Search

TThis research paper presents research conducted to control the sound level of the system using hand gestures. The proposed system is designed using Python programming language and OpenCV library. The development of programs that can be controlled using natural gestures is an important area of research in the field of human - computer interaction. The system captures the video feed from the camera and analyzes it to de-tect the hand gestures. The captured frames are preprocessed to remove noise and sim-plify processing. The image is then converted to grayscale, thresholded to separate the hand from the background, and contours are found in the thresholded image. The de-tected gestures are then mapped to control the sound level of the system. The proposed system is implemented and tested on a laptop computer with satisfactory results. The program is tested on a range of operating systems and environments to ensure com-patibility and functionality. To optimize for speed and efficiency, the program can be parallelized and/or implemented using GPU acceleration.

Moving fully or partially online during the pandemic has exposed challenges in appreciating the nuances of sociomaterial design work in the design student / tutor encounter, while also offering opportunities for introducing “new” practices to otherwise resistant students and tutors. This paper explores a simple format for and practice of video capture that encourages students to provide detailed descriptions of up-close visual material, giving tutors a comparatively expanded view of the student work and the student or student-teams relationship to their work. By framing the video capture moment as a form of performance for both the tutor(s) and the student(s) involved in the video capture, the paper argues that the video-making process is a productive practice in and of itself, and a collaborative, dialogic one in concert with the tutor as audience, as well as its use as representational practice for tutor consumption.

Moving fully or partially online during the pandemic has exposed challenges in appreciating the nuances of sociomaterial design work in the design student / tutor encounter, while also offering opportunities for introducing “new” practices to otherwise resistant students and tutors. This paper explores a simple format for and practice of video capture that encourages students to provide detailed descriptions of up-close visual material, giving tutors a comparatively expanded view of the student work and the student or student-teams relationship to their work. By framing the video capture moment as a form of performance for both the tutor(s) and the student(s) involved in the video capture, the paper argues that the video-making process is a productive practice in and of itself, and a collaborative, dialogic one in concert with the tutor as audience, as well as its use as representational practice for tutor consumption.

Moving fully or partially online during the pandemic has exposed challenges in appreciating the nuances of sociomaterial design work in the design student / tutor encounter, while also offering opportunities for introducing “new” practices to otherwise resistant students and tutors. This paper explores a simple format for and practice of video capture that encourages students to provide detailed descriptions of up-close visual material, giving tutors a comparatively expanded view of the student work and the student or student-teams relationship to their work. By framing the video capture moment as a form of performance for both the tutor(s) and the student(s) involved in the video capture, the paper argues that the video-making process is a productive practice in and of itself, and a collaborative, dialogic one in concert with the tutor as audience, as well as its use as representational practice for tutor consumption.

Moving fully or partially online during the pandemic has exposed challenges in appreciating the nuances of sociomaterial design work in the design student / tutor encounter, while also offering opportunities for introducing “new” practices to otherwise resistant students and tutors. This paper explores a simple format for and practice of video capture that encourages students to provide detailed descriptions of up-close visual material, giving tutors a comparatively expanded view of the student work and the student or student-teams relationship to their work. By framing the video capture moment as a form of performance for both the tutor(s) and the student(s) involved in the video capture, the paper argues that the video-making process is a productive practice in and of itself, and a collaborative, dialogic one in concert with the tutor as audience, as well as its use as representational practice for tutor consumption.

Moving fully or partially online during the pandemic has exposed challenges in appreciating the nuances of sociomaterial design work in the design student / tutor encounter, while also offering opportunities for introducing “new” practices to otherwise resistant students and tutors. This paper explores a simple format for and practice of video capture that encourages students to provide detailed descriptions of up-close visual material, giving tutors a comparatively expanded view of the student work and the student or student-teams relationship to their work. By framing the video capture moment as a form of performance for both the tutor(s) and the student(s) involved in the video capture, the paper argues that the video-making process is a productive practice in and of itself, and a collaborative, dialogic one in concert with the tutor as audience, as well as its use as representational practice for tutor consumption.

Behavior can sometimes be observed directly, and can also be affected by the presence of human observers. Technological devices have strongly advanced our understanding of certain aspects of animal behavior, and the small cameras borne in a straight line by study animals offer a reliable alternative to direct observation. One possible way to make animal welfare assessments easier and faster could be the application of audio and video data analysis. In this research, the main goal is to reach the requirements determination, and the construction to build a concurrent alternative to CCTV software based on new proprietary software, developed in Matlab® language, to record and capture video sequences in digital memory hardware. The proposed software stakeholders’ needs are written attending the specification in the ISO/IEC/IEEE 29148:2011 standard, and the life cycle adapted to the development was based in the standard ISO/IEC/IEEE 12207:2008. The main user interface was generated using the Matlab® GUI (Graphical User Interface). In the results, a resumed table with the final document of Requirement Specification (StRS) was generated and the main interface is coded. The system validation took place in the animal houses (bioterium) over a period of three months and the data collection and software usability reach the attendance to all the requirements listed. Thus, in the conclusions, it was observed that its users considered the developed software a good tool to help researches in the poultry and laying hens’ facility (bioterium).

Behavior can sometimes be observed directly, and can also be affected by the presence of human observers. Technological devices have strongly advanced our understanding of certain aspects of animal behavior, and the small cameras borne in a straight line by study animals offer a reliable alternative to direct observation. One possible way to make animal welfare assessments easier and faster could be the application of audio and video data analysis. In this research, the main goal is to reach the requirements determination, and the construction to build a concurrent alternative to CCTV software based on new proprietary software, developed in Matlab® language, to record and capture video sequences in digital memory hardware. The proposed software stakeholders’ needs are written attending the specification in the ISO/IEC/IEEE 29148:2011 standard, and the life cycle adapted to the development was based in the standard ISO/IEC/IEEE 12207:2008. The main user interface was generated using the Matlab® GUI (Graphical User Interface). In the results, a resumed table with the final document of Requirement Specification (StRS) was generated and the main interface is coded. The system validation took place in the animal houses (bioterium) over a period of three months and the data collection and software usability reach the attendance to all the requirements listed. Thus, in the conclusions, it was observed that its users considered the developed software a good tool to help researches in the poultry and laying hens’ facility (bioterium).

Behavior can sometimes be observed directly, and can also be affected by the presence of human observers. Technological devices have strongly advanced our understanding of certain aspects of animal behavior, and the small cameras borne in a straight line by study animals offer a reliable alternative to direct observation. One possible way to make animal welfare assessments easier and faster could be the application of audio and video data analysis. In this research, the main goal is to reach the requirements determination, and the construction to build a concurrent alternative to CCTV software based on new proprietary software, developed in Matlab® language, to record and capture video sequences in digital memory hardware. The proposed software stakeholders’ needs are written attending the specification in the ISO/IEC/IEEE 29148:2011 standard, and the life cycle adapted to the development was based in the standard ISO/IEC/IEEE 12207:2008. The main user interface was generated using the Matlab® GUI (Graphical User Interface). In the results, a resumed table with the final document of Requirement Specification (StRS) was generated and the main interface is coded. The system validation took place in the animal houses (bioterium) over a period of three months and the data collection and software usability reach the attendance to all the requirements listed. Thus, in the conclusions, it was observed that its users considered the developed software a good tool to help researches in the poultry and laying hens’ facility (bioterium).

Behavior can sometimes be observed directly, and can also be affected by the presence of human observers. Technological devices have strongly advanced our understanding of certain aspects of animal behavior, and the small cameras borne in a straight line by study animals offer a reliable alternative to direct observation. One possible way to make animal welfare assessments easier and faster could be the application of audio and video data analysis. In this research, the main goal is to reach the requirements determination, and the construction to build a concurrent alternative to CCTV software based on new proprietary software, developed in Matlab® language, to record and capture video sequences in digital memory hardware. The proposed software stakeholders’ needs are written attending the specification in the ISO/IEC/IEEE 29148:2011 standard, and the life cycle adapted to the development was based in the standard ISO/IEC/IEEE 12207:2008. The main user interface was generated using the Matlab® GUI (Graphical User Interface). In the results, a resumed table with the final document of Requirement Specification (StRS) was generated and the main interface is coded. The system validation took place in the animal houses (bioterium) over a period of three months and the data collection and software usability reach the attendance to all the requirements listed. Thus, in the conclusions, it was observed that its users considered the developed software a good tool to help researches in the poultry and laying hens’ facility (bioterium).

Behavior can sometimes be observed directly, and can also be affected by the presence of human observers. Technological devices have strongly advanced our understanding of certain aspects of animal behavior, and the small cameras borne in a straight line by study animals offer a reliable alternative to direct observation. One possible way to make animal welfare assessments easier and faster could be the application of audio and video data analysis. In this research, the main goal is to reach the requirements determination, and the construction to build a concurrent alternative to CCTV software based on new proprietary software, developed in Matlab® language, to record and capture video sequences in digital memory hardware. The proposed software stakeholders’ needs are written attending the specification in the ISO/IEC/IEEE 29148:2011 standard, and the life cycle adapted to the development was based in the standard ISO/IEC/IEEE 12207:2008. The main user interface was generated using the Matlab® GUI (Graphical User Interface). In the results, a resumed table with the final document of Requirement Specification (StRS) was generated and the main interface is coded. The system validation took place in the animal houses (bioterium) over a period of three months and the data collection and software usability reach the attendance to all the requirements listed. Thus, in the conclusions, it was observed that its users considered the developed software a good tool to help researches in the poultry and laying hens’ facility (bioterium).

Behavior can sometimes be observed directly, and can also be affected by the presence of human observers. Technological devices have strongly advanced our understanding of certain aspects of animal behavior, and the small cameras borne in a straight line by study animals offer a reliable alternative to direct observation. One possible way to make animal welfare assessments easier and faster could be the application of audio and video data analysis. In this research, the main goal is to reach the requirements determination, and the construction to build a concurrent alternative to CCTV software based on new proprietary software, developed in Matlab® language, to record and capture video sequences in digital memory hardware. The proposed software stakeholders’ needs are written attending the specification in the ISO/IEC/IEEE 29148:2011 standard, and the life cycle adapted to the development was based in the standard ISO/IEC/IEEE 12207:2008. The main user interface was generated using the Matlab® GUI (Graphical User Interface). In the results, a resumed table with the final document of Requirement Specification (StRS) was generated and the main interface is coded. The system validation took place in the animal houses (bioterium) over a period of three months and the data collection and software usability reach the attendance to all the requirements listed. Thus, in the conclusions, it was observed that its users considered the developed software a good tool to help researches in the poultry and laying hens’ facility (bioterium).

The Embry-Riddle Aeronautical University (ERAU) Spacesuit Utilization of Innovative Technology Laboratory (S.U.I.T. Lab) is dedicated to the pursuit of advancing human spaceflight by contributing to spacesuit and operations research with experiential programs for students. A significant portion of the S.U.I.T. Lab’s portfolio is dedicated to the design and execution of spacesuit range of motion (ROM) investigations using video and motion capture systems. ROM biomechanical angles were measured using these techniques in conjunction with developing protocols for both simulated extravehicular activity suits at spaceflight analogue expeditions, and on ERAU campus with Final Frontier Design (FFD) intravehicular activity pressure suits. Designing protocols ensures effective communication for the analysis of simulated spacesuit performance to a remote crew. With communication delays to Earth, a self-sufficient spacesuit diagnosis is required to provide future astronauts with immediate action to take when dealing with a malfunctioning spacesuit. The video capture methodology is designed so that any crew would be able to conduct recordings with minimal impact to their schedule and with camera resources that are standard equipment. Spaceflight mission analogues involved in this study include: Hawai'i Space Exploration Analog and Simulation (HI-SEAS Mission V, 2017); Mars Desert Research Station (MDRS Crew 188, 2018), and AMADEE-18 in Oman (2018). Video capture can be used to collaborate with several spacesuit manufacturers to offer a snapshot comparison between designs, validate and verify capabilities, and aid with the selection of the right suit for the right job. The analogue locations recorded unsuited and suited data, while the November FFD test focused on motion capture (with video capture taken for validation) of unsuited, suited unpressurized, and suited while pressurized to 3.5 psid conditions. Early results from the motion capture align with values estimated from vid

Inspiring Science Education (ISE) (http://www.inspiringscience.eu/) is an EU funded initiative that seeks to further the use of inquiry-based science learning (IBSL) through the medium of ICT in the classroom. The Basketball Shot is a scenario (lesson plan) that involves the use of video capture to help the student investigate the concepts of speed, velocity and acceleration. Using the LoggerPro® programme from Vernier Software and Technology (http://www.vernier.com/products/software/lp/), video is captured of a player throwing a ball towards the basket. The ball does not reach the basket, but instead bounces on the floor and continues its motion. The concept of constant velocity, vectors, acceleration in two dimensions is therefore demonstrated. Moreover, a connection with mathematics is established where the relevancy of linear and quadratic equations are clearly demonstrated in the context of the motion of the ball. The effectiveness of this lesson plan is evaluated through the lens of the “Conversational Framework” underpinned by the five stage inquiry-based learning approach.

Travel speed (average speed of travel while active) and day range (average speed over the daily activity cycle) are behavioural metrics that influence processes including energy use, foraging success, disease transmission and human-wildlife interactions, and which can therefore be applied to a range of questions in ecology and conservation. These metrics are usually derived from telemetry or direct observations. Here, we describe and validate an entirely new alternative approach, using camera traps recording passing animals to measure movement paths at very fine scale. Dividing the length of a passage by its duration gives a speed observation, and average travel speed is estimated by fitting size-biased probability distributions to a sample of speed observations. Day range is then estimated as the product of travel speed and activity level (proportion of time spent active), which can also be estimated from camera-trap data. We field tested the procedure with data from a survey of terrestrial mammals on Barro Colorado Island, Panama. Travel speeds and day ranges estimated for 12 species scaled positively with body mass, and were higher in faunivores than in herbivores, patterns that are consistent with those obtained using independent estimates derived from tracked individuals. Comparisons of our day range estimates with independent telemetry-based estimates for three species also showed very similar values in absolute terms. We conclude that these methods are accurate and ready to use for estimating travel speed and day range in wildlife. Key advantages of the methods are that they are non-invasive, and that measurements are made at very high resolution in time and space, yielding estimates that are comparable across species and studies. Combined with emerging techniques in computer vision, we anticipate that these methods will help to expand the range of species for which we can estimate movement rate in the wild.

Sunlight reflected on the moving sea surface, often referred to as glitter, is usually considered a hindrance to analysis of ocean scenes, and glitter removal algorithms are often employed in pre-processing of ocean imagery. However, glitter statistics can provide valuable insight into sea surface behavior, both from the standpoint of characterizing image clutter and gaining a better understanding of sea surface roughness. In this work, sun glitter is observed through shore-based video of the ocean collected at various optical wavelengths (visible and infrared), and various statistical properties of the collected video are analyzed., The original document contains color images.

This project's main objective is to evaluate the performance of the capture made by Elphel 353 camera. The assessment will serve as a starting point for the integration of these cameras in the new Smart room built in the Department of Signal Theory and Communications ,UPC (Universitat Politècnica de Catalunya). First the most important properties of the camera and the tools provided by the camera are described, Next, we study how to use these tools to get images in two capture modes, online and offline. Once we know how to get images, we define the methods used for evaluation, finally the capture is evaluated and the results and conclusions are presented.

Tato práce se zaměřuje na vytvoření modulárního systému, který by poskytoval možnosti zachytávání videí a screencastů z výuky na UTB. Systém je koncipován jako webový portál s architekturou klient-server. Klientská část obsahuje funkce pro vysílání streamů z dostupných multimediálních zařízení po lokální síti. Dále je v klientské aplikace určené pro operační systém Microsoft Windows přidána funkce pro ukládání zachyceného videa do souboru. Server poté obsahuje funkce na zachytávání video ze streamů a následnou distribuci po internetové síti pomocí torrentů. Webové aplikace použité v projektu jsou chráněny přihlašovacím jménem a heslem. Uživatelé jsou rozděleni do skupin a je jim možno definovat přístup do jednotlivých částí systému. K vytvoření systému byly použity následující technologie: .NET Framework 3.0 (desktopová aplikace), HTML, PHP5, Python, JavaScript. Data systému jsou uložena v databázi MySQL. Jádro systému je modulární a je možno jej jednoduše rozšířit., The aim of this master thesis is to create the modular system, which provides capability for capturing videos and screen casts from the education on UTB in Zlin. System is structured as website with client-server architecture. Client part contains functions for sending streams from accessible multimedia devices to local area network. Client application for Microsoft Windows OS has added function for saving captured videos to the file. Server part contains functions for capturing video from streams and for successive distributing on the Internet using torrent files. Web applications used in this system are secured by login name and password. Users of this application are sorted to user groups and they have a specific access rights to the system. There are used these technologies for developing the system: NET Framework 3.0 (desktop application), HTML, PHP5, Python, Java Script. Data of the system are stored in MySQL database. System core has modular architecture and it is easy to extend it., Ústav aplikované informatiky, obhájeno

This paper describes a modular system, which provides capability for capturing videos and screen casts from lectures and presentations in any academic or commercial environment. The system uses client-server architecture. Client node sends streams from available multimedia devices to local area network The server provides functions for capturing video from streams and for distributing the captured video files using torrent. For protecting the video files, the web-based user interface provides authentication and authorization similar to the traditional Unix file permissions system.

This paper describes a modular system, which provides capability for capturing videos and screen casts from lectures and presentations in any academic or commercial environment. The system uses client-server architecture. Client node sends streams from available multimedia devices to local area network The server provides functions for capturing video from streams and for distributing the captured video files using torrent. For protecting the video files, the web-based user interface provides authentication and authorization similar to the traditional Unix file permissions system.

Distance Learning Environments (DLEs) are elusive to define, difficult to successfully implement and costly due to their proprietary nature. With few open-source solutions, organizations are forced to invest large amounts of their resources in the procurement and support of proprietary products. Once an organization has chosen a particular solution, it becomes prohibitively expensive to choose another path later in the development process. The resolution to these challenges is realized in the use of open-standards, no proprietary solutions. This thesis explores the multiple definitions of DLEs, defines metrics of successful implementation and develops open-source solutions for the delivery of multimedia in the Distance Learning Environment. Through the use of the Java Media Framework API, multiple tools are created to increase the transmission, capture and availability of multimedia content. Development of this technology, through the use of case studies, leaves a legacy of lectures and knowledge on the Internet to entertain and enlighten future generations., "The original document contains color images"

The motion activated articulating seat (MAAS) is a pilot aid in lifting the shoulder/upper torso while flying and aircraft. The MAAS system has the ability to respond rapidly should the pilot require a different shoulder/ upper torso position in response to changing mission requirements, such as checking 6 . The approach uses a high speed desk top computer, a video camera, a specialized video processing capture board, a set of specifically geometrically designed air bags (three independently functionable) with operational valving, a modified cockpit seat with a 30 degree seat back angle, a flight helmet with identifiable indicators, and an in house developed operating software program. The system has been demonstrated statistically and successfully processed head/ helmet movements for generating seat motion. The video capture technique is being applied to other laboratory research efforts., Prepared in collaboration with Systems Research Lab., Inc.

Práce se zabývá implementací aplikace, která umožňuje zabezpečení prostoru pomocí web kamery a OS Linux. Hlavní součástí aplikace je proces běžící v pozadí, který komunikuje s kamerou přes V4L rozhraní. Pomocí dynamicky nahrávaných modulů se provádí detekce pohybu ve snímané scéně. Algoritmus detekce lze jednoduše měnit pomocí uživatelských modulů. Aplikace umožňuje ukládat snímaná data ve formě obrázků nebo video souborů. Pro monitorování snímané scény v reálném čase byl implementován klient, který umožňuje připojení přes TCP/IP k hlavní aplikaci. V komunikačním protokolu je implementována i jednoduchá autentizace klientů a šifrování přenášených dat., This thesis deals with the implementation of security guard software for OS Linux using an appropriate web camera. The main part of this application is process running in background using V4L application interface to communicate with web cam. Because this program uses dynamically loaded plug-ins for motion detection, it is very simple to change detection algorithm just by modifying configuration file. Application data can be saved as images or video files. Client application was created for online monitoring by user. It communicates with security guard software over network by TCP/IP protocol. Implemented application layer protocol allows simple client authentication and data encryption.

Obsahem této práce je mobilní aplikace pro platformu iOS. Aplikace cílí na sportovce, kterým by měla pomoci během tréninků a slouží jako nástroj pro automatické zaznamenávání krátkých videí. Implementace proběhla v programovacím jazyce Swift, s využitím frameworku AVFoundation. Aplikace má, pomocí modelu CoreML, implementovanou detekci lidské postavy, a je tak schopna rozeznávat pohyby člověka. Díky tomu zaznamenává pouze stěžejní herní momenty. Krátký videozáznam, zachycený pomocí této aplikace, pak obsahuje několik sekund, které předcházely hernímu momentu, a také několik sekund, které herní moment následují., The content of this work is a mobile application for the iOS platform. The application is aimed at athletes, whom it should help during their training, and serves as a tool for automatically recording short snippets of video. The implementation is in Swift using the AVFoundation framework. The application has implemented the human pose detector using the CoreML model and can recognize certain game moments which will be captured. The short video snippet recorded with this application then contains the few seconds that preceded the game moment and also the few seconds that followed.

Obsahem této práce je mobilní aplikace pro platformu iOS. Aplikace cílí na sportovce, kterým by měla pomoci během tréninků a slouží jako nástroj pro automatické zaznamenávání krátkých videí. Implementace proběhla v programovacím jazyce Swift, s využitím frameworku AVFoundation. Aplikace má, pomocí modelu CoreML, implementovanou detekci lidské postavy, a je tak schopna rozeznávat pohyby člověka. Díky tomu zaznamenává pouze stěžejní herní momenty. Krátký videozáznam, zachycený pomocí této aplikace, pak obsahuje několik sekund, které předcházely hernímu momentu, a také několik sekund, které herní moment následují., The content of this work is a mobile application for the iOS platform. The application is aimed at athletes, whom it should help during their training, and serves as a tool for automatically recording short snippets of video. The implementation is in Swift using the AVFoundation framework. The application has implemented the human pose detector using the CoreML model and can recognize certain game moments which will be captured. The short video snippet recorded with this application then contains the few seconds that preceded the game moment and also the few seconds that followed.

Práce se zabývá implementací aplikace, která umožňuje zabezpečení prostoru pomocí web kamery a OS Linux. Hlavní součástí aplikace je proces běžící v pozadí, který komunikuje s kamerou přes V4L rozhraní. Pomocí dynamicky nahrávaných modulů se provádí detekce pohybu ve snímané scéně. Algoritmus detekce lze jednoduše měnit pomocí uživatelských modulů. Aplikace umožňuje ukládat snímaná data ve formě obrázků nebo video souborů. Pro monitorování snímané scény v reálném čase byl implementován klient, který umožňuje připojení přes TCP/IP k hlavní aplikaci. V komunikačním protokolu je implementována i jednoduchá autentizace klientů a šifrování přenášených dat., This thesis deals with the implementation of security guard software for OS Linux using an appropriate web camera. The main part of this application is process running in background using V4L application interface to communicate with web cam. Because this program uses dynamically loaded plug-ins for motion detection, it is very simple to change detection algorithm just by modifying configuration file. Application data can be saved as images or video files. Client application was created for online monitoring by user. It communicates with security guard software over network by TCP/IP protocol. Implemented application layer protocol allows simple client authentication and data encryption.

Van der Westhuizen, Y., & Chai, D. (2018). 3D dynamic barcode. Electronics Letters, 54(17), 1024-1026. Available here

Operational knowledge in industries is difficult to capture because of the tacit nature of gestures. The operators can be equipped with video capture devices. They can also be invited to describe the intentions of their gesture. But the bottleneck is in the gesture itself. This paper describes an experiment, which was performed at EDF (Electricité de France). Several categories of professional gestures were studied, and 10 of them were investigated. For the capture phase, the protocol aims to approach the intentions of operators, their mental models. We have produced training video material called "MAP" (Multimedia Apprenticeship Platform) for novices to learn and internalize the practice. An anthropocentric three-step methodology was applied. For all the gestures, eight descriptors were used to qualify the environment and the situation: realism, reproducibility, length, granularity, mobility, interaction, visual salience and haptic salience. A four-value scale is used on each descriptor to quantify the criticism of the gestures. Results include the perimeter of application of the MAP methodology, describing professional gestures which can be captured, formalized and transmitted. The majority of the descriptors have a moderated influence on the process, concentrating their impact on one point of the method. Only two descriptors have high-level impact on the whole process: interaction between operators and visual dimension during the realization of the professional gesture.

Práce se zabývá implementací aplikace, která umožňuje zabezpečení prostoru pomocí web kamery a OS Linux. Hlavní součástí aplikace je proces běžící v pozadí, který komunikuje s kamerou přes V4L rozhraní. Pomocí dynamicky nahrávaných modulů se provádí detekce pohybu ve snímané scéně. Algoritmus detekce lze jednoduše měnit pomocí uživatelských modulů. Aplikace umožňuje ukládat snímaná data ve formě obrázků nebo video souborů. Pro monitorování snímané scény v reálném čase byl implementován klient, který umožňuje připojení přes TCP/IP k hlavní aplikaci. V komunikačním protokolu je implementována i jednoduchá autentizace klientů a šifrování přenášených dat., This thesis deals with the implementation of security guard software for OS Linux using an appropriate web camera. The main part of this application is process running in background using V4L application interface to communicate with web cam. Because this program uses dynamically loaded plug-ins for motion detection, it is very simple to change detection algorithm just by modifying configuration file. Application data can be saved as images or video files. Client application was created for online monitoring by user. It communicates with security guard software over network by TCP/IP protocol. Implemented application layer protocol allows simple client authentication and data encryption.

Obsahem této práce je mobilní aplikace pro platformu iOS. Aplikace cílí na sportovce, kterým by měla pomoci během tréninků a slouží jako nástroj pro automatické zaznamenávání krátkých videí. Implementace proběhla v programovacím jazyce Swift, s využitím frameworku AVFoundation. Aplikace má, pomocí modelu CoreML, implementovanou detekci lidské postavy, a je tak schopna rozeznávat pohyby člověka. Díky tomu zaznamenává pouze stěžejní herní momenty. Krátký videozáznam, zachycený pomocí této aplikace, pak obsahuje několik sekund, které předcházely hernímu momentu, a také několik sekund, které herní moment následují., The content of this work is a mobile application for the iOS platform. The application is aimed at athletes, whom it should help during their training, and serves as a tool for automatically recording short snippets of video. The implementation is in Swift using the AVFoundation framework. The application has implemented the human pose detector using the CoreML model and can recognize certain game moments which will be captured. The short video snippet recorded with this application then contains the few seconds that preceded the game moment and also the few seconds that followed.

Obsahem této práce je mobilní aplikace pro platformu iOS. Aplikace cílí na sportovce, kterým by měla pomoci během tréninků a slouží jako nástroj pro automatické zaznamenávání krátkých videí. Implementace proběhla v programovacím jazyce Swift, s využitím frameworku AVFoundation. Aplikace má, pomocí modelu CoreML, implementovanou detekci lidské postavy, a je tak schopna rozeznávat pohyby člověka. Díky tomu zaznamenává pouze stěžejní herní momenty. Krátký videozáznam, zachycený pomocí této aplikace, pak obsahuje několik sekund, které předcházely hernímu momentu, a také několik sekund, které herní moment následují., The content of this work is a mobile application for the iOS platform. The application is aimed at athletes, whom it should help during their training, and serves as a tool for automatically recording short snippets of video. The implementation is in Swift using the AVFoundation framework. The application has implemented the human pose detector using the CoreML model and can recognize certain game moments which will be captured. The short video snippet recorded with this application then contains the few seconds that preceded the game moment and also the few seconds that followed.

Obsahem této práce je mobilní aplikace pro platformu iOS. Aplikace cílí na sportovce, kterým by měla pomoci během tréninků a slouží jako nástroj pro automatické zaznamenávání krátkých videí. Implementace proběhla v programovacím jazyce Swift, s využitím frameworku AVFoundation. Aplikace má, pomocí modelu CoreML, implementovanou detekci lidské postavy, a je tak schopna rozeznávat pohyby člověka. Díky tomu zaznamenává pouze stěžejní herní momenty. Krátký videozáznam, zachycený pomocí této aplikace, pak obsahuje několik sekund, které předcházely hernímu momentu, a také několik sekund, které herní moment následují., The content of this work is a mobile application for the iOS platform. The application is aimed at athletes, whom it should help during their training, and serves as a tool for automatically recording short snippets of video. The implementation is in Swift using the AVFoundation framework. The application has implemented the human pose detector using the CoreML model and can recognize certain game moments which will be captured. The short video snippet recorded with this application then contains the few seconds that preceded the game moment and also the few seconds that followed.

Práce se zabývá implementací aplikace, která umožňuje zabezpečení prostoru pomocí web kamery a OS Linux. Hlavní součástí aplikace je proces běžící v pozadí, který komunikuje s kamerou přes V4L rozhraní. Pomocí dynamicky nahrávaných modulů se provádí detekce pohybu ve snímané scéně. Algoritmus detekce lze jednoduše měnit pomocí uživatelských modulů. Aplikace umožňuje ukládat snímaná data ve formě obrázků nebo video souborů. Pro monitorování snímané scény v reálném čase byl implementován klient, který umožňuje připojení přes TCP/IP k hlavní aplikaci. V komunikačním protokolu je implementována i jednoduchá autentizace klientů a šifrování přenášených dat., This thesis deals with the implementation of security guard software for OS Linux using an appropriate web camera. The main part of this application is process running in background using V4L application interface to communicate with web cam. Because this program uses dynamically loaded plug-ins for motion detection, it is very simple to change detection algorithm just by modifying configuration file. Application data can be saved as images or video files. Client application was created for online monitoring by user. It communicates with security guard software over network by TCP/IP protocol. Implemented application layer protocol allows simple client authentication and data encryption.

Práce se zabývá implementací aplikace, která umožňuje zabezpečení prostoru pomocí web kamery a OS Linux. Hlavní součástí aplikace je proces běžící v pozadí, který komunikuje s kamerou přes V4L rozhraní. Pomocí dynamicky nahrávaných modulů se provádí detekce pohybu ve snímané scéně. Algoritmus detekce lze jednoduše měnit pomocí uživatelských modulů. Aplikace umožňuje ukládat snímaná data ve formě obrázků nebo video souborů. Pro monitorování snímané scény v reálném čase byl implementován klient, který umožňuje připojení přes TCP/IP k hlavní aplikaci. V komunikačním protokolu je implementována i jednoduchá autentizace klientů a šifrování přenášených dat., This thesis deals with the implementation of security guard software for OS Linux using an appropriate web camera. The main part of this application is process running in background using V4L application interface to communicate with web cam. Because this program uses dynamically loaded plug-ins for motion detection, it is very simple to change detection algorithm just by modifying configuration file. Application data can be saved as images or video files. Client application was created for online monitoring by user. It communicates with security guard software over network by TCP/IP protocol. Implemented application layer protocol allows simple client authentication and data encryption.

Práce se zabývá implementací aplikace, která umožňuje zabezpečení prostoru pomocí web kamery a OS Linux. Hlavní součástí aplikace je proces běžící v pozadí, který komunikuje s kamerou přes V4L rozhraní. Pomocí dynamicky nahrávaných modulů se provádí detekce pohybu ve snímané scéně. Algoritmus detekce lze jednoduše měnit pomocí uživatelských modulů. Aplikace umožňuje ukládat snímaná data ve formě obrázků nebo video souborů. Pro monitorování snímané scény v reálném čase byl implementován klient, který umožňuje připojení přes TCP/IP k hlavní aplikaci. V komunikačním protokolu je implementována i jednoduchá autentizace klientů a šifrování přenášených dat., This thesis deals with the implementation of security guard software for OS Linux using an appropriate web camera. The main part of this application is process running in background using V4L application interface to communicate with web cam. Because this program uses dynamically loaded plug-ins for motion detection, it is very simple to change detection algorithm just by modifying configuration file. Application data can be saved as images or video files. Client application was created for online monitoring by user. It communicates with security guard software over network by TCP/IP protocol. Implemented application layer protocol allows simple client authentication and data encryption.

Obsahem této práce je mobilní aplikace pro platformu iOS. Aplikace cílí na sportovce, kterým by měla pomoci během tréninků a slouží jako nástroj pro automatické zaznamenávání krátkých videí. Implementace proběhla v programovacím jazyce Swift, s využitím frameworku AVFoundation. Aplikace má, pomocí modelu CoreML, implementovanou detekci lidské postavy, a je tak schopna rozeznávat pohyby člověka. Díky tomu zaznamenává pouze stěžejní herní momenty. Krátký videozáznam, zachycený pomocí této aplikace, pak obsahuje několik sekund, které předcházely hernímu momentu, a také několik sekund, které herní moment následují., The content of this work is a mobile application for the iOS platform. The application is aimed at athletes, whom it should help during their training, and serves as a tool for automatically recording short snippets of video. The implementation is in Swift using the AVFoundation framework. The application has implemented the human pose detector using the CoreML model and can recognize certain game moments which will be captured. The short video snippet recorded with this application then contains the few seconds that preceded the game moment and also the few seconds that followed.

This paper explores the potential of video capture to generate a collaborative space for teacher preparation; a space in which traditional hierarchies and boundaries between actors (student teacher, school mentor and university tutor) and knowledge (academic, professional and practical) are disrupted. The study, based in a teacher education department in an English university, is contextualised in the policy context of school–university partnerships. Video capture is used as a vehicle to promote dialogue and collaborative practice between partners during school-based elements of a teacher preparation course. Analysis highlights the power of this space to promote reciprocal learning across the partnership.

This paper explores the potential of video capture to generate a collaborative space for teacher preparation; a space in which traditional hierarchies and boundaries between actors (student teacher, school mentor and university tutor) and knowledge (academic, professional and practical) are disrupted. The study, based in a teacher education department in an English university, is contextualised in the policy context of school–university partnerships. Video capture is used as a vehicle to promote dialogue and collaborative practice between partners during school-based elements of a teacher preparation course. Analysis highlights the power of this space to promote reciprocal learning across the partnership.

This paper explores the potential of video capture to generate a collaborative space for teacher preparation; a space in which traditional hierarchies and boundaries between actors (student teacher, school mentor and university tutor) and knowledge (academic, professional and practical) are disrupted. The study, based in a teacher education department in an English university, is contextualised in the policy context of school–university partnerships. Video capture is used as a vehicle to promote dialogue and collaborative practice between partners during school-based elements of a teacher preparation course. Analysis highlights the power of this space to promote reciprocal learning across the partnership.