In this paper a deblurring algorithm is proposed that takes advantage of the properties of the shear let transform. Shear lets have mathematically been proven to be more efficient than traditional wavelets for representing distributed discontinuities such as edges. The proposed method extends the state of art Forward algorithm by incorporating shear lets. Experimental results show a significant improvement over some important deblurring algorithms found in the literature.
{"title":"Image De-blurring Using Shearlets","authors":"Amirhossein Firouzmanesh, P. Boulanger","doi":"10.1109/CRV.2012.30","DOIUrl":"https://doi.org/10.1109/CRV.2012.30","url":null,"abstract":"In this paper a deblurring algorithm is proposed that takes advantage of the properties of the shear let transform. Shear lets have mathematically been proven to be more efficient than traditional wavelets for representing distributed discontinuities such as edges. The proposed method extends the state of art Forward algorithm by incorporating shear lets. Experimental results show a significant improvement over some important deblurring algorithms found in the literature.","PeriodicalId":372951,"journal":{"name":"2012 Ninth Conference on Computer and Robot Vision","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122734086","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}
Object recognition systems that use 3D point cloud as the input data are potentially subjected to the problems of signal attenuation at a local level, or occlusions in cluttered scenes. In an attempt to develop more robust methods in handling these problems, the present paper introduces the notion of repeatable regions through a 3D region segmentation algorithm based on the extraction of repeatable interest points. A segmentation method presented is presented which is capable of segmenting 3D images of free-form objects using piece-wise boundary curves and regions reconstructed from extracted interest points. An experimental evaluation was devised to confirm the repeatability of segments in various realistic scenes, including cluttered and partially occluded scene. Three different 3D free-form objects in seven 2.5D scenes were tested in the experiment, with results showing that out of the top 15 selected regions from each 3D model, an average of six repeatable segmented regions with at least one correctly segmented region were recorded for each scene. This shows that highly repeatable regions can be localized and used to drive robust object recognition in 3D data.
{"title":"On the Repeatability of 3D Point Cloud Segmentation Based on Interest Points","authors":"Joseph Lam, M. Greenspan","doi":"10.1109/CRV.2012.9","DOIUrl":"https://doi.org/10.1109/CRV.2012.9","url":null,"abstract":"Object recognition systems that use 3D point cloud as the input data are potentially subjected to the problems of signal attenuation at a local level, or occlusions in cluttered scenes. In an attempt to develop more robust methods in handling these problems, the present paper introduces the notion of repeatable regions through a 3D region segmentation algorithm based on the extraction of repeatable interest points. A segmentation method presented is presented which is capable of segmenting 3D images of free-form objects using piece-wise boundary curves and regions reconstructed from extracted interest points. An experimental evaluation was devised to confirm the repeatability of segments in various realistic scenes, including cluttered and partially occluded scene. Three different 3D free-form objects in seven 2.5D scenes were tested in the experiment, with results showing that out of the top 15 selected regions from each 3D model, an average of six repeatable segmented regions with at least one correctly segmented region were recorded for each scene. This shows that highly repeatable regions can be localized and used to drive robust object recognition in 3D data.","PeriodicalId":372951,"journal":{"name":"2012 Ninth Conference on Computer and Robot Vision","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131251779","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}
Behaviour recognition and video understanding are core components of video surveillance and its real life applications. Recently there has been much effort to devise automated real-time high accuracy video surveillance systems. In this paper, we introduce an approach that detects semantic behaviours based on object and inter-object motion features. A number of interesting types of behaviour have been selected to demonstrate the capabilities of this approach. These types of behaviour are relevant to and most commonly encountered in public transportation systems such as abandoned and stolen luggage, fighting, fainting, and loitering. Using standard public datasets, the experimental results here demonstrate the effectiveness and low computational complexity of this approach, and its superiority to approaches described in some other work.
{"title":"Real-Time Semantics-Based Detection of Suspicious Activities in Public Spaces","authors":"Mohannad Elhamod, M. Levine","doi":"10.1109/CRV.2012.42","DOIUrl":"https://doi.org/10.1109/CRV.2012.42","url":null,"abstract":"Behaviour recognition and video understanding are core components of video surveillance and its real life applications. Recently there has been much effort to devise automated real-time high accuracy video surveillance systems. In this paper, we introduce an approach that detects semantic behaviours based on object and inter-object motion features. A number of interesting types of behaviour have been selected to demonstrate the capabilities of this approach. These types of behaviour are relevant to and most commonly encountered in public transportation systems such as abandoned and stolen luggage, fighting, fainting, and loitering. Using standard public datasets, the experimental results here demonstrate the effectiveness and low computational complexity of this approach, and its superiority to approaches described in some other work.","PeriodicalId":372951,"journal":{"name":"2012 Ninth Conference on Computer and Robot Vision","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122695482","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 recent years, many different proposals for visual saliency computation have been put forth, that generally frame the determination of visual saliency as a measure of local feature contrast. There is however, a paucity of approaches that take into account more global holistic elements of the scene. In this paper, we propose a novel mechanism that augments the visual representation used to compute saliency. Inspired by research into biological vision, this strategy is one based on the role of recurrent computation in a visual processing hierarchy. Unlike existing approaches, the proposed model provides a manner of refining local saliency based computation based on the more global composition of a scene that is independent of semantic labeling or viewpoint. The results presented demonstrate that a fast recurrent mechanism significantly augments the determination of salient regions of interest as compared with a purely feed forward visual saliency architecture. This demonstration is applied to the problem of detecting targets of interest in various surveillance scenarios.
{"title":"Recurrent Refinement for Visual Saliency Estimation in Surveillance Scenarios","authors":"Neil D. B. Bruce, Xun Shi, John K. Tsotsos","doi":"10.1109/CRV.2012.23","DOIUrl":"https://doi.org/10.1109/CRV.2012.23","url":null,"abstract":"In recent years, many different proposals for visual saliency computation have been put forth, that generally frame the determination of visual saliency as a measure of local feature contrast. There is however, a paucity of approaches that take into account more global holistic elements of the scene. In this paper, we propose a novel mechanism that augments the visual representation used to compute saliency. Inspired by research into biological vision, this strategy is one based on the role of recurrent computation in a visual processing hierarchy. Unlike existing approaches, the proposed model provides a manner of refining local saliency based computation based on the more global composition of a scene that is independent of semantic labeling or viewpoint. The results presented demonstrate that a fast recurrent mechanism significantly augments the determination of salient regions of interest as compared with a purely feed forward visual saliency architecture. This demonstration is applied to the problem of detecting targets of interest in various surveillance scenarios.","PeriodicalId":372951,"journal":{"name":"2012 Ninth Conference on Computer and Robot Vision","volume":"299 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123274666","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, a contact-free heart rate measurement method using an ambient light camera is proposed. The color features of skin-like pixels are used for time domain frequency analysis, in which a skin color classifier is applied. A novel data adjustment scheme is further integrated to automatically expand sampling time length and increase measurement precision. Five people of different age, six cameras of different type, and four different body parts have been tested in this paper. Experimental results show the effectiveness of the proposed method comparing with a pulse oximeter device. The advantages of the proposed method include: 1) it uses a low-cost ambient light camera, 2) it eases the discomfort of people based on contact-free methodology, 3) it measures multiple persons' heart rates fully automatic, and 4) it can be applied in multiple parts of a human body such as head and neck, arm, and palm regions.
{"title":"Contact-Free Heart Rate Measurement Using a Camera","authors":"Kual-Zheng Lee, Pang-Chan Hung, L. Tsai","doi":"10.1109/CRV.2012.27","DOIUrl":"https://doi.org/10.1109/CRV.2012.27","url":null,"abstract":"In this paper, a contact-free heart rate measurement method using an ambient light camera is proposed. The color features of skin-like pixels are used for time domain frequency analysis, in which a skin color classifier is applied. A novel data adjustment scheme is further integrated to automatically expand sampling time length and increase measurement precision. Five people of different age, six cameras of different type, and four different body parts have been tested in this paper. Experimental results show the effectiveness of the proposed method comparing with a pulse oximeter device. The advantages of the proposed method include: 1) it uses a low-cost ambient light camera, 2) it eases the discomfort of people based on contact-free methodology, 3) it measures multiple persons' heart rates fully automatic, and 4) it can be applied in multiple parts of a human body such as head and neck, arm, and palm regions.","PeriodicalId":372951,"journal":{"name":"2012 Ninth Conference on Computer and Robot Vision","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125502329","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}
During exploration of an unknown environment by a single robot, the robot is driven by two conflicting goals: to explore as fast as possible, and to produce the most accurate map. While fast exploration necessitates minimizing traversal of already mapped territory, accurate mapping requires that the robot passes over previously explored areas to reduce the localization and map uncertainty. This problem has been labelled as exploration versus exploitation. In this paper the problem of mapping a camera sensor network by a mobile robot has been used to demonstrate the effect that different exploration strategies have on uncertainty and speed of exploration. Simulation results using a realistic noise model are presented for different environments and for different strategies.
{"title":"Single Robot Exploration: Simultaneous Localization and Uncertainty Reduction on Maps (SLURM)","authors":"Ioannis M. Rekleitis","doi":"10.1109/CRV.2012.36","DOIUrl":"https://doi.org/10.1109/CRV.2012.36","url":null,"abstract":"During exploration of an unknown environment by a single robot, the robot is driven by two conflicting goals: to explore as fast as possible, and to produce the most accurate map. While fast exploration necessitates minimizing traversal of already mapped territory, accurate mapping requires that the robot passes over previously explored areas to reduce the localization and map uncertainty. This problem has been labelled as exploration versus exploitation. In this paper the problem of mapping a camera sensor network by a mobile robot has been used to demonstrate the effect that different exploration strategies have on uncertainty and speed of exploration. Simulation results using a realistic noise model are presented for different environments and for different strategies.","PeriodicalId":372951,"journal":{"name":"2012 Ninth Conference on Computer and Robot Vision","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121499320","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 address the problem of path planning for robot missions based on waypoints suggested by multiple human users. These users may be operating under distinct mission objectives and hence suggest different locations for the robot to visit. We formulate this problem using a constrained optimization approach by imposing various operational considerations, such as the robot's maximum traversable distance. We then propose an approximative path planning algorithm with parameterized control over the degree of "social fairness" in the selection of waypoints from different users. Through a user study, we compared the performance of the proposed path planner under different fairness settings and for different mission scenarios.
{"title":"Socially-Driven Collective Path Planning for Robot Missions","authors":"J. A. G. Higuera, Anqi Xu, F. Shkurti, G. Dudek","doi":"10.1109/CRV.2012.62","DOIUrl":"https://doi.org/10.1109/CRV.2012.62","url":null,"abstract":"We address the problem of path planning for robot missions based on waypoints suggested by multiple human users. These users may be operating under distinct mission objectives and hence suggest different locations for the robot to visit. We formulate this problem using a constrained optimization approach by imposing various operational considerations, such as the robot's maximum traversable distance. We then propose an approximative path planning algorithm with parameterized control over the degree of \"social fairness\" in the selection of waypoints from different users. Through a user study, we compared the performance of the proposed path planner under different fairness settings and for different mission scenarios.","PeriodicalId":372951,"journal":{"name":"2012 Ninth Conference on Computer and Robot Vision","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133193548","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}
M. Abdelrahman, Asem M. Ali, A. Farag, M. Casanova, A. Farag
Autism is a complex developmental disability, characterized by deficits in social interaction, communication skills, range of interests, and occasionally the presence of stereotyped behaviors. Several studies show that changes in brain weight and volume over aging follow a unique trajectory in those affected by the condition~cite{MICCAIMost00}. In this work, we develop a robust technique for evaluating the volume of white matter (WM), and use it as the main classification criteria. We perform MRI-based analysis on the brains of 14 autistic and 28 control subjects, male and female between aged 7 to 38 years. The proposed framework consists of several stages. First, the entire T1-weighted MRI scans are filtered out from noise using anisotropic diffusion filter. Then, the white matter (WM) is segmented from the skull. The segmentation framework is the search for maximum-a-posterior configurations in a Markov Gibbs Random Field (MGRF) model. A 3D mesh is then generated from the segmented WM. Finally, the volume of the 3D mesh is computed using a new algorithm. The experiments show accurate classification results of the proposed framework.
{"title":"New Approach for Classification of Autistic vs. Typically Developing Brain Using White Matter Volumes","authors":"M. Abdelrahman, Asem M. Ali, A. Farag, M. Casanova, A. Farag","doi":"10.1109/CRV.2012.44","DOIUrl":"https://doi.org/10.1109/CRV.2012.44","url":null,"abstract":"Autism is a complex developmental disability, characterized by deficits in social interaction, communication skills, range of interests, and occasionally the presence of stereotyped behaviors. Several studies show that changes in brain weight and volume over aging follow a unique trajectory in those affected by the condition~cite{MICCAIMost00}. In this work, we develop a robust technique for evaluating the volume of white matter (WM), and use it as the main classification criteria. We perform MRI-based analysis on the brains of 14 autistic and 28 control subjects, male and female between aged 7 to 38 years. The proposed framework consists of several stages. First, the entire T1-weighted MRI scans are filtered out from noise using anisotropic diffusion filter. Then, the white matter (WM) is segmented from the skull. The segmentation framework is the search for maximum-a-posterior configurations in a Markov Gibbs Random Field (MGRF) model. A 3D mesh is then generated from the segmented WM. Finally, the volume of the 3D mesh is computed using a new algorithm. The experiments show accurate classification results of the proposed framework.","PeriodicalId":372951,"journal":{"name":"2012 Ninth Conference on Computer and Robot Vision","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131221423","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 addresses the problem of full body articulated human motion tracking from multi-view video data recorded in a laboratory environment. The problem is formulated as a high dimensional (31-dimensional) non-linear optimization problem. In recent years, metaheuristics such as Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Artificial Immune System (AIS), Firefly Algorithm (FA) are applied to complex non-linear optimization problems. These population based evolutionary algorithms have diversified search capabilities and are computationally robust and efficient. One such recently proposed metaheuristic, Bat Algorithm (BA), is employed in this work for full human body pose estimation. The performance of BA is compared with Particle Filter (PF), Annealed Particle Filter (APF) and PSO using a standard data set. The qualitative and the quantitative evaluation of the performance of full body human tracking demonstrates that BA performs better then PF, APF and PSO.
{"title":"A Metaheuristic Bat-Inspired Algorithm for Full Body Human Pose Estimation","authors":"S. Akhtar, Abdul-Rahim Ahmad, E. Abdel-Rahman","doi":"10.1109/CRV.2012.55","DOIUrl":"https://doi.org/10.1109/CRV.2012.55","url":null,"abstract":"This paper addresses the problem of full body articulated human motion tracking from multi-view video data recorded in a laboratory environment. The problem is formulated as a high dimensional (31-dimensional) non-linear optimization problem. In recent years, metaheuristics such as Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Artificial Immune System (AIS), Firefly Algorithm (FA) are applied to complex non-linear optimization problems. These population based evolutionary algorithms have diversified search capabilities and are computationally robust and efficient. One such recently proposed metaheuristic, Bat Algorithm (BA), is employed in this work for full human body pose estimation. The performance of BA is compared with Particle Filter (PF), Annealed Particle Filter (APF) and PSO using a standard data set. The qualitative and the quantitative evaluation of the performance of full body human tracking demonstrates that BA performs better then PF, APF and PSO.","PeriodicalId":372951,"journal":{"name":"2012 Ninth Conference on Computer and Robot Vision","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115670746","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}
Current background subtraction methods require background modeling to handle dynamic backgrounds. The purpose of our study is to investigate a background template subtraction method to detect foreground objects in the presence of background variations. The method uses a single reference image but the change detection process allows change in the background including illumination changes and dynamic scenes. Using indoor and outdoor scenes, we compare our method to the best state-of-the art algorithms using both quantitative and qualitative evaluation. The results show that our method is in general more accurate and more effective.
{"title":"Robust Background Subtraction Using Geodesic Active Contours in ICA Subspace for Video Surveillance Applications","authors":"H. Sekkati, R. Laganière, A. Mitiche, R. Youmaran","doi":"10.1109/CRV.2012.33","DOIUrl":"https://doi.org/10.1109/CRV.2012.33","url":null,"abstract":"Current background subtraction methods require background modeling to handle dynamic backgrounds. The purpose of our study is to investigate a background template subtraction method to detect foreground objects in the presence of background variations. The method uses a single reference image but the change detection process allows change in the background including illumination changes and dynamic scenes. Using indoor and outdoor scenes, we compare our method to the best state-of-the art algorithms using both quantitative and qualitative evaluation. The results show that our method is in general more accurate and more effective.","PeriodicalId":372951,"journal":{"name":"2012 Ninth Conference on Computer and Robot Vision","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125965355","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：