shu, G. Roth","doi":"10.1109/CRV.2006.19","DOIUrl":"https://doi.org/10.1109/CRV.2006.19","url":null,"abstract":"The power of Markov random field formulations of lowlevel vision problems, such as stereo, has been known for some time. However, recent advances, both algorithmic and in processing power, have made their application practical. This paper presents a novel implementation of Bayesian belief propagation for graphics processing units found in most modern desktop and notebook computers, and applies it to the stereo problem. The stereo problem is used for comparison to other BP algorithms.","PeriodicalId":369170,"journal":{"name":"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130664926","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}
One of the more important limitations of actual tools for performing arts production and design is that collaboration between designers is hard to achieve. In fact, designers must actually be co-located to collaborate in the design of a show, something that is not always possible. While teleconference tools could be used to partially solve this problem, this solution offers no direct interactivity and no synchronization between designers. Also some problems like perspective effects and single viewpoint constrained by the camera are inherent to this solution. Specialized software for performing arts design (e.g. "Life Forms") do not generally provide real-time collaboration and are not really convenient for collaborative work. Also, these systems are often expensive and complex to operate. A more adapted solution combining concepts from virtual reality, network technology, and computer vision has then been specifically developed for collaborative work by performing arts designers. This paper presents a virtual reality application for supporting distributed collaborative production of theater shows resulting from our research. Among other constraints, this application has to ensure that the virtual scene that is being shared between multiple designers is always in sync (by use of computer vision) with a real counterpart and that this synchronization is achieved in real-time. Also, system cost must be kept as low as possible, platform independence must be achieved whenever possible and, since it is to be used by people that are not computer experts, the application has to be user-friendly.
{"title":"Avatar: a virtual reality based tool for collaborative production of theater shows","authors":"Christian Dompierre, D. Laurendeau","doi":"10.1109/CRV.2006.18","DOIUrl":"https://doi.org/10.1109/CRV.2006.18","url":null,"abstract":"One of the more important limitations of actual tools for performing arts production and design is that collaboration between designers is hard to achieve. In fact, designers must actually be co-located to collaborate in the design of a show, something that is not always possible. While teleconference tools could be used to partially solve this problem, this solution offers no direct interactivity and no synchronization between designers. Also some problems like perspective effects and single viewpoint constrained by the camera are inherent to this solution. Specialized software for performing arts design (e.g. \"Life Forms\") do not generally provide real-time collaboration and are not really convenient for collaborative work. Also, these systems are often expensive and complex to operate. A more adapted solution combining concepts from virtual reality, network technology, and computer vision has then been specifically developed for collaborative work by performing arts designers. This paper presents a virtual reality application for supporting distributed collaborative production of theater shows resulting from our research. Among other constraints, this application has to ensure that the virtual scene that is being shared between multiple designers is always in sync (by use of computer vision) with a real counterpart and that this synchronization is achieved in real-time. Also, system cost must be kept as low as possible, platform independence must be achieved whenever possible and, since it is to be used by people that are not computer experts, the application has to be user-friendly.","PeriodicalId":369170,"journal":{"name":"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)","volume":"361 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132983441","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}
This paper presents the groundwork for a distributed network of collaborating, intelligent surveillance cameras, implemented with low-cost embedded microprocessor camera modules. Each camera trains a person detection classifier using the Winnow algorithm for unsupervised, online learning. Training examples are automatically extracted and labelled, and the classifier is then used to locate person instances. To improve detection performance, multiple cameras with overlapping fields of view collaborate to confirm results. We present a novel, unsupervised calibration technique that allows each camera module to represent its spatial relationship with the rest. During runtime, cameras apply the learned spatial correlations to confirm each other’s detections. This technique implicitly handles non-overlapping regions that cannot be confirmed. Its computational efficiency is well-suited to real-time processing on our hardware.
{"title":"Collaborative Multi-Camera Surveillance with Automated Person Detection","authors":"T. Ahmedali, James J. Clark","doi":"10.1109/CRV.2006.21","DOIUrl":"https://doi.org/10.1109/CRV.2006.21","url":null,"abstract":"This paper presents the groundwork for a distributed network of collaborating, intelligent surveillance cameras, implemented with low-cost embedded microprocessor camera modules. Each camera trains a person detection classifier using the Winnow algorithm for unsupervised, online learning. Training examples are automatically extracted and labelled, and the classifier is then used to locate person instances. To improve detection performance, multiple cameras with overlapping fields of view collaborate to confirm results. We present a novel, unsupervised calibration technique that allows each camera module to represent its spatial relationship with the rest. During runtime, cameras apply the learned spatial correlations to confirm each other’s detections. This technique implicitly handles non-overlapping regions that cannot be confirmed. Its computational efficiency is well-suited to real-time processing on our hardware.","PeriodicalId":369170,"journal":{"name":"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130999485","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 show that differentiation via fitting B-splines to the spatio-temporal intensity data comprising an image sequence provides at least the same and usually better 2D Lucas and Kanade optical flow than that computed via Simoncelli’s balanced/matched filters.
{"title":"Using 3D Spline Differentiation to Compute Quantitative Optical Flow","authors":"J. Barron, M. Daniel, J. Mari","doi":"10.1109/CRV.2006.84","DOIUrl":"https://doi.org/10.1109/CRV.2006.84","url":null,"abstract":"We show that differentiation via fitting B-splines to the spatio-temporal intensity data comprising an image sequence provides at least the same and usually better 2D Lucas and Kanade optical flow than that computed via Simoncelli’s balanced/matched filters.","PeriodicalId":369170,"journal":{"name":"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121309905","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}
A method is proposed to detect multi-part man-made or natural objects in complex images. It consists in first extracting simple curves and straight lines from the edge map. Then, a search tree is expanded by selecting and ordering the segmented primitives on the basis of generic local and global grouping criteria. The set of partial contours provided by the parallel search are combined into more complex forms. Global scores produce a sorted list of potential object silhouettes.
{"title":"Generic Detection of Multi-Part Objects by High-Level Analysis","authors":"J. Bernier, R. Bergevin","doi":"10.1109/CRV.2006.36","DOIUrl":"https://doi.org/10.1109/CRV.2006.36","url":null,"abstract":"A method is proposed to detect multi-part man-made or natural objects in complex images. It consists in first extracting simple curves and straight lines from the edge map. Then, a search tree is expanded by selecting and ordering the segmented primitives on the basis of generic local and global grouping criteria. The set of partial contours provided by the parallel search are combined into more complex forms. Global scores produce a sorted list of potential object silhouettes.","PeriodicalId":369170,"journal":{"name":"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122182174","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}
V. Petrushin, Gang Wei, Omer Shakil, D. Roqueiro, A. Gershman
This paper describes a surveillance system that uses a network of sensors of different kind for localizing and tracking people in an office environment. The sensor network consists of video cameras, infrared tag readers, a fingerprint reader and a PTZ camera. The system implements a Bayesian framework that uses noisy, but redundant data from multiple sensor streams and incorporates it with the contextual and domain knowledge. The paper describes approaches to camera specification, dynamic background modeling, object modeling and probabilistic inference. The preliminary experimental results are presented and discussed.
{"title":"Multiple-Sensor Indoor Surveillance System","authors":"V. Petrushin, Gang Wei, Omer Shakil, D. Roqueiro, A. Gershman","doi":"10.1109/CRV.2006.50","DOIUrl":"https://doi.org/10.1109/CRV.2006.50","url":null,"abstract":"This paper describes a surveillance system that uses a network of sensors of different kind for localizing and tracking people in an office environment. The sensor network consists of video cameras, infrared tag readers, a fingerprint reader and a PTZ camera. The system implements a Bayesian framework that uses noisy, but redundant data from multiple sensor streams and incorporates it with the contextual and domain knowledge. The paper describes approaches to camera specification, dynamic background modeling, object modeling and probabilistic inference. The preliminary experimental results are presented and discussed.","PeriodicalId":369170,"journal":{"name":"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125232645","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：