{"title":"Models and Algorithms for Detection and Tracking of Coordinated Groups","authors":"S. K. Pang, Jack Li, S. Godsill","doi":"10.1109/AERO.2008.4526445","DOIUrl":"https://doi.org/10.1109/AERO.2008.4526445","url":null,"abstract":"In this paper, we describe a set of models and algorithms for detection and tracking of group and individual targets. We develop a novel group dynamical model within a continuous time setting and a group structure transition model. This is combined with an interaction model using Markov Random Fields (MRF) to create a realistic group model. We use a Markov Chain Monte Carlo (MCMC)-Particle Algorithm to perform the sequential inference. Computer simulations demonstrate the ability of the algorithm to detect and track targets, as well as infer the correct group structure.","PeriodicalId":112420,"journal":{"name":"2007 5th International Symposium on Image and Signal Processing and Analysis","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117320507","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}
B. Bijnens, P. Claus, C. Parsai, M. Čikeš, S. Lončarić, L. Anderson, G. Sutherland
{"title":"An integrated framework for the assessment of cardiac function - Description and illustrated applications","authors":"B. Bijnens, P. Claus, C. Parsai, M. Čikeš, S. Lončarić, L. Anderson, G. Sutherland","doi":"10.1109/ISPA.2007.4383714","DOIUrl":"https://doi.org/10.1109/ISPA.2007.4383714","url":null,"abstract":"Assessing myocardial function is a difficult task in clinical practice. Routinely, (systolic) cardiac function is mostly quantified based on ejection fraction, a measure of the volume fraction of the left ventricle being ejected with each cardiac cycle. However, this approach has a lot of limitations since normal ejection fraction can occur while there are clearly functional abnormalities, while a reduced value does not say anything about what is wrong with the heart muscle. Recently, echocardiographic strain (-rate) imaging has been introduced, enabling the regional quantification of myocardial deformation. However, local deformation is also influenced by a number of factors and therefore does not necessarily represent local contractile force development. In this paper, we present an integrated framework, describing intrinsic cardiac function in its relationship with the boundary conditions. To illustrate how this framework can be used to study and understand cardiac function, two applications are discussed (regional ischemia and left bundle branch block). These applications are illustrated with simulations of regional deformation profiles.","PeriodicalId":112420,"journal":{"name":"2007 5th International Symposium on Image and Signal Processing and Analysis","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122210857","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}
David Excell, A. Taylan Cemgil, William J. Fitzgerald
{"title":"Generative Model for Human Motion Recognition","authors":"David Excell, A. Taylan Cemgil, William J. Fitzgerald","doi":"10.1109/ISPA.2007.4383731","DOIUrl":"https://doi.org/10.1109/ISPA.2007.4383731","url":null,"abstract":"This paper describes a generative Bayesian model designed to track an articulated 3D human skeleton in an image sequence. The model infers the subjects appearance, pose, and movement. This technique provides a novel method for implicity modelling depth and self occlusion, two issues that have been identified as drawbacks of existing models. We also employ a switching linear dynamical system to efficiently propose skeleton configurations. The model is verified using synthetic data. A video clip from the Caviar data set is used to demonstrate the potential of the methodology for tracking on real data.","PeriodicalId":112420,"journal":{"name":"2007 5th International Symposium on Image and Signal Processing and Analysis","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128589463","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":"New Scene-Based Nonuniformity Correction Algorithm of Infrared Focal-Plane Arrays","authors":"Yong-jin Liu, Hong Zhu, Yi-gong Zhao","doi":"10.1109/ISPA.2007.4383704","DOIUrl":"https://doi.org/10.1109/ISPA.2007.4383704","url":null,"abstract":"The technique for nonuniformity correction in infrared focal-plane arrays is a typical blind-estimation problem, and the infrared images without noises are not available. In order to correct the observed images in the presence of the fixed-pattern noise caused by pixel-to-pixel nonuniformity, it is necessary to estimate the corresponding true scene values. A new scene-based nonuniformity correction algorithm is developed, which can use the interframe-prediction technique to achieve the estimates of true scene values. Therefore, we can predict the true value of the next uncorrected frame through the current corrected one. With these scene estimates and the corresponding observed values through a given array, a line-fitting procedure is used to estimate the individual detector response parameters, which can then be used to correct the nonuniformity. Thus, with a frame-by-frame iteration, the response parameters will converge to the optimum values. The strength of the algorithm lies in its high convergent speed despite the level of nonuniformity, and its ability of reducing ghosting artifacts is noticeable. The performance of the algorithm is demonstrated by the use of an ideal infrared image sequence with simulated nonuniformity and an actual infrared image sequence with real nonuniformity.","PeriodicalId":112420,"journal":{"name":"2007 5th International Symposium on Image and Signal Processing and Analysis","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129261831","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}
E. Ceyhan, L. Fong, T. Tasky, M. Hurdal, M. Beg, M. Martone, J. Ratnanather
{"title":"Type-Specific Analysis of Morphometry of Dendrite Spines of Mice","authors":"E. Ceyhan, L. Fong, T. Tasky, M. Hurdal, M. Beg, M. Martone, J. Ratnanather","doi":"10.1109/ISPA.2007.4383655","DOIUrl":"https://doi.org/10.1109/ISPA.2007.4383655","url":null,"abstract":"In this article, we analyze the morphometric measures of dendrite spines of mice derived from electron tomography images for different spine types based on pre-assigned categories. The morphometric measures we consider include the metric distance, volume, surface area, and length of dendrite spines of mice. The question of interest is how these morphometric measures differ by condition of mice; and how the metric distance relates to volume, surface area, length, and condition of mice. The large deformation diffeomorphic metric mapping algorithm is the tool we use to obtain the metric distances that quantize the morphometry of binary images of dendrite spines with respect to a template spine. We demonstrate that for the values not adjusted for scale metric distances and other morphometric measures are significantly different between the conditions. The morphometric measures (rather than the mice condition) explain almost all the variation in metric distances. Since size (or scale) dominates the other variables in variation, we adjust metric distances and other morphometric measures for scale. We demonstrate that the scaled metric distances and other scaled morphometric variables still differ for condition, and scaled metric distances depend most significantly on scaled morphometric measures. The methodology used is also valid for morphometric measures of other organs or tissues and metric distances other than LDDMM.","PeriodicalId":112420,"journal":{"name":"2007 5th International Symposium on Image and Signal Processing and Analysis","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130383105","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":"Narrow band region approach for active contours and surfaces","authors":"J. Mille, R. Boné, P. Makris, H. Cardot","doi":"10.1109/ISPA.2007.4383682","DOIUrl":"https://doi.org/10.1109/ISPA.2007.4383682","url":null,"abstract":"We introduce a narrow band region approach for explicit deformable models in the perspective of 2D and 3D image segmentation. Embedding a region term into the evolution process, we derive a general framework which is applied both on a 2D parametric contour and a 3D triangular mesh. Evolution of deformable models is performed by means of energy minimization using the computationally efficient greedy algorithm. The use of a region energy related to the vicinity of the evolving surface overcomes limitations of edge-based active models while remaining time effective. Experiments with segmentation quality assessment are carried out on medical data sets.","PeriodicalId":112420,"journal":{"name":"2007 5th International Symposium on Image and Signal Processing and Analysis","volume":"217 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123358466","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":"Real-time Finger Tracking for Interaction","authors":"N. Shaker, M. Abou Zliekha","doi":"10.1109/ISPA.2007.4383679","DOIUrl":"https://doi.org/10.1109/ISPA.2007.4383679","url":null,"abstract":"In this work, we describe an approach for human finger motion and gesture detection using two cameras. The target of pointing on a flat monitor or screen is identified using image processing and line intersection. This is accomplished by processing above and side images of the hand. The system is able to track the finger movement without building the 3D model of the hand. Coordinates and movement of the finger in a live video feed can be taken to become the coordinates and movement of the mouse pointer for human-computer interaction purpose.","PeriodicalId":112420,"journal":{"name":"2007 5th International Symposium on Image and Signal Processing and Analysis","volume":"33 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114117976","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":"Basic Linear Filters in Extracting of Auditory Evoked Potentials","authors":"S. Aydin","doi":"10.1109/ISPA.2007.4383698","DOIUrl":"https://doi.org/10.1109/ISPA.2007.4383698","url":null,"abstract":"The aim of this study is to assess the performance of additivity-based linear filtering techniques into two groups in extracting of auditory evoked potentials (EPs) from a relatively small number of sweeps. We named these groups as: Group A (the Wiener filtering (WF) and coherence weighted WF (CWWF) of orthogonal projections) and Group B (standard adaptive algorithms of Least Mean Square (LMS), Recursive Least Square (RLS), and one-step Kalman filtering (KF)). All methods are compared to the traditional ensemble averaging (EA) in simulations, pseudo-simulations and experimental studies based on the signal-to-noise-ratio (SNR) enhancement. We observed that the KF is the best methods among them. The filtering of the projections instead of the raw data improves the performance of filtering operations in both cases of the LMS and WF. The CWWF works better than the conventional WF when it is applied to the projections as well. In conclusion, most of the linear filters show definitely better performance compared to EA. The KF effectively reduce the experimental time (to one-fourth of that required by EA). The projection method so called Subspace Method (SM) in the current study is a useful pre-filter to significantly reduce the noise on the raw data. The use of the SM is revealed in auditory EP estimation. The SM improves the performance of different algorithms.","PeriodicalId":112420,"journal":{"name":"2007 5th International Symposium on Image and Signal Processing and Analysis","volume":"35 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113959493","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":"Real Time Motion Tracking by Seismic Wave Analysis","authors":"J. Diaz, O. Hernandez","doi":"10.1109/ISPA.2007.4383661","DOIUrl":"https://doi.org/10.1109/ISPA.2007.4383661","url":null,"abstract":"Acoustic source localization has been considered a great point of focus in order to solve a wide range of applications, including detection, tracking and even source classification. In surveillance applications there are different types of sensors used to provide many approaches to the problem of source localization. In this application we use arrays of seismic sensors which provide a reliable sensing solution to the problem of real time object tracking by analyzing the waves the object generates while it moves over the ground. The aim of this work is to provide the position in real time of an object moving over a designated area on a soccer field, using arrays of geophones connected to a dual core development kit called DIOPSIS 740, which comprises of a DSP and a microcontroller. The DSP is able to process 1 Gflops @ 1 MHz and counts with 4 stereo analog inputs suitable for this application. The geometry of the array and different algorithms used to determine the direction of arrival (DOA) were also matter of analysis in this work to finally implement a pair of uniform linear arrays and an algorithm based on time-delay estimation for the source tracking.","PeriodicalId":112420,"journal":{"name":"2007 5th International Symposium on Image and Signal Processing and Analysis","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128100958","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":"A New Spatio-Temporal Fast Motion Estimation Algorithm","authors":"V. Fotopoulos, A. Skodras","doi":"10.1109/ISPA.2007.4383742","DOIUrl":"https://doi.org/10.1109/ISPA.2007.4383742","url":null,"abstract":"A new spatio-temporal approach is proposed for fast block motion estimation in video coding. The approach exploits the existing correlation of the spatio- temporal block neighborhood by utilizing the frequency of appearance of the neighborhood's motion vectors. Extensive simulations show that the proposed algorithm performs close to the full search algorithm (in terms of quality) with a significant computational gain. Under fine tuning of specific parameters, the algorithm becomes comparable to other fast search algorithms.","PeriodicalId":112420,"journal":{"name":"2007 5th International Symposium on Image and Signal Processing and Analysis","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131969513","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}