My thesis is dealing with the Learnable Evolution Model (LEM), a new evolutionary method of optimization, which employs a classification algorithm. The optimization process is guided by a characteristics of differences between groups of high and low performance solutions in the population. In this thesis I introduce new variants of LEM using classification algorithm AdaBoost or SVM. The qualities of proposed LEM variants were validated in a series of experiments in static and dynamic enviroment. The results have shown that the metod has better results with smaller group sizes. When compared to the Estimation of Distribution Algorithm, the LEM variants achieve comparable or better values faster. However, the LEM variant which combined the AdaBoost approach with the SVM approach had the best overall performance.

This thesis describes the design and implementation of hardware unit to detect objects in the image. Design of unit is optimized for fast streaming processing. Object detection is performed by the trained classifiers using local image features. It describes a new technique for multi-scale detection. Detector used accelerating algorithm based on neighboring positions. The correct functionality of the detector is verified by simulation and part of a whole is implemented on development kit.

This work deals with the OpenCL technology and its use for the task of object detection. The introduction is devoted to description of OpenCL fundamentals, as well as basic theory of object detection. Next chapter of the work is analysis, with design proposal which takes into consideration the possibilities of OpenCL. Further, there's description of implementation of detection application and experimental evaluation of detector's performance. The last chapter summarizes the achieved results.

This master's thesis describes principles of the most widely used object tracking systems in video and then mainly focuses on characterization and on implementation of an interactive offline tracking system for generic color objects. The algorithm quality consists in high accuracy evaluation of object trajectory. The system creates the output trajectory from input data specified by user which may be interactively modified and added to improve the system accuracy. The algorithm is based on a detector which uses a color bin features and on the temporal coherence of object motion to generate multiple candidate object trajectories. Optimal output trajectory is then calculated by dynamic programming whose parameters are also interactively modified by user. The system achieves 15-70 fps on a 480x360 video. The thesis describes implementation of an application which purpose is to optimally evaluate the tracker accuracy. The final results are also discussed.

Recognition of handwritten digits is a problem, which could serve as model task for multiclass recognition of image patterns. This thesis studies different kinds of algoritms (Self-Organizing Maps, Randomized tree and AdaBoost) and methods for increasing accuracy using fusion (majority voting, averaging log likelihood ratio, linear logistic regression). Fusion methods were used for combine classifiers with indentical train parameters, with different training methods and with multiscale input.

The essence of face recognition within the image is generally computer vision, which provides methods and algorithms for the implementation. Some of them are described just in this work. Whole process is split in to three main phases. These are detection, aligning of detected faces and finally its recognition. Algorithms which are used to applied in given issue and which are still in progress from todays view are mentioned in every phase. Implementation is build up on three main algorithms, AdaBoost to obtain the classifier for detection, method of aligning face by principal features and method of Eigenfaces for recognizing. There are theoretically described except already mentioned algorithms neural networks for detection, ASM - Active Shape Models algorithm for aligning and AAM - Active Appearance Model for recognition. In the end there are tables of data retrieved by implemented system, which evaluated the main implementation.

Image analysis of wear particles is a suitable support tool for detail analysis of engine, gear, hydraulic and industrial oils. It allows to obtain information not only of basic parameters of abrasion particles but also data that would be very difficult to obtain using classical ways of evaluation. Based on the analysis of morphological or image characteristics of particles, the progress of wearing the machine parts out can be followed and, as a result, possible breakdown of the engine can be prevented or the optimum period for changing the oil can be determined. The aim of this paper is to explore the possibilities of using the image analysis combined with the method of analytical ferrography and suggest a tool for automated particle classification. Current methods of wear particle analysis are derived from the evaluation that does not offer an exact idea of processes that take place between the friction surfaces in the engine system. The work is based upon the method of analytical ferrography which allows to evaluate the state of the machine. The benefit of use of classifiers defined in this wirk is the possibility of automated evaluation of analytical ferrography outputs; the use of them eliminates the crucial disadvantage of ferrographical analysis which is its dependence on the subjective evaluation done by the expert who performs the analysis. Classifiers are defined as a result of using the methods of machine learning. Based on an extensive database of particles that was created in the first part of the work, the classifiers were trained as a result, they make the evaluation of ferrographically separated abrasion particles from oils taken from lubricated systems possible. In the next stage, experiments were carried out and optimum classifier settings were determined based on the results of the experiments.

Tato práce navrhuje zlepšení výkonu testování programů použitím technik dolování z dat a genetických algoritmů při testování paralelních programů.  Paralelní programování se v posledních letech stává velmi populárním i přesto, že toto programování je mnohem náročnějsí než jednodušší sekvenční a proto jeho zvýšené používání vede k podstatně vyššímu počtu chyb. Tyto chyby se vyskytují v důsledku chyb v synchronizaci jednotlivých procesů programu. Nalezení takových chyb tradičním způsobem je složité a navíc opakované spouštění těchto testů ve stejném prostředí typicky vede pouze k prohledávání stejných prokládání. V práci se využívá metody vstřikování šumu, která vystresuje program tak, že se mohou objevit některá nová chování. Pro účinnost této metody je nutné zvolit vhodné heuristiky a též i hodnoty jejich parametrů, což není snadné. V práci se využívá metod dolování z dat, genetických algoritmů a jejich kombinace pro nalezení těchto heuristik a hodnot parametrů. V práci je vedle výsledků výzkumu uveden stručný přehled dalších Technik testování paralelních programů.

This method demonstrates an approach to determine the best grasping location on an unknown object using Weighted Random Forest Algorithm. It used RGB-D value of an object as input to find a suitable rectangular grasping region as the output. To accomplish this task, it uses a subspace of most important features from a very high dimensional extensive feature space that contains both image and point cloud features. Usage of most important features in the grasping algorithm has enabled the system to be computationally very fast while preserving maximum information gain. In this approach, the Random Forest operates using optimum parameters e.g. Number of Trees, Number of Features at each node, Information Gain Criteria etc. ensures optimization in learning, with highest possible accuracy in minimum time in an advanced practical setting. The Weighted Random Forest chosen over Support Vector Machine (SVM), Decision Tree and Adaboost for implementation of the grasping system outperforms the stated machine learning algorithms both in training and testing accuracy and other performance estimates. The Grasping System utilizing learning from a score function detects the rectangular grasping region after selecting the top rectangle that has the largest score. The system is implemented and tested in a Baxter Research Robot with Parallel Plate Gripper in action.

Unmanned Aerial Vehicles (UAVs) provides a platform for many automated tasks and with an ever increasing advances in computing, these tasks can be more complex. The use of UAVs is expanded in this thesis with the goal of Search and Rescue (SAR), where a UAV can assist fast responders to search for a lost person and relay possible search areas back to SAR teams. To identify a person from an aerial perspective, low-level Histogram of Oriented Gradients (HOG) feature descriptors are used over a segmented region, provided from thermal data, to increase classification speed. This thesis also introduces a dataset to support a Bird’s-Eye-View (BEV) perspective and tests the viability of low level HOG feature descriptors on this dataset. The low-level feature descriptors are known as Boosted Histogram of Oriented Gradients (BHOG) features, which discretizes gradients over varying sized cells and blocks that are trained with a Cascaded Gentle AdaBoost Classifier using our compiled BEV dataset. The classification is supported by multiple sensing modes with color and thermal videos to increase classification speed. The thermal video is segmented to indicate any Region of Interest (ROI) that are mapped to the color video where classification occurs. The ROI decreases classification time needed for the aerial platform by eliminating a per-frame sliding window. Testing reveals that with the use of only color data iv and a classifier trained for a profile of a person, there is an average recall of 78%, while the thermal detection results with an average recall of 76%. However, there is a speed up of 2 with a video of 240x320 resolution. The BEV testing reveals that higher resolutions are favored with a recall rate of 71% using BHOG features, and 92% using Haar-Features. In the lower resolution BEV testing, the recall rates are 42% and 55%, for BHOG and Haar-Features, respectively.