We present a formal framework for robotic cooperation in which we use an extension to Petri nets, known as workflow nets, to establish a protocol among mobile agents based on the task coverage they maintain. Our choice is motivated by the fact that Petri nets handle concurrency and that goal reachability can be theoretically established. We describe the means by which cooperation is performed with Petri nets and analyze their structural and behavioral characteristics in order to show the correctness of our framework.
{"title":"Petri Net-Based Cooperation In Multi-Agent Systems","authors":"Y. Kotb, S. Beauchemin, J. Barron","doi":"10.1109/CRV.2007.49","DOIUrl":"https://doi.org/10.1109/CRV.2007.49","url":null,"abstract":"We present a formal framework for robotic cooperation in which we use an extension to Petri nets, known as workflow nets, to establish a protocol among mobile agents based on the task coverage they maintain. Our choice is motivated by the fact that Petri nets handle concurrency and that goal reachability can be theoretically established. We describe the means by which cooperation is performed with Petri nets and analyze their structural and behavioral characteristics in order to show the correctness of our framework.","PeriodicalId":304254,"journal":{"name":"Fourth Canadian Conference on Computer and Robot Vision (CRV '07)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123953469","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 propose a novel object tracking algorithm in video sequences. The formulation of the object tracking is based on variational calculus, where an adaptive parametric mixture model is used for object features representation. The tracking is based on matching the object mixture models between successive frames of the sequence by using active contours while adapting the mixture model to varying object appearance changes due to illumination conditions and camera geometry. The implementation of the method is based on level set active contours which allow for automatic topology changes and stable numerical schemes. We validate our approach on examples of object tracking performed on real video sequences.
{"title":"Adaptive Appearance Model for Object Contour Tracking in Videos","authors":"M. S. Allili, D. Ziou","doi":"10.1109/CRV.2007.9","DOIUrl":"https://doi.org/10.1109/CRV.2007.9","url":null,"abstract":"In this paper, we propose a novel object tracking algorithm in video sequences. The formulation of the object tracking is based on variational calculus, where an adaptive parametric mixture model is used for object features representation. The tracking is based on matching the object mixture models between successive frames of the sequence by using active contours while adapting the mixture model to varying object appearance changes due to illumination conditions and camera geometry. The implementation of the method is based on level set active contours which allow for automatic topology changes and stable numerical schemes. We validate our approach on examples of object tracking performed on real video sequences.","PeriodicalId":304254,"journal":{"name":"Fourth Canadian Conference on Computer and Robot Vision (CRV '07)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122437776","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}
To perform as desired in a dynamic environment a vision system must adapt to a variety of operating conditions by selecting vision modules, tuning their parameters, and controlling image acquisition. Knowledge-based (KB) controller-agents that reason over explicitly represented knowledge and interact with their environment can be used for this task; however, the lack of a unifyingmethodology and development tools makes KB controllers difficult to create, maintain, and reuse. This paper presents the INVICON toolkit, based on the IndiGolog agent programming language with elements from control theory. It provides a basic methodology, a vision module declaration template, a suite of control components, and support tools for KB controller development. We have evaluated INVICON in two case studies that involved controlling vision-based pose estimation systems. The case studies show that INVICON reduces the effort needed to build KB controllers for challenging domains and improves their flexibility and robustness.
{"title":"INVICON: A Toolkit for Knowledge-Based Control of Vision Systems","authors":"O. Borzenko, Y. Lespérance, M. Jenkin","doi":"10.1109/CRV.2007.41","DOIUrl":"https://doi.org/10.1109/CRV.2007.41","url":null,"abstract":"To perform as desired in a dynamic environment a vision system must adapt to a variety of operating conditions by selecting vision modules, tuning their parameters, and controlling image acquisition. Knowledge-based (KB) controller-agents that reason over explicitly represented knowledge and interact with their environment can be used for this task; however, the lack of a unifyingmethodology and development tools makes KB controllers difficult to create, maintain, and reuse. This paper presents the INVICON toolkit, based on the IndiGolog agent programming language with elements from control theory. It provides a basic methodology, a vision module declaration template, a suite of control components, and support tools for KB controller development. We have evaluated INVICON in two case studies that involved controlling vision-based pose estimation systems. The case studies show that INVICON reduces the effort needed to build KB controllers for challenging domains and improves their flexibility and robustness.","PeriodicalId":304254,"journal":{"name":"Fourth Canadian Conference on Computer and Robot Vision (CRV '07)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121080132","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 introduces a novel method to simulate B-mode medical ultrasound speckle in synthetic images. Our approach takes into account both the ultrasound image formation model and the speckle formation model. The algorithm first modifies the geometry of an ideal noiseless image to match that of a sectoral B-mode ultrasonogram, by subsampling a grid of pixels to simulate the acquisition and quantization steps of image formation. Then, speckle is added by simulating a random walk in the plane of the complex amplitude, according to the Burckhardt speckle formation model. We finally interpolate the noisy subsampled pixels in order to fill the space introduced by the sampling step and recover a complete image, as would a real ultrasonograph. Synthetic speckle images generated by this method are visually and theoretically very close to real ultrasonograms.
{"title":"Speckle Simulation Based on B-Mode Echographic Image Acquisition Model","authors":"Charles Perreault, M. Auclair-Fortier","doi":"10.1109/CRV.2007.61","DOIUrl":"https://doi.org/10.1109/CRV.2007.61","url":null,"abstract":"This paper introduces a novel method to simulate B-mode medical ultrasound speckle in synthetic images. Our approach takes into account both the ultrasound image formation model and the speckle formation model. The algorithm first modifies the geometry of an ideal noiseless image to match that of a sectoral B-mode ultrasonogram, by subsampling a grid of pixels to simulate the acquisition and quantization steps of image formation. Then, speckle is added by simulating a random walk in the plane of the complex amplitude, according to the Burckhardt speckle formation model. We finally interpolate the noisy subsampled pixels in order to fill the space introduced by the sampling step and recover a complete image, as would a real ultrasonograph. Synthetic speckle images generated by this method are visually and theoretically very close to real ultrasonograms.","PeriodicalId":304254,"journal":{"name":"Fourth Canadian Conference on Computer and Robot Vision (CRV '07)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130706944","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 work addresses the practical problem of keeping a camera network calibrated during a recording session. When dealing with real-time applications, a robust calibration of the camera network needs to be assured, without the burden of a full system recalibration at every (un)intended camera displacement. In this paper we present an efficient algorithm to detect when the extrinsic parameters of a camera are no longer valid, and reintegrate the displaced camera into the previously calibrated camera network. When the intrinsic parameters of the cameras are known, the algorithm can also be used to build ad-hoc distributed camera networks, starting from three calibrated cameras. Recalibration is done using pairs of essential matrices, based on image point correspondences. Unlike other approaches, we do not explicitly compute any 3D structure for our calibration purposes.
{"title":"Extrinsic Recalibration in Camera Networks","authors":"C. Hermans, Maarten Dumont, P. Bekaert","doi":"10.1109/CRV.2007.31","DOIUrl":"https://doi.org/10.1109/CRV.2007.31","url":null,"abstract":"This work addresses the practical problem of keeping a camera network calibrated during a recording session. When dealing with real-time applications, a robust calibration of the camera network needs to be assured, without the burden of a full system recalibration at every (un)intended camera displacement. In this paper we present an efficient algorithm to detect when the extrinsic parameters of a camera are no longer valid, and reintegrate the displaced camera into the previously calibrated camera network. When the intrinsic parameters of the cameras are known, the algorithm can also be used to build ad-hoc distributed camera networks, starting from three calibrated cameras. Recalibration is done using pairs of essential matrices, based on image point correspondences. Unlike other approaches, we do not explicitly compute any 3D structure for our calibration purposes.","PeriodicalId":304254,"journal":{"name":"Fourth Canadian Conference on Computer and Robot Vision (CRV '07)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116785339","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 how a greedy approach to visual search - i.e., directly moving to the most likely location of the target - can be suboptimal, if the target object is hard to detect. Instead it is more efficient and leads to higher detection accuracy to first look for other related objects, that are easier to detect. These provide contextual priors for the target that make it easier to find. We demonstrate this in simulation using POMDP models, focussing on two special cases: where the target object is contained within the related object, and where the target object is spatially adjacent to the related object.
{"title":"A non-myopic approach to visual search","authors":"Julia Vogel, Kevin P. Murphy","doi":"10.1109/CRV.2007.5","DOIUrl":"https://doi.org/10.1109/CRV.2007.5","url":null,"abstract":"We show how a greedy approach to visual search - i.e., directly moving to the most likely location of the target - can be suboptimal, if the target object is hard to detect. Instead it is more efficient and leads to higher detection accuracy to first look for other related objects, that are easier to detect. These provide contextual priors for the target that make it easier to find. We demonstrate this in simulation using POMDP models, focussing on two special cases: where the target object is contained within the related object, and where the target object is spatially adjacent to the related object.","PeriodicalId":304254,"journal":{"name":"Fourth Canadian Conference on Computer and Robot Vision (CRV '07)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128957233","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 images framed by human operators, as opposed to those taken under computer control, the position of objects can be an important clue to saliency. This paper uses the Berkeley image data set to show how locational and photometric information can be combined to extract a probability of saliency for all image pixels. This probability can then be thresholded and segmented to extract compact image regions with high probability of saliency. A self assessment procedure allows the algorithm to evaluate the accuracy of its results. The method can extract salient regions of non uniform color, brightness or texture against highly variable background.
{"title":"Extracting Salient Objects from Operator-Framed Images","authors":"D. Crevier","doi":"10.1109/CRV.2007.30","DOIUrl":"https://doi.org/10.1109/CRV.2007.30","url":null,"abstract":"In images framed by human operators, as opposed to those taken under computer control, the position of objects can be an important clue to saliency. This paper uses the Berkeley image data set to show how locational and photometric information can be combined to extract a probability of saliency for all image pixels. This probability can then be thresholded and segmented to extract compact image regions with high probability of saliency. A self assessment procedure allows the algorithm to evaluate the accuracy of its results. The method can extract salient regions of non uniform color, brightness or texture against highly variable background.","PeriodicalId":304254,"journal":{"name":"Fourth Canadian Conference on Computer and Robot Vision (CRV '07)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115827710","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 proposes a novel single-camera range estimation method using images transmitted through a double-sided half-mirror plate. The exit-side halfmirror reflects and transmits the transmitted light through the incident-side half-mirror. The transmitted light directly reaches to the camera through the exit-side half-mirror, but some of the reflected light at the exitside half-mirror is then reflected again at the incidentside half-mirror and reaches the camera. Those multiple paths create a layered image in which displacement between the images differs with object distance. The constraint in the layered image is presented. The range to the object can be derived by finding correspondences on constraint lines using the autocorrelation of the layered image with similarity indices. The correspondence position is estimated using a parabola fitting with systematic error cancellation to enhance the accuracy without iteration. Ray tracing enables computation of a rigorous range to the object. This paper presents a theoretical formulation and experimental results obtained using an actual system with a doublesided half-mirror, which is realized using a transparent acrylic plate and two half-mirrors on thin glass-plate.
{"title":"Monocular Range Estimation through a Double-Sided Half-Mirror Plate","authors":"M. Shimizu, M. Okutomi","doi":"10.1109/CRV.2007.46","DOIUrl":"https://doi.org/10.1109/CRV.2007.46","url":null,"abstract":"This paper proposes a novel single-camera range estimation method using images transmitted through a double-sided half-mirror plate. The exit-side halfmirror reflects and transmits the transmitted light through the incident-side half-mirror. The transmitted light directly reaches to the camera through the exit-side half-mirror, but some of the reflected light at the exitside half-mirror is then reflected again at the incidentside half-mirror and reaches the camera. Those multiple paths create a layered image in which displacement between the images differs with object distance. The constraint in the layered image is presented. The range to the object can be derived by finding correspondences on constraint lines using the autocorrelation of the layered image with similarity indices. The correspondence position is estimated using a parabola fitting with systematic error cancellation to enhance the accuracy without iteration. Ray tracing enables computation of a rigorous range to the object. This paper presents a theoretical formulation and experimental results obtained using an actual system with a doublesided half-mirror, which is realized using a transparent acrylic plate and two half-mirrors on thin glass-plate.","PeriodicalId":304254,"journal":{"name":"Fourth Canadian Conference on Computer and Robot Vision (CRV '07)","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132415674","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 design and implementation of a multi-resolution graph cuts (MRGC) for stereo-motion framework that produces dense disparity maps. Both stereo and motion are estimated simultaneously under the original graph cuts framework. Our framework extends the problem from one to five dimensions, creating a large in- crease in complexity. Using three different multi-resolution graph cut algorithms, LDNR, EL and SAC, we reduce the number of pixels m and the number of labels n that limit the alpha - beta swap algorithm (with complexity O(mn 2) required from the definition of our semi-metric smoothness function. This results in a reduction of computation time and the ability to handle larger images and larger label sets. The choice of the three MRGC algorithms to use in computation deter- mines the appropriate level of accuracy and computation time desired.
{"title":"Establishing Visual Correspondence from Multi-Resolution Graph Cuts for Stereo-Motion","authors":"Joshua Worby, James MacLean","doi":"10.1109/CRV.2007.28","DOIUrl":"https://doi.org/10.1109/CRV.2007.28","url":null,"abstract":"This paper presents the design and implementation of a multi-resolution graph cuts (MRGC) for stereo-motion framework that produces dense disparity maps. Both stereo and motion are estimated simultaneously under the original graph cuts framework. Our framework extends the problem from one to five dimensions, creating a large in- crease in complexity. Using three different multi-resolution graph cut algorithms, LDNR, EL and SAC, we reduce the number of pixels m and the number of labels n that limit the alpha - beta swap algorithm (with complexity O(mn 2) required from the definition of our semi-metric smoothness function. This results in a reduction of computation time and the ability to handle larger images and larger label sets. The choice of the three MRGC algorithms to use in computation deter- mines the appropriate level of accuracy and computation time desired.","PeriodicalId":304254,"journal":{"name":"Fourth Canadian Conference on Computer and Robot Vision (CRV '07)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132203569","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}
An active vision system has to enable the implementation of reactive visual processes in real time. Given a stereoscopic vision system, the vergence angle, together with version and tilt angles, describes uniquely the fixation point in space. We interpret vision and motor control, and in particular we focus on developing and testing of a control strategy that fits the Hering's law, by studying the cooperation of vergence and version movements. The analysis of the simulation results confirmed the advantages of the Hering's law to achieve fast system reactions. We show that real-time active vergence and depth estimation become possible when the estimated disparity is reliable and fast. In this framework, the advantage of a simple and fast phase-based technique for depth estimation that allows real-time stereo processing with sub-pixel resolution is also discussed.
{"title":"Version and vergence control of a stereo camera head by fitting the movement into the Hering's law","authors":"J. Samarawickrama, S. Sabatini","doi":"10.1109/CRV.2007.69","DOIUrl":"https://doi.org/10.1109/CRV.2007.69","url":null,"abstract":"An active vision system has to enable the implementation of reactive visual processes in real time. Given a stereoscopic vision system, the vergence angle, together with version and tilt angles, describes uniquely the fixation point in space. We interpret vision and motor control, and in particular we focus on developing and testing of a control strategy that fits the Hering's law, by studying the cooperation of vergence and version movements. The analysis of the simulation results confirmed the advantages of the Hering's law to achieve fast system reactions. We show that real-time active vergence and depth estimation become possible when the estimated disparity is reliable and fast. In this framework, the advantage of a simple and fast phase-based technique for depth estimation that allows real-time stereo processing with sub-pixel resolution is also discussed.","PeriodicalId":304254,"journal":{"name":"Fourth Canadian Conference on Computer and Robot Vision (CRV '07)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114328754","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：