In this thesis, we address the problem of panoramic scene construction in which a single image covering the entire visible area of the scene is constructed from an aerial image video. In the literature, there are several algorithms developed for construction of panoramic scene of a video sequence. These algorithms can be categorized as feature based and featureless algorithms. In this thesis, we concentrate on the feature based algorithms and comparison of these algorithms is performed for aerial videos. The comparison is performed on video sequences captured by non-stationary cameras, whose optical axis does not have to be the same. In addition, the matching and tracking performances of the algorithms are separately analyzed, their advantages-disadvantages are presented and several modifications are proposed.

Perception, hence the usage of visual sensors is indispensable in mobile and autonomous robotics. Visual sensors such as cameras, rigidly mounted on a robot frame are the most common usage scenario. In this case, the motion of the camera due to the motion of the moving platform as well as the resulting shocks or vibrations causes a number of distortions on video frame sequences. Two most important ones are the frame-to-frame changes of the line-of-sight (LOS) and the presence of motion blur in individual frames. The latter of these two, namely motion blur plays a particularly dominant role in determining the performance of many vision algorithms used in mobile robotics. It is caused by the relative motion between the vision sensor and the scene during the exposure time of the frame. Motion blur is clearly an undesirable phenomenon in computer vision not only because it degrades the quality of images but also causes other feature extraction procedures to degrade or fail. Although there are many studies on feature based tracking, navigation, object recognition algorithms in the computer vision and robotics literature, there is no comprehensive work on the effects of motion blur on different image features and their extraction. In this thesis, a survey of existing models of motion blur and approaches to motion deblurring is presented. We review recent literature on motion blur and deblurring and we focus our attention on motion blur induced degradation of a number of popular feature detectors. We investigate and characterize this degradation using video sequences captured by the vision system of a mobile legged robot platform. Harris Corner detector, Canny Edge detector and Scale Invariant Feature Transform (SIFT) are chosen as the popular feature detectors that are most commonly used for mobile robotics applications. The performance degradation of these feature detectors due to motion blur are categorized to analyze the effect of legged locomotion on feature performance for perception. These analysis results are obtained as a first step towards the stabilization and restoration of video sequences captured by our experimental legged robotic platform and towards the development of motion blur robust vision system.

Η παρούσα διπλωματική εργασία ασχολείται με ένα σημαντικό ερευνητικό πρόβλημα του πεδίου της υπολογιστικής όρασης το οποίο είναι η Αναγνώριση Προτύπων (pattern recognition) μέσα από εικόνες. Πιο συγκεκριμένα, θα μελετήσουμε τον σχεδιασμό και την υλοποίηση ενός συστήματος αναγνώρισης αντικειμένων από ψηφιακές εικόνες καθώς και την ταξινόμησή τους σε κατηγορίες (image classification). / This thesis deals with an important research problem field of computer vision which is pattern recognition through images. In particular, we will study the design and implementation of a system to recognize objects from digital images and their classification in categories (image classification).

Ένα σημαντικό πρόβλημα είναι η αντιστοίχιση εικόνων με σκοπό τη δημιουργία πανοράματος. Στην παρούσα εργασία έχουν χρησιμοποιηθεί αλγόριθμοι που βασίζονται στη χρήση σημείων κλειδιών. Αρχικά στην εργασία βρίσκονται σημεία κλειδιά για κάθε εικόνα που μένουν ανεπηρέαστα από τις αναμενόμενες παραμορφώσεις με την βοήθεια του αλγορίθμου SIFT (Scale Invariant Feature Transform). Έχοντας τελειώσει αυτή τη διαδικασία για όλες τις εικόνες, προσπαθούμε να βρούμε το πρώτο ζευγάρι εικόνων που θα ενωθεί. Για να δούμε αν δύο εικόνες μπορούν να ενωθούν, ακολουθεί ταίριασμα των σημείων κλειδιών τους. Όταν ένα αρχικό σετ αντίστοιχων χαρακτηριστικών έχει υπολογιστεί, πρέπει να βρεθεί ένα σετ που θα παράγει υψηλής ακρίβειας αντιστοίχιση. Αυτό το πετυχαίνουμε με τον αλγόριθμο RANSAC, μέσω του οποίου βρίσκουμε το γεωμετρικό μετασχηματισμό ανάμεσα στις δύο εικόνες, ομογραφία στην περίπτωσή μας. Αν ο αριθμός των κοινών σημείων κλειδιών είναι επαρκής, δηλαδή ταιριάζουν οι εικόνες, ακολουθεί η ένωσή τους. Αν απλώς ενώσουμε τις εικόνες, τότε θα έχουμε σίγουρα κάποια προβλήματα, όπως το ότι οι ενώσεις των δύο εικόνων θα είναι πολύ εμφανείς. Γι’ αυτό, για την εξάλειψη αυτού του προβλήματος, χρησιμοποιούμε τη μέθοδο των Λαπλασιανών πυραμίδων. Επαναλαμβάνεται η παραπάνω διαδικασία μέχρι να δημιουργηθεί το τελικό πανόραμα παίρνοντας κάθε φορά σαν αρχική την τελευταία εικόνα που φτιάξαμε στην προηγούμενη φάση. / Stitching multiple images together to create high resolution panoramas is one of the most popular consumer applications of image registration and blending. At this work, feature-based registration algorithms have been used. The first step is to extract distinctive invariant features from every image which are invariant to image scale and rotation, using SIFT (Scale Invariant Feature Transform) algorithm. After that, we try to find the first pair of images in order to stitch them. To check if two images can be stitched, we match their keypoints (the results from SIFT). Once an initial set of feature correspondences has been computed, we need to find the set that is will produce a high-accuracy alignment. The solution at this problem is RANdom Sample Consensus (RANSAC). Using this algorithm (RANSAC) we find the motion model between the two images (homography). If there is enough number of correspond points, we stitch these images. After that, seams are visible. As solution to this problem is used the method of Laplacian Pyramids. We repeat the above procedure using as initial image the ex panorama which has been created.

This work focuses on analysing and improving feature detection and matching. After creating an initial framework of study, four main areas of work are researched. These areas make up the main chapters within this thesis and focus on using the Scale Invariant Feature Transform (SIFT).The preliminary analysis of the SIFT investigates how this algorithm functions. Included is an analysis of the SIFT feature descriptor space and an investigation into the noise properties of the SIFT. It introduces a novel use of the a contrario methodology and shows the success of this method as a way of discriminating between images which are likely to contain corresponding regions from images which do not. Parameter analysis of the SIFT uses both parameter sweeps and genetic algorithms as an intelligent means of setting the SIFT parameters for different image types utilising a GPGPU implementation of SIFT. The results have demonstrated which parameters are more important when optimising the algorithm and the areas within the parameter space to focus on when tuning the values. A multi-exposure, High Dynamic Range (HDR), fusion features process has been developed where the SIFT image features are matched within high contrast scenes. Bracketed exposure images are analysed and features are extracted and combined from different images to create a set of features which describe a larger dynamic range. They are shown to reduce the effects of noise and artefacts that are introduced when extracting features from HDR images directly and have a superior image matching performance. The final area is the development of a novel, 3D-based, SIFT weighting technique which utilises the 3D data from a pair of stereo images to cluster and class matched SIFT features. Weightings are applied to the matches based on the 3D properties of the features and how they cluster in order to attempt to discriminate between correct and incorrect matches using the a contrario methodology. The results show that the technique provides a method for discriminating between correct and incorrect matches and that the a contrario methodology has potential for future investigation as a method for correct feature match prediction.

This work refers existing solutions and options for the task registration of photos to 3D model based on the previous knowledge of the geographic position of the camera. The contribution of the work are new ways and possibilities of the solution with the usage of graph algorithms. In this area, the work interests are useful points of interest detection in input data, a construction of graphs and graph matching possibilities.

The amount surveillance footage recorded each day is too large for human operators to analyze. A video summary system to process and refine this video data would prove beneficial in many instances. This work defines the problem in terms of its inputs, outputs and sub-problems, identifies suitable techniques and existing works as well as describes a design of such system. The system is implemented, and the results are examined.

This paper deals step by step with process of stitching images taken by perspective camera rotated by its optical center into the panoramic image. There are described keypoint searching algorhytms, possibilities of calculating homography matrix and methods of eliminating unwanted seams between source images in final panoramic image. A part of this paper is also standalone application in which are implemented some algorhytms described in the work.

This master's thesis deals with the interest point detection in images. The main goal is to create an application for making panoramic photos, which is based on this detection. The application uses the SIFT detector for finding keypoints of the image. Afterwards the geometrical consistence of image points using the RANSAC algorithm is finds out and images are transform into panorama in accordance with this geometrical consistence. Finally techniques for blending of transition between photos are used.

This thesis is interested in detection of corresponding points in images, which display the same object, eventually some of important elements and synchronizing these images. The aim of this thesis is to find, study and choose suitable algorithm for detecting interesting points in image. This algorithm will be apply at couple of images and in these images will find couples of corresponding points across these images. Functional output of this thesis will be application which will realize choosen interesting points detector, algorithm for finding correspondencies of regions and their synchronizing and joint them to one output image.