|
|
Recognition of Vehicle Class in Image
Čabala, Roman ; Kodym, Oldřich (referee) ; Špaňhel, Jakub (advisor)
The goal of this bachelor thesis is to recognize the type of vehicle from the image using neural networks. Vehicles are divided into 6 types, namely a car, a small van, a van, a mini truck, a truck and a bus. The data set was picked from videos that record the trajectory of the vehicles. Subsequently, an image annotation tool was built. The following architectures were used for network training: VGG16, ResNet50, Xception, InceptionResNet-v2. The result of the work is a comparison of architectures. All architectures were trained and achieved a result above 90%.
|
|
|
Context-Aware Notification Filter for Android
Jaklovský, Samuel ; Špaňhel, Jakub (referee) ; Szentandrási, István (advisor)
The goal of this thesis is to develop an application for devices running Android which will determine user profile, based on obtained context, and apply user pre-defined sound settings for this profile. The thesis contains a description of common theory and design of user interface which was implemented as fully operational application. The application uses Naive Bayes classifier and Decision tree for determining the user profile. The functionality of the application was successfully tested by twenty users. The average ratings in the questionnaires were about eight and a half points from a possible maximum of ten. These results can be considered successful.
|
|
|
Web-Based Image Annotation Tool
Dvořáček, David ; Kapinus, Michal (referee) ; Špaňhel, Jakub (advisor)
This work deals with the creation of web tool for image data annotation. The theoretical part specifies the application, its design and functionality. The practical part deals with the implementation of the web tool for image data annotation such as point, line, rectangle, polygon with focus on modularity and easy extensibility of the tool for various types of annotations and implementation of image manipulation and transformation functions. For practical part of this work was used library Flask using Python, HTML, Javascript. The tool was created and developed iteratively.
|
|
|
On-Board License Plate Detection and Recognition
Tomovič, Martin ; Sochor, Jakub (referee) ; Špaňhel, Jakub (advisor)
This Bachelor's thesis aims to create an aplication for detection and recognition of license plates suitable for real-time processing. The work contains analysis of available methods. Part of the work is focused on present form of licence plates in Czech Republic. As a result of work, new data set was created and computer application was implemented. The application uses existing libraries designed for computer vision and machine learning with main purpose to detect and recognize licence plates from video. Detection is realized with help of cascade classifier, and recognition by Perceptron neural network. Final chapter subsequently contains evaluation of success rate of implemented solution.
|
|
|
Vehicle Make and Model Recognition in Image
Buchta, Martin ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
This thesis deals with classification of a car model from an image. It describes several methods, such as convolutional neural networks, methods limited to the fron/rear view and methods using 3D CAD models. From these approaches it chooses convolutional neural networks, which it further deals with. The work contains a description of the individual layers of which such a network consists. The practical part describes the procedure by which the classifier, that has an accuracy of 80.7\,\%, was created. A dataset containing 1\,034 photos was created to verify functionality. The work further experiments with different architectures and evaluates their accuracy. The work contains a program which, thanks to the car detector, finds the vehicle in the video and marks it with a square and a description of the car model in the given video.
|
|
|
Fine-Grained Vehicle Recognition from Traffic Surveillance Camera
Mencner, Pavel ; Špaňhel, Jakub (referee) ; Sochor, Jakub (advisor)
The aim of this thesis is image based detection of vehicles from traffic surveillance camera and fine-grained vehicle type recognition (manufacturer and model). In the thesis the Unpack normalization method is implemented which transforms the vehicle image into its apparent flat representation in order to increase the classifier's success rate. The Unpack method make use of 3D bounding box of the vehicle. This bounding box is constructed during test period using the information of vehicle contour and direction toward vanishing points. The thesis involve accuracy comparison between direct and Unpack classification methods. The proposed solution is based on several related parts that benefit from convolutional neural networks. These parts are: vehicle detection from image data, estimation of the directions towards vanishing points solved as classification task, vehicle contour detection using convolutional Encoder-Decoder network and fine-grained vehicle type classification. Using Unpack based classification the 2% accuracy improvement against direct classification has been achieved, resulting in 86% overall success rate. The outcome of this thesis is fine-grained vehicle classification system that works with traffic surveillance video without any viewpoint limitations.
|
|
|
License Plate Detection and Recognition from Still Image
Janíček, Kryštof ; Sochor, Jakub (referee) ; Špaňhel, Jakub (advisor)
This thesis describes the design and implementation of system for detection and recognition of license plate. This system is divided into three parts which are license plate detection, character segmentation and optical character recognition. License plate detection is done by cascade classifier that achieves hit rate of 95.5% and precision rate of 95.9%. Character segmentation is based on contour finding that achieves hit rate of 93.3% and precision rate of 96.5%. Optical character recognition is done by neural network and achieves hit rate of 98.4% for individual characters. The whole system is able to detect and recognize up to 81.5% of license plates from the test data set.
|
|
|
Web App for Management of Appointments
Balajka, Pavel ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
The aim of this work is to create an aplication that allows lectors create and manage consultation appointments on which students will be able to sing on. Therefore a web application designed to run on a server was created, that lectors and students can access with an internet browser. The mentioned problem is solved in a way which simplifies the work of its users and offers them additional possibilities regarding consultation management. For example, the application is able to send a notification when a section of a consultation becomes available or to show consultation's history - which user has done what action with a chosen consultation. The procedure of simple usage of the application is the following: Lector creates a consultation - chooses date, time and number of sections. Student selects a lector in the appliacion, displays his consultations, chooses desired time and signs on the consultation by just one click. Application was developed primarily for university lectors and students but it can be as well used by other subjects that need or want a system where they can create an event on which other people can sign on.
|
|
|
Vehicle Collision Detection
Kruták, Martin ; Sochor, Jakub (referee) ; Špaňhel, Jakub (advisor)
This bachelor thesis decribes a system for detection and tracking of multiple vehicles from a surveillance camera with a collision detection. The focus is on detection and prediction of collisions of vehicles in one direction - towards the camera. System is not fully automatic, meaning that some initial settings are needed (e.g. lines on the road) to quarantee a good functionality of the system. Accurate vehicles' contour is obtained in the detection phase, and object centroids are calculated. Each detected vehicle is assigned to the specific lane and tracked separately. This thesis then describes the method of prediction and detection of a collision. A rectangle is created around the ground part of every vehicle. This rectangle of each of the vehicles is enlarged and checked for the overlaps. Those rectangles that overlaps are then subject to further analysis for the collision detection. Experimental results show a success rate of 72 % for the accurate rectangle construction being a crucial part for the collision detection. The advantage of the proposed system is its possible usage in surveillance cameras monitoring the traffic flow on highways.
|
|
|
Visual Localization of Chess Pieces
Hampl, Tomáš ; Špaňhel, Jakub (referee) ; Hradiš, Michal (advisor)
The main goal of this thesis was to analyze state of the chess game and to locate chess pieces on the chessboard. Chessboard recognition is based on locating lines in image using Hough transform and PClines. The figures were detected by models of convolutional neural networks - YOLOv3, YOLOv4 and YOLOv4 tiny. Evaluation was perfomed on our data set. Chessboard detection achieves accuracy of 97%, complete localization of the state reaches 74,5% and piece localization 96%.
|
guest ::
RSS feed.