Visual object tracking is a classical and very popular problem in computer vision with a plethora of applications such as vehicle navigation, human computer interface, human motion analysis, surveillance, auto-control systems and many more. Given the initial state of a target in the first frame, the goal of tracking is to predict states of the target over time where the states describe a bounding box covering the target. Despite numerous object tracking methods that have been proposed in recent years [1-4], most of these trackers suffer a degradation in performance mainly because of several challenges that include illumination changes, motion blur, complex motion, out of plane rotation, and partial or full occlusion, while occlusion is usually the most contributing factor in degrading the majority of trackers, if not all of them. This thesis is devoted to the advancement of generic object trackers tackling different challenges through different proposed methods. The work presented propose four new state-of-the-art trackers. One of which is 3D based tracker in a particle filter framework where both synchronization and registration of RGB and depth streams are adjusted automatically, and three works in correlation filters that achieve state-of-the-art performance in terms of accuracy while maintaining reasonable speeds.

The word “Perception” seems to be intuitive and maybe the most straightforward problem for the human brain because as a child we have been trained to classify images, detect objects, but for computers, it can be a daunting task. Giving intuition and reasoning to a computer which has mere capabilities to accept commands and process those commands is a big challenge. However, recent leaps in hardware development, sophisticated software frameworks, and mathematical techniques have made it a little less daunting if not easy. There are various applications built around to the concept of “Perception”. These applications require substantial computational resources, expensive hardware, and some sophisticated software frameworks. Building an application for perception for the embedded system is an entirely different ballgame. Embedded system is a culmination of hardware, software and peripherals developed for specific tasks with imposed constraints on memory and power. Therefore, the applications developed should keep in mind the memory and power constraints imposed due to the nature of these systems.Before 2012, the problems related to “Perception” such as classification, object detection were solved using algorithms with manually engineered features. However, in recent years, instead of manually engineering the features, these features are learned through learning algorithms. The game-changing architecture of Convolution Neural Networks proposed in 2012 by Alex K, provided a tremendous momentum in the direction of pushing Neural networks for perception. This thesis is an attempt to develop a convolution neural network architecture for embedded systems, i.e. an architecture that has a small model size and competitive accuracy. Recreate state-of-the-art architectures using fire module’s concept to reduce the model size of the architecture. The proposed compact models are feasible for deployment on embedded devices such as the Bluebox 2.0. Furthermore, attempts are made to integrate the compact Convolution Neural Network with object detection pipelines.

Purpose of this thesis is the quality check of correct button text display on photographed monitors. These photographs contain a variety of image distortions which complicates the following image graphic element recognition. This paper outlines several possibilities to detect buttons on forms and further elaborates on the implemented detection based on contour shapes description. After buttons are found, their defects are detected subsequently. Additionally, this thesis describes an automatic identification of picture with the highest quality for documentation purposes.

The ability to generate accurate approximations of derivatives holds significant importance in numerous scientific fields, including chemistry, economics and fluid mechanics. This thesis is centred around extracting hidden information in data using Smoothness-Increasing Accuracy-Conserving (SIAC) filters. The target application is in calculating derivatives in simulations of fluid flow. SIAC filters are based on convolution. Because of the properties used to construct the convolution kernel, we are able to design post-processing filters that can extract extra derivative information with high accuracy. In the past, these filters have typically had a tensor-product structure, which requires multi-dimensional filtering. Because of this, the filtering process can be very computationally expensive. The goal of this thesis is to develop one-dimensional line filters that are able to extract the derivative information more efficiently. By utilizing line filters, we aim to significantly cut the computational cost of the filtering process, while also maintaining the high accuracy. / Att kunna generera approximeringar av derivator med hög noggrannhet har stor användning inom många vetenskapliga områden, inklusive kemi, ekonomi och strömningsmekanik. Denna uppsats är fokuserad på att extrahera dold information i data med hjälp av en specifik typ av faltningsfilter. Dessa filter kan öka kontinuitetsgraden av data utan att minska noggrannheten. Den avsedda tilläpningen för dessa filter är inom strömningsmekanik, framförallt beräkning av derivator i flöden. Tack vare egenskaperna som används för att konstruera faltningskärnan kan vi utforma efterbehandlingsfilter som kan extrahera derivatainformation med hög noggrannhet. Tidigare har dessa filter ofta haft en tensorproduktstruktur, vilket kräver flerdimensionell filtrering. På grund av detta har filtreringen ofta en hög beräkningskostnad. Målet med denna uppsats är att utveckla endimensionella linjefilter som kan extrahera derivatainformation mer effektivt. Syftet är att använda dessa linjefilter för att betydligt miska filtreringens beräkningskostnad och samtidigt behålla den höga noggrannheten.