The increased usage of infrared sensors by pilots has created a growing demand for simulated environments based on infrared radiation. This has led to an increased need for Saab to refine their existing model for simulating real-time infrared imagery, resulting in the carrying through of this thesis. Saab develops the Gripen aircraft, and they provide training simulators where pilots can train in a realistic environment. The new model is required to be based on the real-world behavior of infrared radiation, and furthermore, unlike Saab's existing model, have dynamically changeable attributes. This thesis seeks to develop a simulation model compliant with the requirements presented by Saab, and to develop the implementation of a test environment demonstrating the features and capabilities of the proposed model. All through the development of the model, the pilot training value has been kept in mind. The first part of the thesis consists of a literature study to build a theoretical base for the rest of the work. This is followed by the development of the simulation model itself and a subsequent implementation thereof. The simulation model and the test implementation are evaluated as the final step conducted within the framework of this thesis. The main conclusions of this thesis first of all includes that the proposed simulation model does in fact have its foundation in physics. It is further concluded that certain attributes of the model, such as time of day, are dynamically changeable as requested. Furthermore, the test implementation is considered to have been feasibly integrated with the current simulation environment. A plan concluding how to proceed has also been developed. The plan suggests future work with the proposed simulation model, since the evaluation shows that it performs well in comparison to the existing model as well as other products on the market.

Object recognition is a much studied computer vision problem, where the task is to find a given object in an image. This Master Thesis aims at doing a MATLAB implementation of an object recognition algorithm that finds three kinds of objects in images: electrical outlets, light switches and wall mounted air-conditioning controls. Visually, these three objects are quite similar and the aim is to be able to locate these objects in an image, as well as being able to distinguish them from one another. The object recognition was accomplished using Histogram of Oriented Gradients (HOG). During the training phase, the program was trained with images of the objects to be located, as well as reference images which did not contain the objects. A Support Vector Machine (SVM) was used in the classification phase. The performance was measured for two different setups, one where the training data consisted of photos and one where the training data consisted of digitally generated images created using a 3D modeling software, in addition to the photos. The results show that using digitally generated images as training images didn’t improve the accuracy in this case. The reason for this is probably that there is too little intraclass variability in the gradients in digitally generated images, they’re too synthetic in a sense, which makes them poor at reflecting reality for this specific approach. The result might have been different if a higher number of digitally generated images had been used.

Several automatic methods exist for creating 3D point clouds extracted from 2D photos. In manycases, the result is a sparse point cloud, unevenly distributed over the scene.After determining the coordinates of the same point in two images of an object, the 3D positionof that point can be calculated using knowledge of camera data and relative orientation. A model created from a unevenly distributed point clouds may loss detail and precision in thesparse areas. The aim of this thesis is to study methods for densification of point clouds. This thesis contains a literature study over different methods for extracting matched point pairs,and an implementation of Least Square Template Matching (LSTM) with a set of improvementtechniques. The implementation is evaluated on a set of different scenes of various difficulty. LSTM is implemented by working on a dense grid of points in an image and Wallis filtering isused to enhance contrast. The matched point correspondences are evaluated with parameters fromthe optimization in order to keep good matches and discard bad ones. The purpose is to find detailsclose to a plane in the images, or on plane-like surfaces. A set of extensions to LSTM is implemented in the aim of improving the quality of the matchedpoints. The seed points are improved by Transformed Normalized Cross Correlation (TNCC) andMultiple Seed Points (MSP) for the same template, and then tested to see if they converge to thesame result. Wallis filtering is used to increase the contrast in the image. The quality of the extractedpoints are evaluated with respect to correlation with other optimization parameters and comparisonof standard deviation in x- and y- direction. If a point is rejected, the option to try again with a largertemplate size exists, called Adaptive Template Size (ATS).

3D cameras delivering height data can be used for quality inspection of goods on a conveyor. It is then of interest to distinguish the important parts of the image from background and noise and further to divide these interesting parts into segments that have a strong correlation to objects on the conveyor belt. Segmentation can easily be done by thresholding in the simple case. However, in more complex situations, for example when objects touch or overlap, this does not work well. In this thesis, research and evaluation of a few different methods for segmentation of height image data are presented. The focus is to find an accurate method for segmentation of smooth irregularly shaped organic objects such as vegetables or shellfish. For evaluative purposes a database consisting of height images depicting a variety of such organic objects has been collected. We show in the thesis that a conventional gradient magnitude method is hard to beat in the general case. If, however, the objects to be segmented are heavily non-convex with a lot of crests and valleys within themselves one could be better off choosing a normalized least squares method. / 3D-kameror som levererar höjddata kan användas för kvalitetskontroll av varor på ett löpande band. Det är då av intresse att urskilja de viktiga delarna av bilden från bakgrund och brus samt även att dela upp dessa intressanta delar i segment med stark korrelans till objekten på bandet. Segmentering kan utföras genom tröskling i det enkla fallet. I mer komplexa situationer då objekt vidrör eller överlappar varandra blir det svårare. I detta examensarbete presenteras forskning och utvärdering av några olika metoder för segmentering av höjdbildsdata. Fokus ligger på att finna en noggrann metod för segmentering av mjuka släta oregelbundna objekt som grönsaker och skaldjur. I utvärderingssyfte har en databas bestående höjdbilder föreställande lite olika typer av sådana organiska objekt samlats in. Vi visar i uppstatsen att en konventionell gradientlängdsmetod är svår att slå i det generella fallet. Om objekten som ska segmenteras är kraftigt icke-konvexa å andra sidan, med en mängd krön och dalar inom varje objekt, kan man göra bättre i att välja en normaliserad minstakvadratfelsmetod.

The main purpose of this work is to reconstruct 3D model of an entire scene byusing two ordinary cameras. We develop a mobile phone application, based onstereo vision and image analysis algorithms, executed either locally or on a remotehost, to calculate the dietary intake using the current questionnaire and the mobilephone photographs. The information of segmented 3D models are used to calculatethe volume -and then the calories- of a person’s daily intake food. The method ischecked using different solid food samples, in different camera arrangements. Theresults shows that the method successfully reconstructs 3D model of different foodsample with high details.

Within this thesis an algorithm for object recognition called Cluster Matching has been developed, implemented and evaluated. The image information is sampled at arbitrary sample points, instead of interest points, and local image features are extracted. These sample points are used as a compact representation of the image data and can quickly be searched for prior known objects. The algorithm is evaluated on a test set of images and the result is surprisingly reliable and time efficient.

3D Models of botanical trees are very important in video games, simulation, virtual reality, digital city modeling and other fields of computer graphics. However, since the early days of computer graphics, the modeling of trees has been challenging, because of the huge dynamical range between its smallest and largest structures and their geometrical complexity. Trees are also ubiquitous which makes it even hard to model them in a realistic way, Current techniques are limited in that they model a tree either in a rule-based way or in an approximated way. These methods emphasize appearance while sacrificing its real structure. Recent development in range scanners are making 3D aquisition feasible for large and complex objects. This report presents the semi-automatic technique developed for modeling laser-scanned trees. First, the user draws a few strokes on the depth image plane generated from the dataset. Branches are then extracted through the 2D Curve detection algorithm originally developed. Afterwards, those short branches are connected together to generate the skeleton of the tree by forming a Minimum Spanning Tree (MST). Finally, the geometry of the tree skeleton is produced using allometric rules for branch thickness and branching angles.

In this thesis an algorithm for producing saliency maps as well as an algorithm for detecting salient regions based on the saliency map was developed. The saliency values are computed as center-surround differences and a local descriptor called the region p-channel is used to represent center and surround respectively. An integral image representation called the integral p-channel is used to speed up extraction of the local descriptor for any given image region. The center-surround difference is calculated as either histogram or p-channel dissimilarities. Ground truth was collected using human subjects and the algorithm’s ability to detect salient regions was evaluated against this ground truth. The algorithm was also compared to another saliency algorithm. Two different center-surround interpretations are tested, as well as several p-channel and histogram dissimilarity measures. The results show that for all tested settings the best performing dissimilarity measure is the so called diffusion distance. The performance comparison showed that the algorithm developed in this thesis outperforms the algorithm against which it was compared, both with respect to region detection and saliency ranking of regions. It can be concluded that the algorithm shows promising results and further investigation of the algorithm is recommended. A list of suggested approaches for further research is provided.

Methods for measuring deformation and motion of the human heart in-vivo are crucial in the assessment of cardiac function. Applications ranging from basic physiological research, through early detection of disease to follow-up studies, all benefit from improved methods of measuring the dynamics of the heart. This thesis presents new methods for acquisition, reconstruction and visualization of cardiac motion and deformation, based on magnetic resonance imaging. Local heart wall deformation can be quantified in a strain rate tensor field. This tensor field describes the local deformation excluding rigid body translation and rotation. The drawback of studying this tensor-valued quantity, as opposed to a velocity vector field, is the high dimensionality of the tensor. The problem of visualizing the tensor field is approached by combining a local visualization that displays all degrees of freedom for a single tensor with an overview visualization using a scalar field representation of the complete tensor field. The scalar field is obtained by iterated adaptive filtering of a noise field. Several methods for synchronizing the magnetic resonance imaging acquisition to the heart beat have previously been used to resolve individual heart phases from multiple cardiac cycles. In the present work, one of these techniques is extended to resolve two temporal dimensions simultaneously, the cardiac cycle and the respiratory cycle. This is combined with volumetric imaging to produce a five-dimensional data set. Furthermore, the acquisition order is optimized in order to reduce eddy current artifacts. The five-dimensional acquisition either requires very long scan times or can only provide low spatiotemporal resolution. A method that exploits the variation in temporal bandwidth over the imaging volume, k-t BLAST, is described and extended to two simultaneous temporal dimensions. The new method, k-t2 BLAST, allows simultaneous reduction of scan time and improvement of spatial resolution.

The possibility to use real-time computer vision in video sequences gives many opportunities for a system to interact with the environment. Possible ways for interaction are e.g. augmented reality like in the MATRIS project where the purpose is to add new objects into the video sequence, or surveillance where the purpose is to find abnormal events. The increase of the speed of computers the last years has simplified this process and it is now possible to use at least some of the more advanced computer vision algorithms that are available. The computational speed of computers is however still a problem, for an efficient real-time system efficient code and methods are necessary. This thesis deals with both problems, one part is about efficient implementations using single instruction multiple data (SIMD) instructions and one part is about robust tracking. An efficient real-time system requires efficient implementations of the used computer vision methods. Efficient implementations requires knowledge about the CPU and the possibilities given. In this thesis, one method called SIMD is explained. SIMD is useful when the same operation is applied to multiple data which usually is the case in computer vision, the same operation is executed on each pixel. Following the position of a feature or object in a video sequence is called tracking. Tracking can be used for a number of applications. The application in this thesis is to use tracking for pose estimation. One way to do tracking is to cut out a small region around the feature, creating a patch and find the position on this patch in the other frames. To find the position, a measure of the difference between the patch and the image in a given position is used. This thesis thoroughly investigates the sum of absolute difference (SAD) error measure. The investigation involves different ways to improve the robustness and to decrease the average error. One method to estimate the average error, the covariance of the position error is proposed. An estimate of the average error is needed when different measurements are combined. Finally, a system for camera pose estimation is presented. The computer vision part of this system is based on the result in this thesis. This presentation contains also a discussion about the result of this system. / Report code: LIU-TEK-LIC-2007:5. The report code in the thesis is incorrect.