{"title":"Direction Adaptive Super-Resolution Imaging","authors":"E. Turgay, G. Akar","doi":"10.1109/SIU.2009.5136326","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136326","url":null,"abstract":"In this paper a novel edge-preserving super-resolution (SR) image reconstruction method is proposed. The proposed maximum a-posteriori (MAP) based estimator uses gradient direction and amount for optimal noise reduction while preserving the edges. Compared to the other edge-preserving methods, the proposed algorithm uses the gradient direction for optimum regularization. The proposed method estimates gradient amplitude and direction at each iteration. This gradient map guides the SR reconstruction stage through iterations. Proposed method is compared against other traditional super resolution methods. Peak-signal-to-noise-ratio (PSNR) measures and illustrations clearly show that the proposed method is successful especially on edge structures in images.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"280 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133505637","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}
{"title":"Automatic point matching and robust fundamental matrix estimation for hybrid camera scenarios","authors":"Y. Bastanlar, A. Temi̇zel, Y. Yardimci","doi":"10.1109/SIU.2009.5136361","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136361","url":null,"abstract":"In this paper, we propose a method to estimate the fundamental matrix for hybrid cameras robustly. In our study a catadioptric omnidirectional camera and a perspective camera were used to obtain hybrid image pairs. For automatic feature point matching, we employed Scale Invariant Feature Transform (SIFT) and improved matching results with the proposed image preprocessing. We also performed matching using virtual camera plane (VCP) images, which are unwarped from the omnidirectional image and carries perspective image properties. Although both approaches are able to produce succesful results, we observed that VCP-perspective matching is more robust to increasing baseline when compared to direct omnidirectional-perspective matching. We implemented RANSAC based on the hybrid epipolar geometry which enables robust estimation of the fundamental matrix as well as elimination of false matches.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132163709","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}
{"title":"Localization in underwater sensor networks","authors":"M. Erol, S. Oktug","doi":"10.1109/SIU.2009.5136324","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136324","url":null,"abstract":"Applications of Underwater Sensors Networks (USN) include environmental ocean/sea monitoring, underwater mine searching, detection of chemically/biologically harmful substances or pollutants, autonomous underwater attack/defense systems, collecting ambient data for ship navigation, etc. The success of terrestrial sensor networks has promising results for more challenging environments, such as underwater. Using groups of sensors communicating with each other yields better performance in underwater applications rather than single sensor equipments. However, forming a network in underwater is not straightforward. The main challenges arise from the physical communication medium and affect the upper protocol stack such as MAC, routing, transport layer protocols and localization. For USNs, protocols at all those layers should be designed with communication and energy cost in mind. Localization is required for data tagging. In terrestrial sensor networks, either GPS is used wherever available or several GPS-free, messaging-intensive schemes have been used. However, both are unsuitable for USNs. In this paper, we compare the performance of two distributed localization methods tailored for large-scale USNs.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132811936","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}
{"title":"Grey clustering based diagnosis of induction motor faults","authors":"Mehmet Saman, I. Aydin, E. Akin","doi":"10.1109/SIU.2009.5136332","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136332","url":null,"abstract":"In this paper, a fault classification method based on grey clustering is proposed for fault detection of induction motors. The amplitudes of rotor frequency related sideband components obtained through fourier transform of one phase stator current are used for broken rotor bar faults. Park's vector components are extracted from three phase motor currents and then new feature is obtained using principal component analysis on park vector components. Obtained features constitute the inputs of grey clustering algorithm. One broken rotor bar, stator faults and stator and multiple faults are diagnosed.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133018407","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}
{"title":"The analyzing of the variations of electric fields and boundary conditions in the interface of a double step-index waveguide","authors":"M. Temiz, M. Unal","doi":"10.1109/SIU.2009.5136513","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136513","url":null,"abstract":"In this work, the boundary conditions are investigated in terms of the normalized propagation constant α in TE mode in a double step-index waveguide. Obtaining these boundary conditions, the variations of the electric field waves for the regions of the double step-index waveguide are given schematically for four cases.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114622603","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}
{"title":"Ship classification by sound signature","authors":"Idris Aykun, M. Karsligil","doi":"10.1109/SIU.2009.5136342","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136342","url":null,"abstract":"Nowadays, either for supervision or for defense purposes, the transportation is being controlled by RADAR (Radio Detecting and Ranging). RADAR helps us get information about objects of interest by transmitting electromagnetic radio waves to the target and analyzing the reflecting signals. We understand that in order to determine any given object's information (speed, distance etc) the first action is always taken by the control center. This also tells us that the moving object can also notice the electromagnetic radio waves and hence the control center can also be sensed.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114723583","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}
{"title":"Diagnosis of Alzheimer's disease from MR images using relevance feedback","authors":"C.B. Akgul, D. Unay, A. Ekin","doi":"10.1109/SIU.2009.5136500","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136500","url":null,"abstract":"In this work, we present a learning framework to help early diagnosis of Alzheimer's disease (AD) from magnetic resonance images. Our approach relies on a nearest neighbor (NN) procedure where the similarity measure is obtained via on-line supervised learning. We propose two alternative approaches to learn the similarities between cases. Several experiments on OASIS database establish that, even with weak global visual descriptors and small training sets, this framework has better diagnostic performance than standard classification based approaches and enjoys a certain degree of robustness against incorrect relevance judgments.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114988778","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}
{"title":"Blur estimation and superresolution from multiple registered images","authors":"Engin Utku Senses, ilkay Ulusoy","doi":"10.1109/SIU.2009.5136482","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136482","url":null,"abstract":"In this study, a superresolution method using registered, noisy and down sampled images is presented. Maximum a Posteriori (MAP) method, one of the statistical pixel domain approaches, is used as the superresolution algorithm. Performances of different data fidelity terms and regularization terms used in the literature are shown. In most of the applications the effects that degrade the image frame are assumed to be known completely or known limited. In this application, the performances of the several methods used to find the amount of blur caused by the unfocussed camera lenses are shown and the best method results are used in the superrresolution algorithm. In this way, the error value of superresolved image is decreased.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"25 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131859700","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}
{"title":"Recursive geolocation with Time Differences of Arrival","authors":"Sedat Camlica, Y. Tanik","doi":"10.1109/SIU.2009.5136539","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136539","url":null,"abstract":"Geolocation has particular interest and importance in Electronic Warfare. In this work, Time Difference of Arrival (TDOA) Geolocation is studied. A recursive least squares filter based algorithm has been developed. Location estimation is updated using TDOA measurement sets from moving receivers under the assumption of fixed emitter location. Moreover, simulation results and comments are given at the end of the text.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"220 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132292407","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}
{"title":"Color and shape based traffic sign detection","authors":"Emre Ulay, G. Akar, M. M. Bulut","doi":"10.1109/SIU.2009.5136365","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136365","url":null,"abstract":"This paper proposes two different methods in order to improve the performance of traffic sign detection process. These methods are used for efficient and robust detection of red or blue colored, circular, octagonal, rectangular and triangular traffic signs. Proposed methods use both color and shape features of the traffic signs. Both of the methods gather the color and edge information of the image in order to form a search domain for the shape based detection algorithm. The main difference between the methods appears in the fusion process of color and shape features of the gathered images. Although methods employ different algorithms for color segmentation, they both use HSV color domain. Tests on static images show improvement especially on false positive and detection rate.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128600094","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}