This thesis attempts to create an application to determine head rotation angle in video recorded from a security camera. The application consists of three parts: face detection, facial landmarks detection and determination of person's head rotation. The face detection has been implemented using Viola-Jones and HOG algorithms. Facial landmarks detection has been done using algorithm based on active shape model. Two methods to calculate the head rotation angles have been used: the first method works with anthropometric head features. The second method uses Perspective-n-Point algorithm to find the right rotation angles. Finally, all algorithms implemented have been tested and the proper parameters have been determined.

Tato práce se zabývá zvýšením úspěšnosti rozpoznávání obličejů v dohledových CCTV systémech a systémech kontroly vstupu. K dosažení tohoto cíle je využit nový přístup - optimalizace vzorů obličejů. Optimalizace tvorby vzorů umožní vytvořit vzory, které zajistí zvýšení úspěšnosti rozpoznání. Měření a další zvyšování úspěšnosti rozpoznávání obličejů vyžaduje naplnění následujících dílčích cílů této práce. Prvním cílem je návrh a sestavení reprezentativní databáze obličejů, která umožní dosáhnout věrohodných a statisticky spolehlivých výsledků rozpoznávání obličejů v dohledových CCTV systémech a systémech kontroly vstupu. Druhým cílem je vytvoření metodiky pro statisticky spolehlivé porovnání výsledků, která umožní konstatování relevantních závěrů. Třetím cílem je výzkum tvorby vzorů a jejich optimalizace. Z dosažených výsledků vyplývá, že optimalizace tvorby vzorů zvyšuje úspěšnost rozpoznávání v uvedených a náročných aplikacích typicky o 4-8%, a v některých případech i 15%. Optimalizace tvorby vzorů přispívá použitelnosti rozpoznávání obličejů v uvedených aplikacích.

This master's thesis deals with design and implementation of system for securing and monitoring objects. The whole system is serving as an application getaway between typical TCP/IP network and heterogeneous network containing different end devices such as security cameras, microphones and some sensors (e.g. for temperature measurement). In case of detected event, the notification is created, recorded and the user is informed via administrative front-end. System can be managed from remote location and data from devices can be shown by web interface. Theoretical part of this project concerns with the analysis of different types of connecting devices and sensors and the possibilities of their usage for the monitoring systems along with description of communications protocols for each end device. The next part deals with the cameras interfaces, content analysis and connectivity with central server. Practical part describes methods and techniques used for implementation of system.

The theme of this thesis is the design of peripheral devices of a smart home SmartFlat and the design of communication interface for this system. Designed units are the humidity and temperature measuring unit, the unit of security and the smart socket unit for remote control, power measurement and power control. All units are designed for wired communicaton and also for wireless communication with control unit.

This thesis deals with analysis of company’s MBG, spol. s r.o. problems, following with teoretical basis for these problems and in the end, it suggests the solutions. These problems are insufficient monitoring, any of used technology are old and absent of any information security management system. The first part is focused on a teoretical basis for the described problems, the second part will completely analyze all mentioned problems of a company. Final part will contain a solution for every company’s problem, based on theory and analysis with taking care about company’s demand too.

This study is designed to assess the effectiveness of closed-circuit television (CCTV) as a post-partum teaching tool using an interactive problem-solving approach, compared with conventional group classes, in fostering the acquisition of skills and knowledge around baby care. A second primary objective is to determine the level of satisfaction of respondents with both approaches to post-partum education. An extensive discussion of the theoretical basis for the proposal is presented, drawing upon and synthesising concepts from the literature of Sociology, Education and Health Sciences. The conceptual model (Sword 1990) represents a synthesis of Mezirow’s (1978) theory of the transformation of meaning perspective with D’Zurilla’s (1986) cognitive-appraisal approach to the acquisition of new knowledge. In addition, adult learning principles are applied to the selected teaching strategies to identify optimal conditions of learning (Zemke and Zemke 1988). A two-group cohort design was used for randomisation, and the data collected was subjected to both quantitative and qualitative analysis. Two measures of learning were not significantly different for the videotape and live class groups. Statistically significant differences were identified between the groups in the attitude measures of convenience and ease of understanding. There was also a measurable difference in levels of satisfaction with the different approaches used. However, the results of this study suggest that combining an interactive, problem-solving approach to post-partum education with CCTV, is no more effective than live group classes in achieving knowledge acquisition for new mothers. CCTV can be used to address the basic and repetitive aspects of patient education and it appears to be effective for short-term knowledge gain. Several issues for further study are proposed in relation to the planning and implementation of alternative approaches to conventional post-partum teaching, as well as the design of future televised patient education programmes. / Thesis / Master of Science (MSc)

This thesis presents the novel use of Coherent Point Drift in improving the robustness of a number of computer vision applications. CPD approach includes two methods for registering two images - rigid and non-rigid point set approaches which are based on the transformation model used. The key characteristic of a rigid transformation is that the distance between points is preserved, which means it can be used in the presence of translation, rotation, and scaling. Non-rigid transformations - or affine transforms - provide the opportunity of registering under non-uniform scaling and skew. The idea is to move one point set coherently to align with the second point set. The CPD method finds both the non-rigid transformation and the correspondence distance between two point sets at the same time without having to use a-priori declaration of the transformation model used. The first part of this thesis is focused on speaker identification in video conferencing. A real-time, audio-coupled video based approach is presented, which focuses more on the video analysis side, rather than the audio analysis that is known to be prone to errors. CPD is effectively utilised for lip movement detection and a temporal face detection approach is used to minimise false positives if face detection algorithm fails to perform. The second part of the thesis is focused on multi-exposure and multi-focus image fusion with compensation for camera shake. Scale Invariant Feature Transforms (SIFT) are first used to detect keypoints in images being fused. Subsequently this point set is reduced to remove outliers, using RANSAC (RANdom Sample Consensus) and finally the point sets are registered using CPD with non-rigid transformations. The registered images are then fused with a Contourlet based image fusion algorithm that makes use of a novel alpha blending and filtering technique to minimise artefacts. The thesis evaluates the performance of the algorithm in comparison to a number of state-of-the-art approaches, including the key commercial products available in the market at present, showing significantly improved subjective quality in the fused images. The final part of the thesis presents a novel approach to Vehicle Make & Model Recognition in CCTV video footage. CPD is used to effectively remove skew of vehicles detected as CCTV cameras are not specifically configured for the VMMR task and may capture vehicles at different approaching angles. A LESH (Local Energy Shape Histogram) feature based approach is used for vehicle make and model recognition with the novelty that temporal processing is used to improve reliability. A number of further algorithms are used to maximise the reliability of the final outcome. Experimental results are provided to prove that the proposed system demonstrates an accuracy in excess of 95% when tested on real CCTV footage with no prior camera calibration.

安控產業存在於市場上已有數十年的時間了，近十年來由於科技的突飛猛進，加上恐怖主義盛行，也帶動了這個產業的蓬勃發展。在2011年以後，安控產業預計將正式超過PC產業的產值，成為下一個明星產業。 雖說安控產業的前景一片看好，可是，馬上連想到的是PC產業的削價競爭。由於大陸安控產業的興起，全球安控產品的價格近年來也因此大幅滑落，未來，安控產業的業者若不尋找新的藍海，重新定位安控產業，則在低階的安控市場，很可見的將會都是大陸產品的天下。 本研究的目的在為安控產業找到新的價值與定位。由於安控產業的核心價值就是實時監控及遠端連線，對一個連鎖企業或跨國企業管理來說，其實可以提供一很實時的競爭資訊，進而可以使企業提升為實時企業。安控系統就如同經營者的雙眼，時時的監控著整個企業的運作，甚至可以透過智慧型影像辨識，主動蒐集所有可能的競爭資訊，盡可能極早期的發現問題所在，或是可以比競爭者更早發現新的商機。 本研究主要由兩個方向著手，一是策略風險管理，一是企業危機防範，藉由這兩個構面，加上動態價值鏈的重整與再鏈結，可以讓一個實時企業隨時都保持在低風險的境界。 / CCTV industry presence in the market for several decades, and over the past decade as technology advances, coupled with widespread terrorism also contributed to the rapid development of this industry. In many research institutions have done studies predict that after 2011, the revenue of CCTV industry will be more than PC industry, becoming the next rising star. Although the optimistic vision of CCTV industry, however, the same as PC industry, the price war is the first concern. Since the rise of China manufacturing, the prices of CCTV products have fallen dramatically. CCTV industry needs to find a new blue ocean to re-position CCTV industry; otherwise, China brands eventually will gain all the low level of CCTV market. The purpose of this study is trying to find a way to re-position the CCTV industry. As the core values of CCTV industry is the real-time monitoring and remote connection, for the management of chain-stores and multi-national enterprise, the CCTV can provide an unbeatable value to help them to be a real-time enterprise. A CCTV system is just like a pair of eyes to help managers to watch their enterprise all the time efficiently. In addition, through the intelligent image recognition, a CCTV system may collect all the possible competition information to help managers to find the business opportunities in a very early stage. This study includes two dimensions, strategic risk management and corporate crisis prevention. Based on the above two dimensions, coupled with the dynamic value chain, we can make a real-time enterprise maintained at a low-level risk state always.

The aim of my thesis is to elucitade MBI model to primary and secondary educational system, it means to schools and their elected IT processes from practical point of view. The reference model of Management Business Information is developed at the Department of Information at the Faculty of Information and Statistics at the School of Economics in Prague. The theoretical part of my thesis deals with elucitading of the reference MBI model to a reader. It briefly summarizes IT processes at educational system and refers to sources used while defining new MBI objects. This chapter also defines elected IT processes at educational system for which there are made MBI objects in a practical part of my thesis. In practical part of my thesis there are made proposals of defined objects including samples of documentation patterns. These objects are presented in charts that correspond with a format of MBI objects. In the last part of my thesis there is an example of applying the defined objects in practice while solving the process of installation the safety (camera) system with recording -- personal data processing. The proposals of defined objects are also published on MBI portal.

The content of this thesis is the complex security system proposal, specifically of PZTS system and CCTV system. The thesis is divided into three parts. The first part is analysis of the current state, the second is theoretical part and the third part is a practical part. The first part deals with the analysis of the current state of physical security and technical protection of the premises. The theoretical part deals with theoretical solutions for security system proposal. The practical part is focused on separate PZTS and CCTV systems proposal, that will meet all the requirements and standards of the customer.