|
|
Apparent Personality Analysis from Video
Čigáš, Patrik ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
This bachelor thesis deals with experiments with systems for apparent personality analysis from video, and compares accuracy of these systems. Systems from the experiments are created by linear regression and convolutional neural networks. Experiments compare accuracy of linear regressors processing visual and audial modality of video. On spectograms made from audial modality of video, thesis evaluates results of convolutional neural networks with varying number of convolutional and fully connected layers nad subsequently compares accuracy of regression solution and classification solution of the problem. For visual modality of video the thesis compares information values of gaze movement and face landmarks movement. System processing face landmarks movement reaches the best results in the experiments.
|
|
|
Deep Learning for Facial Recognition in Video
Stratil, Jan ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
This bachelor's thesis deals with facial recognition in video using deep neural networks. This task is split into 2 parts. The first part deals with training network that produces compact feature vector which represents the face identity from a video frame. The second part deals with training aggregation network that aggregates those feature vectors into one. This aggregation is fast and it has shown that its results are better than naive pooling methods. Results are tested on the LFW dataset, where it achieves 92.8% accuracy and on the YTF dataset, where the accuracy is 84.06%.
|
|
|
Tracker of Motorcycle Trips for iOS
Pinka, Martin ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
The aim of the thesis is to create an innovative mobile application that can be used for tracking of motorcycle trips on iOS platform.The benefits include the improvement of automatic pause detection mechanism, which ignores movements that user do not want to include in the trip.Additionally, the application provides a way to organize records which helps user to find specific recorded trip. This is solved by using tags that can be added to the records. The solution greatly improves the speed of finding specific routes if the user honestly fills information about trips. The implementation part of the thesis describes the drawing of a very long colored polyline on the map where colors represent speed of passing the places.As a result of all the effort there is an innovative, functional application that is ready for real usage.
|
|
|
Vehicle Following Distance Estimation from Mobile Phone in Vehicle
Zemánek, Ondřej ; Špaňhel, Jakub (referee) ; Sochor, Jakub (advisor)
The aim of this bachelor thesis is to create a mobile application for Android that estimates the distance of vehicles based on vehicle size in the camera image of the mobile phone. The estimation of the following distance is evaluated based on known camera parameters, the average vehicle width and the size of image area that represents detected car. Vehicles and their licences plates are detected in the image using cascade classifiers. Licence plate is detected only in the area of the detected vehicle. A training dataset for cascade classifier was created as part of this work. The cascade classifier is designed for vehicle detection. This work is extended with feature that tracks following distance in time and warns you with an acoustic signal on sudden distances change. This thesis is divided into five main parts - comparison of existing solutions for distance estimation, review of object detection methods, application design, implementation and evaluation of detectors, distance evaluation.
|
|
|
License Plate Recognition
Mrhač, Ondřej ; Sochor, Jakub (referee) ; Navrátil, Jan (advisor)
This thesis talks about problematics of licence plate detection, licence plate recognitionand my implementation for device i.MX 6 Series of NXP semiconductors s.r.o company. Model program for licence plate detection and recognition is written with help of OpenCV library and engine Tesseract and it’s successfully put into operation on this device. Afterwards program was measured his runtime on PC and i.MX6 Series device and those measurements were compared. At the end of this thesis were found the most demanding parts of the program. Future changes and improvements were proposed.
|
|
|
Library for Multiplatform Development of Mobile Apps
Kovařík, Michal ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
This thesis addresses the issues when developing mobile applications for multiple operating systems and development environments, with the target being to create the ideal user interface library. A framework for HTML app development has been designed and implemented that is built on top of modern web standards, allowing the developer to create applications with a single codebase that will, when deployed, intelligently adapt to the device and operating system that they are being run on. Released as an open-source project and currently supporting Windows 10, Android, Chrome OS and Web. Flexus, a framework for building user interfaces, is in live use and active development.
|
|
|
Parallel Deep Learning
Šlampa, Ondřej ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
Aim of this thesis is to propose how to evaluate favourableness of parallel deep learning. In this thesis I analyze parallel deep learning and I focus on its length. I take into account gradient computation length and weight transportation length. Result of this thesis is proposal of equations, which can estimate the speedup on multiple workers. These equations can be used to determine ideal number of workers for training.
|
|
|
Reconstruction of 3D Information about Vehicles Passing in front of a Surveillance Camera
Dobeš, Petr ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
This master's thesis focuses on 3D reconstruction of vehicles passing in front of a traffic surveillance camera. Calibration process of surveillance camera is first introduced and the relation of automatic calibration with 3D information about observed traffic is described. Furthermore, Structure from Motion, SLAM, and optical flow algorithms are presented. A set of experiments with feature matching and the Structure from Motion algorithm is carried out to examine results on images of passing vehicles. Afterwards, the Structure from Motion pipeline is modified. Instead of using SIFT features, DeepMatching algorithm is utilized to obtain quasi-dense point correspondences for the subsequent reconstruction phase. Afterwards, reconstructed models are refined by applying additional constraints specific to the vehicle reconstruction task. The resultant models are then evaluated. Lastly, observations and acquired information about the process of vehicle reconstruction are utilized to form proposals for prospective design of an entirely custom pipeline that would be specialized for 3D reconstruction of passing vehicles.
|
|
|
Mobile System for Text Recognition on iOS
Bobák, Petr ; Sochor, Jakub (referee) ; Zemčík, Pavel (advisor)
This thesis describes a development of a modern client-server application for text recognition on iOS platform. The reader is acquainted with common principles of a client-server model, including its known architecture styles, and with a distribution of logical layers between both sides of the model. After that the thesis depicts current trends and examples of suitable technologies for creating an application programming interface of a web server. Possible ways of text recognition on the server side are discussed as well. In context of a client side, the thesis provides an insight into iOS platform and a few important concepts in iOS application development. Following implementation of the server side is stressed to be reusable as much as possible for different kinds of use cases. Last but not least, the thesis provides a simple iOS framework for a direct communication with the recognition server. Finally, an application for evaluation of food ingredients from a packaging material is implemented as an example of usage.
|
|
|
License Plate Detection and Recognition
Řepka, Michal ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
This paper addresses the problem of object detection and recognition from still images using methods of computer vision. The objects of detection are czech license plates and the goal of this paper was to create an automatic license plate anotation tool. Suggested solution uses edge detection and machine learned cascading classifiers. Created application was then tested on dataset taken by the author.
|
guest ::
