Hand tracking in high-speed camera videos

Visual object tracking has been one of the most popular research topics in the field of computer vision recently. Specifically, hand tracking has attracted significant attention since it would enable many useful practical applications. However, hand tracking is still a very challenging problem which cannot be considered solved. The fact that almost every aspect of hand appearance can change is the fundamental reason for this difficulty. This thesis focused on 2D-based hand tracking in high-speed camera videos. During the project, a toolbox for this purpose was collected which contains nine different tracking methods. In the experiments, these methods were tested and compared against each other with both high-speed videos recorded during the project and publicly available normal speed videos. The results revealed that tracking accuracies varied considerably depending on the video and the method. Therefore, no single method was clearly the best in all videos, but three methods, CT, HT, and TLD, performed better than the others overall. Moreover, the results provide insights about the suitability of each method to different types and situations of hand tracking.

Efficient Optimization Algorithms for Nonlinear Data Analysis

Identification of low-dimensional structures and main sources of variation from multivariate data are fundamental tasks in data analysis. Many methods aimed at these tasks involve solution of an optimization problem. Thus, the objective of this thesis is to develop computationally efficient and theoretically justified methods for solving such problems. Most of the thesis is based on a statistical model, where ridges of the density estimated from the data are considered as relevant features. Finding ridges, that are generalized maxima, necessitates development of advanced optimization methods. An efficient and convergent trust region Newton method for projecting a point onto a ridge of the underlying density is developed for this purpose. The method is utilized in a differential equation-based approach for tracing ridges and computing projection coordinates along them. The density estimation is done nonparametrically by using Gaussian kernels. This allows application of ridge-based methods with only mild assumptions on the underlying structure of the data. The statistical model and the ridge finding methods are adapted to two different applications. The first one is extraction of curvilinear structures from noisy data mixed with background clutter. The second one is a novel nonlinear generalization of principal component analysis (PCA) and its extension to time series data. The methods have a wide range of potential applications, where most of the earlier approaches are inadequate. Examples include identification of faults from seismic data and identification of filaments from cosmological data. Applicability of the nonlinear PCA to climate analysis and reconstruction of periodic patterns from noisy time series data are also demonstrated. Other contributions of the thesis include development of an efficient semidefinite optimization method for embedding graphs into the Euclidean space. The method produces structure-preserving embeddings that maximize interpoint distances. It is primarily developed for dimensionality reduction, but has also potential applications in graph theory and various areas of physics, chemistry and engineering. Asymptotic behaviour of ridges and maxima of Gaussian kernel densities is also investigated when the kernel bandwidth approaches infinity. The results are applied to the nonlinear PCA and to finding significant maxima of such densities, which is a typical problem in visual object tracking.

Automatic recognition of fish from video sequences

The problem of automatic recognition of the fish from the video sequences is discussed in this Master’s Thesis. This is a very urgent issue for many organizations engaged in fish farming in Finland and Russia because the process of automation control and counting of individual species is turning point in the industry. The difficulties and the specific features of the problem have been identified in order to find a solution and propose some recommendations for the components of the automated fish recognition system. Methods such as background subtraction, Kalman filtering and Viola-Jones method were implemented during this work for detection, tracking and estimation of fish parameters. Both the results of the experiments and the choice of the appropriate methods strongly depend on the quality and the type of a video which is used as an input data. Practical experiments have demonstrated that not all methods can produce good results for real data, whereas on synthetic data they operate satisfactorily.

Building object-oriented software with the D-Bus messaging system

Object-oriented programming is a widely adopted paradigm for desktop software development. This paradigm partitions software into separate entities, objects, which consist of data and related procedures used to modify and inspect it. The paradigm has evolved during the last few decades to emphasize decoupling between object implementations, via means such as explicit interface inheritance and event-based implicit invocation. Inter-process communication (IPC) technologies allow applications to interact with each other. This enables making software distributed across multiple processes, resulting in a modular architecture with benefits in resource sharing, robustness, code reuse and security. The support for object-oriented programming concepts varies between IPC systems. This thesis is focused on the D-Bus system, which has recently gained a lot of users, but is still scantily researched. D-Bus has support for asynchronous remote procedure calls with return values and a content-based publish/subscribe event delivery mechanism. In this thesis, several patterns for method invocation in D-Bus and similar systems are compared. The patterns that simulate synchronous local calls are shown to be dangerous. Later, we present a state-caching proxy construct, which avoids the complexity of properly asynchronous calls for object inspection. The proxy and certain supplementary constructs are presented conceptually as generic object-oriented design patterns. The e ect of these patterns on non-functional qualities of software, such as complexity, performance and power consumption, is reasoned about based on the properties of the D-Bus system. The use of the patterns reduces complexity, but maintains the other qualities at a good level. Finally, we present currently existing means of specifying D-Bus object interfaces for the purposes of code and documentation generation. The interface description language used by the Telepathy modular IM/VoIP framework is found to be an useful extension of the basic D-Bus introspection format.

Hardware Accelarated Visual Tracking Algorithms. A Systematic Literature Review

Many industrial applications need object recognition and tracking capabilities. The algorithms developed for those purposes are computationally expensive. Yet ,real time performance, high accuracy and small power consumption are essential measures of the system. When all these requirements are combined, hardware acceleration of these algorithms becomes a feasible solution. The purpose of this study is to analyze the current state of these hardware acceleration solutions, which algorithms have been implemented in hardware and what modifications have been done in order to adapt these algorithms to hardware.

Exploring the impact of celebrity endorsement and product class involvement on advertising effectiveness: an eye tracking approach

Celebrity endorsement has increased in popularity over the past decades and companies are willing to spend increasingly excessive amounts of money into it. Even though multiple studies support celebrity endorsement, further research on its impact on advertising effectiveness is called for. Fur-ther, the role of consumers’ product class involvement in advertising needs to be further studied. The purpose of this study is to explore if consumers’ product class involvement and exposure to celebrity endorsers affect consumers brand recall. Supported by earlier studies, brand recall was used as a measure for advertising effectiveness in this study. In general, a psychological approach was chosen for building the theoretical framework. Concept of classical conditioning was presented in order to understand why people act how they do. Balanced theory and meaning transfer model were presented in order to study how celebrities can be used effectively in advertising context. Further, the importance of product class involvement in advertising effectiveness was evaluated. Hypotheses were formulated based on a literature review of the existing research. Because of the versatility of the research design, a mixed methods approach for this study was adopted. Empirical part of the study was conducted in three stages. First, a pre-test was conducted in order to choose suitable product endorsers for the advertisement stimuli used in the experiment. Second, an eye-tracking experiment with 30 test subjects was conducted in order to study how people view advertisements and whether the familiarity of the product endorser and consumers’ product class involvement affects brand recall. For the experiment, a fictional brand was created in order to avoid bias on brand recall. Third, qualitative interviews for 15 test subjects were conducted in the post-experiment stage in order to gain deeper understating of the phenomenon and to make sense of the findings from the experiment. Findings from this study support celebrity endorsement by suggesting that a famous spokesperson does not steal attention from brand information more than a non-celebrity product endorser. As a result, the use of a celebrity endorser did not decrease brand recall. Results support earlier research as consumer’ higher product class involvement resulted in a better brand recall. Findings from the interviews suggest that consumers have positive perceptions of celebrity endorsement in general. However, the celebrity–brand congruence is a crucial factor when creating attitudes towards the advertisement. Future research ideas were presented based on the limitations and results of this study

Feasibility of replacing multiple ADSL connections with Multi-Dwelling Access

This final project was made for the Broadband/Implementation department of TeliaSonera Finland. The question to be examined is if the operator should replace multiple ADSL connections implemented over a leased line with Multi-Dwelling access based on an Ethernet/Optical Fibre access network. The project starts with describing the technology related to these access network solu-tions and presents the technology that is used in TeliaSonera Finland's access network. It continues from the technology to describe the problem with some of the ADSL implemen-tations of TeliaSonera. The problem is the implementations done over a leased line that can cost TeliaSonera over years as much as a possible investment to extend network when there is several lines leased to the same building. The project proposes a Multi-Dwelling access as a solution to this problem and defines the circumstances when to use it. After a satisfactory solution has found the project takes a view how implementation of the solution might alter the network and a new problem is found. When used commonly to replace need of ADSL implementation Multi-Dwelling access would significantly increase optical cable congestion near operators POP. As a final deed this project also proposes a technical change to existing way to implement multi-dwelling access with EPON technology.

Measurement of Bioactivity of Immunomodulatory Treatment of Relapsing Multiple Sclerosis. With Emphasis on MxA Protein

Background Multiple sclerosis (MS) is a demyelinating disease of the central nervous system, which mainly affects young adults. In Finland, approximately 2500 out of 6000 MS patients have relapsing MS and are treated with disease modifying drugs (DMD): interferon- β (INF-β-1a or INF-β-1b) and glatiramer acetate (GA). Depending on the used IFN-β preparation, 2 % to 40 % of patients develop neutralizing antibodies (NAbs), which abolish the biological effects of IFN-β, leading to reduced clinical and MRI detected efficacy. According to the Finnish Current Care Guidelines and European Federation of Neurological Societis (EFNS) guidelines, it is suggested tomeasure the presence of NAbs during the first 24 months of IFN-β therapy. Aims The aim of this thesis was to measure the bioactivity of IFN-β therapy by focusing on the induction of MxA protein (myxovirus resistance protein A) and its correlation to neutralizing antibodies (NAb). A new MxA EIA assay was set up to offer an easier and rapid method for MxA protein detection in clinical practice. In addition, the tolerability and safety of GA were evaluated in patients who haddiscontinued IFN-β therapy due to side effects and lack of efficacy. Results NAbs developed towards the end of 12 months of treatment, and binding antibodies were detectable before or parallel with them. The titer of NAb correlated negatively with the amount of MxA protein and the mean values of preinjection MxA levels never returned to true baseline in NAb negative patients, but tended to drop in the NAb positive group. The test results between MxA EIA and flow cytometric analysis showed significant correlation. GA reduced the relapse rate and was a safe and well-tolerated therapy in IFN-β-intolerant MS patients. Conclusions NAbs inhibit the induction of MxA protein, which can be used as a surrogate marker of the bioactivity of IFN-β therapy. Compared to flow cytometricanalysis and NAb assay, MxA-EIA seemed to be a sensitive and more practical method in clinical use to measure the actual bioactivity of IFN-β treatment, which is of value also from a cost-effective perspective.