This thesis deals with problems of recognition of an electrometer´s state from sensing image. It is tangibly about electrometer´s scanning by a mobile phone´s camera. There is a surface with an electrometer´s dial which is detected and on this surface the particular numbers are detected consequently. The numbers are recognized via neural network. For more information from this image there are used some techniques of image segmentation to check the status. For the classification of the segmentation´s outputs are used classification tools, especially a support vector machine (SVM) and neural networks. Problems of image segmentations are solved by using OpenCV library. OpenCV is used for the implementation of the vector machine either. Application is on Android platform. Part of the thesis is concerned in a creation of a desktop application which is instrumental towards testing of neural network. The thesis also describes how to save the necessary data gathering in the course of the recognition which are used for working with neural network. The part of the thesis also deals with running web which will be evolved for the opportunity to participate in the further development of the system. There is available a public repository with source codes created during implementation.

Submitted by Alex Sandro R?go (alex@ifpb.edu.br) on 2016-11-23T18:41:52Z No. of bitstreams: 1 IDENTIFICA??O E CLASIFICA??O DE SINALIZA??O HORIZONTAL EM AUTOVIAS UTILIZANDO OPENCV_Francisco_Alves.pdf: 5288985 bytes, checksum: e866e75315506b47d3d232ff39ce4a97 (MD5) / Approved for entry into archive by Alex Sandro R?go (alex@ifpb.edu.br) on 2016-11-23T18:43:51Z (GMT) No. of bitstreams: 1 IDENTIFICA??O E CLASIFICA??O DE SINALIZA??O HORIZONTAL EM AUTOVIAS UTILIZANDO OPENCV_Francisco_Alves.pdf: 5288985 bytes, checksum: e866e75315506b47d3d232ff39ce4a97 (MD5) / Made available in DSpace on 2016-11-23T18:43:51Z (GMT). No. of bitstreams: 1 IDENTIFICA??O E CLASIFICA??O DE SINALIZA??O HORIZONTAL EM AUTOVIAS UTILIZANDO OPENCV_Francisco_Alves.pdf: 5288985 bytes, checksum: e866e75315506b47d3d232ff39ce4a97 (MD5) Previous issue date: 2016-11-23 / Acidentes de tr?nsito podem ser fatais, causando a morte ou invalidez de motoristas e pedestres. Desta forma, muitos pesquisadores est?o desenvolvendo meios para deixar os ve?culos mais seguros, atrav?s do uso de sistemas de apoio ? condu??o que auxiliem os motoristas nas mais diversas situa??es no tr?nsito. O objetivo deste trabalho ? propor um sistema para detec??o e classifica??o de linhas de sinaliza??o horizontais em autovias. Sistemas deste tipo podem ajudar a diminuir a quantidade de acidentes de tr?nsito, auxiliando o condutor do ve?culo a permanecer em sua faixa e realizar ultrapassagens apenas em locais permitidos. As imagens das autovias, capturadas por uma c?mera fixada ao para-brisa no interior do ve?culo, s?o analisadas quadro a quadro em tempo real. O sistema proposto foi desenvolvido na linguagem de programa??o C++, utilizando a biblioteca OpenCV, de c?digo aberto, amplamente empregada em vis?o computacional. Dentre outras t?cnicas, utilizou-se o detector de bordas de Canny e a Transformada Probabil?stica de Hough para identifica??o de segmentos de reta. Adicionalmente, foram desenvolvidos m?todos geom?tricos para otimiza??o e elimina??o de segmentos desnecess?rios e um algoritmo para estima??o do ponto de fuga, o qual auxilia na identifica??o dos segmentos mais relevantes para o sistema. Foram realizados sete experimentos apresentando diferentes n?veis de dificuldade. Acur?cias na faixa de valores de 86,58% a 100% foram alcan?adas. Em m?dia, os experimentos obtiveram uma acur?cia de 94,56% na classifica??o dos diferentes tipos de sinaliza??es horizontais.

Datorseende är ett snabbt växande, tvärvetenskapligt forskningsområde vars tillämpningar tar en allt mer framskjutande roll i dagens samhälle. Med ett ökat intresse för datorseende ökar också behovet av att kunna kontrollera kameror kopplade till datorseende system. Vid Linköpings tekniska högskola, på avdelningen för datorseende, har ramverket EDSDK++ utvecklats för att fjärrstyra digitala kameror tillverkade av Canon Inc. Ramverket är mycket omfattande och innehåller en stor mängd funktioner och inställningsalternativ. Systemet är därför till stor del ännu relativt oprövat. Detta examensarbete syftar till att utveckla ett demonstratorsystem till EDSDK++ i form av ett enkelt active vision system, som med hjälp av ansiktsdetektion i realtid styr en kameratilt, samt en kamera monterad på tilten, till att följa, zooma in och fokusera på ett ansikte eller en grupp av ansikten. Ett krav var att programbiblioteket OpenCV skulle användas för ansiktsdetektionen och att EDSDK++ skulle användas för att kontrollera kameran. Dessutom skulle ett API för att kontrollera kameratilten utvecklas. Under utvecklingsarbetet undersöktes bl.a. olika metoder för ansiktsdetektion. För att förbättra prestandan användes multipla ansiktsdetektorer, som med hjälp av multitrådning avsöker en bild parallellt från olika vinklar. Såväl experimentella som teoretiska ansatser gjordes för att bestämma de parametrar som behövdes för att kunna reglera kamera och kameratilt. Resultatet av arbetet blev en demonstrator, som uppfyllde samtliga krav. / Computer vision is a rapidly growing, interdisciplinary field whose applications are taking an increasingly prominent role in today's society. With an increased interest in computer vision there is also an increasing need to be able to control cameras connected to computer vision systems. At the division of computer vision, at Linköping University, the framework EDSDK++ has been developed to remotely control digital cameras made by Canon Inc. The framework is very comprehensive and contains a large amount of features and configuration options. The system is therefore largely still relatively untested. This thesis aims to develop a demonstrator to EDSDK++ in the form of a simple active vision system, which utilizes real-time face detection in order to control a camera tilt, and a camera mounted on the tilt, to follow, zoom in and focus on a face or a group of faces. A requirement was that the OpenCV library would be used for face detection and EDSDK++ would be used to control the camera. Moreover, an API to control the camera tilt was to be developed. During development, different methods for face detection were investigated. In order to improve performance, multiple, parallel face detectors using multithreading, were used to scan an image from different angles. Both experimental and theoretical approaches were made to determine the parameters needed to control the camera and camera tilt. The project resulted in a fully functional demonstrator, which fulfilled all requirements.

The aim of this thesis was to create two applications for people with learning difficulties. The first, i-CT Framwork, is also an executable application to be used with the target group mentioned above. As an executable application, i-CT Framework operates as a central tool for managing users, applications, and user restrictions. Development of Gesture Translator application presented another aim of the thesis: this application can translate sign language gestures for people with learning difficulties. Both applications are functioning on Android as well as iOS operating systems.

This diploma thesis deals with design of embedded computer vision system and transfer of existing computer vision application for 3D object detection from Windows OS to designed embedded system with Linux OS. Thesis focuses on design of communication interface for system control and camera video transfer through local network with video compression. Then, detection algorithm is enhanced by transferring computationally expensive functions to GPU using CUDA technology. Finally, a user application with graphical interface is designed for system control on Windows platform.

Master’s thesis deals with object pose estimation using monocular camera. As an object is considered every rigid, shape fixed entity with strong edges, ideally textureless. Object position in this work is represented by transformation matrix, which describes object translation and rotation towards world coordinate system. First chapter is dedicated to explanation of theory of geometric transformations and intrinsic and extrinsic parameters of camera. This chapter also describes detection algorithm Chamfer Matching, which is used in this work. Second chapter describes all development tools used in this work. Third, fourth and fifth chapter are dedicated to practical realization of this works goal and achieved results. Last chapter describes created application, that realizes known object pose estimation in scene.

This thesis studies several methods for enhancing details in digital photographs. Methods' algorithms are described and implemented to existing system using C++ and OpenCV. Methods are then compared in terms of the time and memory complexity and their results are evaluated using users' questionnaire. Work overally gives overview of present photographic detail enhancement methods and discuses their future development.

The main aim of this master’s thesis is to get acquainted with the theory of the current segmentation methods, that use deep learning. Segmentation neural network that will be capable of segmenting individual instances of the objects will be proposed and created based on theoretical knowledge. The main focus of the segmentation neural network will be segmentation of electronic components from printed circuit boards.

This diploma thesis summarizes the knowledge about microalgae, their use, cultivation methods and obstacles that prevent their wider use. In the practical part of the work, a device was designed, constructed, and programmed. This device can analyze the bubbles of the tubular photobioreactor and, based on the obtained data, control its aeration. The Python programming language was used to create the program and the OpenCV library was used to analyze the photographs. The bubble detection is based on the edge detection and the subsequent refinement. The data obtained from the analysis are displayed on the device screen and the data are also stored in a csv file. The discussion lists possible improvements and lessons learned during the creation of this device.

The master thesis maps the state of the art of visual object tracking in panoramic 360° video. The thesis aims to reveal the main problems related to visual object tracking and moreover focuses on their solution in panoramic videos. In the study of the existing approaches was found that very few solutions of visual object tracking in equirectangular projection of panoramic video have been implemented so far. This thesis therefore presents two improvements of object tracking methods that are based on the adaptation of equirectangular frames. In addition, this thesis brings the manually created dataset of panoramic videos with more than 9900 annotations. Finally the detailed evaluation of 12 well known and state of the art trackers has been performed for this new dataset.