Object tracking can be done in numerous ways, where the goal is to track a target through all frames in a sequence. The ground truth bounding box is used to initialize the object tracking algorithm. Object tracking can be carried out on infrared imagery suitable for military applications to execute tracking even without illumination. Objects, such as aircraft, can deploy countermeasures to impede tracking. The countermeasures most often mainly impact one wavelength band. Therefore, using two different wavelength bands for object tracking can counteract the impact of the countermeasures. The dataset was created from simulations. The countermeasures applied to the dataset are flares and Directional Infrared Countermeasures (DIRCMs). Different object tracking algorithms exist, and many are based on discriminative correlation filters (DCF). The thesis investigated the DCF-based trackers STRCF and ECO on the created dataset. The STRCF and the ECO trackers were analyzed using one and two wavelength bands. The following features were investigated for both trackers: grayscale, Histogram of Oriented Gradients (HOG), and pre-trained deep features. The results indicated that the STRCF and the ECO trackers using two wavelength bands instead of one improved performance on sequences with countermeasures. The use of HOG, deep features, or a combination of both improved the performance of the STRCF tracker using two wavelength bands. Likewise, the performance of the ECO tracker using two wavelength bands was improved by the use of deep features. However, the negative aspect of using two wavelength bands and introducing more features is that it resulted in a lower frame rate.

There are three main results in this dissertation. The first result is the construction of an abstract visual space for rational numbers mod1, based on the visual primitives, colour, and rational radial direction. Mathematics is performed in this visual notation by defining increasingly refined visual objects from these primitives. In particular, the existence of the Farey tree enumeration of rational numbers mod1 is identified in the texture of a two-dimensional animation. ¶ The second result is a new enumeration of the rational numbers mod1, obtained, and expressed, in abstract visual space, as the visual object coset waves of coset fans on the torus. Its geometry is shown to encode a countably infinite tree structure, whose branches are cosets, nZ+m, where n, m (and k) are integers. These cosets are in geometrical 1-1 correspondence with sequences kn+m, (of denominators) of rational numbers, and with visual subobjects of the torus called coset fans. ¶ The third result is an enumeration in time of the visual hierarchy of the discrete buds of the Mandelbrot boundary by coset waves of coset fans. It is constructed by embedding the circular Farey tree geometrically into the empty internal region of the Mandelbrot set. In particular, coset fans attached to points of the (internal) binary tree index countably infinite sequences of buds on the (external) Mandelbrot boundary.

Title: Image Deblurring in Demanding Conditions Author: Jan Kotera Department: Institute of Information Theory and Automation, Czech Academy of Sciences Supervisor: Doc. Ing. Filip Šroubek, Ph.D., DSc., Institute of Information Theory and Automation, Czech Academy of Sciences Abstract: Image deblurring is a computer vision task consisting of removing blur from image, the objective is to recover the sharp image corresponding to the blurred input. If the nature and shape of the blur is unknown and must be estimated from the input image, image deblurring is called blind and naturally presents a more difficult problem. This thesis focuses on two primary topics related to blind image deblurring. In the first part we work with the standard image deblurring based on the common convolution blur model and present a method of increasing robustness of the deblur- ring to phenomena violating the linear acquisition model, such as for example inten- sity clipping caused by sensor saturation in overexposed pixels. If not properly taken care of, these effects significantly decrease accuracy of the blur estimation and visual quality of the restored image. Rather than tailoring the deblurring method explicitly for each particular type of acquisition model violation we present a general approach based on flexible automatic...