<p>This thesis is about channel-coded feature maps applied in view-based object recognition, tracking, and machine learning. A channel-coded feature map is a soft histogram of joint spatial pixel positions and image feature values. Typical useful features include local orientation and color. Using these features, each channel measures the co-occurrence of a certain orientation and color at a certain position in an image or image patch. Channel-coded feature maps can be seen as a generalization of the SIFT descriptor with the options of including more features and replacing the linear interpolation between bins by a more general basis function.</p><p>The general idea of channel coding originates from a model of how information might be represented in the human brain. For example, different neurons tend to be sensitive to different orientations of local structures in the visual input. The sensitivity profiles tend to be smooth such that one neuron is maximally activated by a certain orientation, with a gradually decaying activity as the input is rotated.</p><p>This thesis extends previous work on using channel-coding ideas within computer vision and machine learning. By differentiating the channel-coded feature maps with respect to transformations of the underlying image, a method for image registration and tracking is constructed. By using piecewise polynomial basis functions, the channel coding can be computed more efficiently, and a general encoding method for N-dimensional feature spaces is presented.</p><p>Furthermore, I argue for using channel-coded feature maps in view-based pose estimation, where a continuous pose parameter is estimated from a query image given a number of training views with known pose. The optimization of position, rotation and scale of the object in the image plane is then included in the optimization problem, leading to a simultaneous tracking and pose estimation algorithm. Apart from objects and poses, the thesis examines the use of channel coding in connection with Bayesian networks. The goal here is to avoid the hard discretizations usually required when Markov random fields are used on intrinsically continuous signals like depth for stereo vision or color values in image restoration.</p><p>Channel coding has previously been used to design machine learning algorithms that are robust to outliers, ambiguities, and discontinuities in the training data. This is obtained by finding a linear mapping between channel-coded input and output values. This thesis extends this method with an incremental version and identifies and analyzes a key feature of the method -- that it is able to handle a learning situation where the correspondence structure between the input and output space is not completely known. In contrast to a traditional supervised learning setting, the training examples are groups of unordered input-output points, where the correspondence structure within each group is unknown. This behavior is studied theoretically and the effect of outliers and convergence properties are analyzed.</p><p>All presented methods have been evaluated experimentally. The work has been conducted within the cognitive systems research project COSPAL funded by EC FP6, and much of the contents has been put to use in the final COSPAL demonstrator system.</p>

<p>This Master Thesis has been conducted at the National Laboratory of Forensic Science (SKL) in Linköping. When images that are to be analyzed at SKL, presenting an interesting object, are of bad quality there may be a need to enhance them. If several images with the object are available, the total amount of information can be used in order to estimate one single enhanced image. A program to do this has been developed by studying methods for image registration and high resolution image estimation. Tests of important parts of the procedure have been conducted. The final results are satisfying and the key to a good high resolution image seems to be the precision of the image registration. Improvements of this part may lead to even better results. More suggestions for further improvementshave been proposed.</p> / <p>Detta examensarbete har utförts på uppdrag av Statens Kriminaltekniska Laboratorium (SKL) i Linköping. Då bilder av ett intressant objekt som ska analyseras på SKL ibland är av dålig kvalitet finns det behov av att förbättra dessa. Om ett flertal bilder på objektet finns tillgängliga kan den totala informationen fråndessa användas för att skatta en enda förbättrad bild. Ett program för att göra detta har utvecklats genom studier av metoder för bildregistrering och skapande av högupplöst bild. Tester av viktiga delar i proceduren har genomförts. De slutgiltiga resultaten är goda och nyckeln till en bra högupplöst bild verkar ligga i precisionen för bildregistreringen. Genom att förbättra denna del kan troligtvis ännu bättre resultat fås. Även andra förslag till förbättringar har lagts fram.</p>

<p>This report present a working model for simulation of what happens to colors displayed on screens when they are observed through optical filters. The results of the model can be used to visually, on one screen, simulate another screen with an applied optical filter. The model can also produce CIE color difference values for the simulated screen colors. The model is data driven and requires spectral measurements for at least the screen to be simulated and the physical filters that will be used. The model is divided into three separate modules or steps where each of the modules can be easily replaced by alternative implementations or solutions. Results from tests performed show that the model can be used for prototyping of optical filters even though the tests of the specific algorithms chosen show there is room for improvements in quality. There is nothing that indicates that future work with this model would not produce better quality in its results.</p> / <p>Denna rapport presenterar en fungerande modell för att optiskt simulera vad som händer med färger på bildskärmar då skärmarna betraktas genom optiska filter. Resultat från modellen består av information som kan användas för visuell simulering av en skärm med applicerat filter på en annan visande skärm. Förutom ren bilddata kan modellen även producera färgskillnadsvärden som kan härledas från CIE 1931 XYZ-koordinater. Modellen är datadriven och kräver initiala mätningar på minst den skärm som ska simuleras samt filter. Hela modellen är uppdelad i tre separata moduler eller steg där de olika delarna lätt kan bytas ut för alternativa algoritmer och lösningar. Resultat från undersökningar visar på att modellen går att använda för prototypning även om de, för arbetet specifikt, valda algoritmerna för de olika stegen i undersökningen visar på brister i kvalité. Det finns inget som visar att framtida arbete där andra algoritmer valts inte skulle kunna prestera ännu bättre resultat.</p>

<p>A laser-triangulating range camera uses a laser plane to light an object. If the position of the laser relative to the camera as well as certrain properties of the camera is known, it is possible to calculate the coordinates for all points along the profile of the object. If either the object or the camera and laser has a known motion, it is possible to combine several measurements to get a three-dimensional view of the object.</p><p>Camera calibration is the process of finding the properties of the camera and enough information about the setup so that the desired coordinates can be calculated. Several methods for camera calibration exist, but this thesis proposes a new method that has the advantages that the objects needed are relatively inexpensive and that only objects in the laser plane need to be observed. Each part of the method is given a thorough description. Several mathematical derivations have also been added as appendices for completeness.</p><p>The proposed method is tested using both synthetic and real data. The results show that the method is suitable even when high accuracy is needed. A few suggestions are also made about how the method can be improved further.</p>

<p>Motion capture is the process of capturing movements from real life into a computer. Existing motion capture systems are often very expensive and require advanced hardware that makes the process complex. This thesis will answer the following question: is it possible to create an optical motion capture system using only a single low cost Dvcamera (Digital Video Camera), that still will produce accurate motion capture data? To answer this question and construct our motion capture system we need to complete these following steps:</p><p>• Create a usable film sequence.</p><p>• Analyze the sequence.</p><p>• Create motion capture data.</p><p>• Apply the motion capture data for 3D character and analyze the outcome.</p><p>The method chosen for this thesis is constructive research. In short terms it is the study of whether we can or cannot build a new artifact. The following theoretic tools were used in the process of creating a motion capture system: Color theory, RGB, Connected component labeling, Skeletons in 3D animation, Calculating angels using trigonometry, .x files and Quaternions. We have found that an optical motion capture system is very complex and it is hard to produce as a low budget system. Our attempt did not live up to our expectations. The idea with using only one DV camera was to simplify the system since it would require no calibration or syncronisation. It would also make the system cost efficient and more available to the general public. The single camera solution unfortunatly created a number of problems in our system. Our system does however work with less complex movements. It can produce motion capture data that is accurate enough to be used in low budget games. It is also cost effective compared to other systems on the market. The system has a very easy setup and does not need any calibration in addition to the init position.</p>

Thesis (Ph. D.)--University of Missouri-Columbia, 2001. / Typescript. Vita. Includes bibliographical references (leaves 116-119). Also available on the Internet.

Thesis (Ph. D.)--University of Missouri-Columbia, 2001. / Typescript. Vita. Includes bibliographical references (leaves 116-119). Also available on the Internet.

Thesis (Ph. D.)--University of California, Riverside, 2009. / Includes abstract. Title from first page of PDF file (viewed January 27, 2010). Includes bibliographical references (p. 99-105). Issued in print and online. Available via ProQuest Digital Dissertations.

Thesis (Ph. D.)--University of Missouri-Columbia, 2003. / Typescript. Vita. Includes bibliographical references (leaves 135-143). Also available on the Internet.

Thesis (M.S.)--Mississippi State University. Department of Mechanical Engineering. / Title from title screen. Includes bibliographical references.