Denna rapport beskriver styrbeteenden för autonoma agenter och utvärderar hur användbar den tekniken är för att skapa flexibla agenter i kontinuerliga miljöer. Arbetet undersöker hur väl det går att använda styrbeteenden i en mer strikt kontrollerad miljö, nämligen biltrafik. De utvecklade agenterna agerar i en trafikmiljö där de navigerar för att följa en väg och undvika kollisioner med andra agenter. Agenterna använder en kombineringsarkitektur som gör det möjligt att använda olika beräkningsmodeller. Agenterna är testade i två scenarion där teknikens användbarhet och flexibilitet är studerad. Resultatet från utvärderingen visar att tekniken är väldigt flexibel men kan kräva mycket finjustering för att uppnå bästa resultat.

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.

Industrial applications of computer vision often utilize traditional image processing techniques whereas state-of-the-art methods in most image processing challenges are almost exclusively based on convolutional neural networks (CNNs). Thus there is a large potential for improving the performance of many machine vision applications by incorporating CNNs. One such application is the classification of juice boxes with straws, where the baseline solution uses classical image processing techniques on depth images to reject or accept juice boxes. This thesis aim to investigate how CNNs perform on the task of semantic segmentation (pixel-wise classification) of said images and if the result can be used to increase classification performance. A drawback of CNNs is that they usually require large amounts of labelled data for training to be able to generalize and learn anything useful. As labelled data is hard to come by, two ways to get cheap data are investigated, one being synthetic data generation and the other being automatic labelling using the baseline solution. The implemented network performs well on semantic segmentation, even when trained on synthetic data only, though the performance increases with the ratio of real (automatically labelled) to synthetic images. The classification task is very sensitive to small errors in semantic segmentation and the results are therefore not as good as the baseline solution. It is suspected that the drop in performance between validation and test data is due to a domain shift between the data sets, e.g. variations in data collection and straw and box type, and fine-tuning to the target domain could definitely increase performance. When trained on synthetic data the domain shift is even larger and the performance on classification is next to useless. It is likely that the results could be improved by using more advanced data generation, e.g. a generative adversarial network (GAN), or more rigorous modelling of the data.

Generic visual tracking is one of the classical problems in computer vision. In this problem, no prior knowledge of the target is available aside from a bounding box in the initial frame of the sequence. The generic visual tracking is a difficult task due to a number of factors such as momentary occlusions, target rotations, changes in target illumination and variations in the target size. In recent years, discriminative correlation filter (DCF) based trackers have shown promising results for visual tracking. These DCF based methods use the Fourier transform to efficiently calculate detection and model updates, allowing significantly higher frame rates than competing methods. However, existing DCF based methods only estimate translation of the object while ignoring changes in size.This thesis investigates the problem of accurately estimating the scale variations within a DCF based framework. A novel scale estimation method is proposed by explicitly constructing translation and scale filters. The proposed scale estimation technique is robust and significantly improve the tracking performance, while operating at real-time. In addition, a comprehensive evaluation of feature representations in a DCF framework is performed. Experiments are performed on the benchmark OTB-2015 dataset, as well as the VOT 2014 dataset. The proposed methods are shown to significantly improve the performance of existing DCF based trackers. / Allmän visuell följning är ett klassiskt problem inom datorseende. I den vanliga formuleringen antas ingen förkunskap om objektet som skall följas, utöver en initial rektangel i en videosekvens första bild.Detta är ett mycket svårt problem att lösa allmänt på grund av occlusioner, rotationer, belysningsförändringar och variationer i objektets uppfattde storlek. På senare år har följningsmetoder baserade på diskriminativea korrelationsfilter gett lovande resultat inom området. Dessa metoder är baserade på att med hjälp av Fourertransformen effektivt beräkna detektioner och modellupdateringar, samtidigt som de har mycket bra prestanda och klarar av många hundra bilder per sekund. De nuvarande metoderna uppskattar dock bara translationen hos det följda objektet, medans skalförändringar ignoreras. Detta examensarbete utvärderar ett antal metoder för att göra skaluppskattningar inom ett korrelationsfilterramverk. En innovativ metod baserad på att konstruera separata skal och translationsfilter. Den föreslagna metoden är robust och har signifikant bättre följningsprestanda, samtidigt som den kan användas i realtid. Det utförs också en utvärdering av olika särdragsrepresentationer på två stora benchmarking dataset för följning.

Integrated camera systems for increasing safety and maneuverability are becoming increasingly common for heavy vehicles. One problem with heavy vehicles today is that there are blind spots where the driver has no or very little view. There is a great demand on increasing the safety and helping the driver to get a better view of his surroundings. This can be achieved by a sophisticated camera system, using cameras with wide field of view, that could cover dangerous blind spots. This master thesis aims to investigate and develop a prototype solution for a camera system consisting of two fisheye cameras. The solution covers both hardware choices and software development including camera calibration and image stitching. Two different fisheye camera calibration toolboxes are compared and their results discussed, with the aim to find the most suitable for this application. The result from the two toolboxes differ in performance, and the result from only one of the toolboxes is sufficient for image stitching.

Anomaly detection is a general theory of detecting unusual patterns or events in data. This master thesis investigates the subject of anomaly detection in two different applications. The first application is product inspection using a camera and the second application is surveillance using a 2D laser scanner. The first part of the thesis presents a system for automatic visual defect inspection. The system is based on aligning the images of the product to a common template and doing pixel-wise comparisons. The system is trained using only images of products that are defined as normal, i.e. non-defective products. The visual properties of the inspected products are modelled using three different methods. The performance of the system and the different methods have been evaluated on four different datasets. The second part of the thesis presents a surveillance system based on a single laser range scanner. The system is able to detect certain anomalous events based on the time, position and velocities of individual objects in the scene. The practical usefulness of the system is made plausible by a qualitative evaluation using unlabelled data.