|
|
Video Enhancement Using Convolutional Networks
Skácel, David ; Špaňhel, Jakub (referee) ; Hradiš, Michal (advisor)
Convolutional neural networks (CNN) represent a state-of-the-art approach to non-trivial image processing tasks, including compression artifacts reduction and image super-resolution. As some research groups nowadays show, these networks can also be leveraged to perform such tasks on real-world video data, resulting in video spatial super-resolution and more. The main goal of this work is to determine whether these nets can be adjusted to perform temporal super-resolution of real-world video data. I utilize the aforementioned neural net architectures in this paper to do so. As I show, given that the input videos are of reasonable quality, these nets are capable of double-image interpolation up to a certain level, where the output image is usable for temporal upsampling. Although the presented results are promising, I encourage more research to be done on this topic.
|
|
|
Counting Vehicles in Static Images
Zemánek, Ondřej ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
Tato práce se zaměřuje na problém počítání vozidel v statickém obraze bez znalosti geometrických vlastností scény. V rámci řešení bylo implementováno a natrénováno 5 architektur konvolučních neuronových sítí. Také byl pořízen rozsáhlý dataset s 19 310 snímky pořízených z 12pohledů a zachycujících 7 různých scén. Použité konvoluční sítě mapují vstupní vzorek na mapu hustoty vozidel, ze které lze získat jejich počet a lokalizaci v kontextu vstupního snímku. Hlavním přínosem této práce je porovnání a aplikace dosavadních nejlepších řešení pro počítání objektů v obraze. Většina z těchto architektur byla navržena pro počítání lidí v obraze, proto musely být uzpůsobeny pro potřeby počítání vozidel v statickém obraze. Natrénované modely jsou vyhodnoceny GAME metrikou na TRANCOS datasetu a na velkém spojeném datasetu. Dosažené výsledky všech modelů jsou následně popsány a porovnány.
|
|
| |
|
|
Holistic License Plate Recognition Based on Convolution Neural Networks
Morbitzer, Dušan ; Juránek, Roman (referee) ; Špaňhel, Jakub (advisor)
The goal of this work is to create a model of neural network for holistic recognition of license plates, focused on accuracy and shortening of the learning process. The model was implemented as a union of convolutional neural network for extraction of deep features of a plate and Bidirectional LSTM with CTC. The trained model was compared to another implementation using a holistic approach, that was trained on the same dataset. My design of the network achieved better results in recognition on a dataset, which is different from the training one, with an error rate of 8.3 %.
|
|
|
Detection of Boxes in Image
Žitňanský, Adam ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
This thesis addresses the problem of cuboid detection, more specifically boxes detection in images. The main result is the implementation of a system for boxes detection based on corners and edges. The system consists of a CNN regression-based corner and edge points detector and decoder, which takes CNN output and turns it into a 2d model of the cuboid. As a part of this work also a a dataset of boxes with 550 images with corners and edges annotations was created
|
|
|
Re-Identification of Vehicles by License Plate Recognition
Špaňhel, Jakub ; Juránková, Markéta (referee) ; Herout, Adam (advisor)
This thesis aims at proposing vehicle license plate detection and recognition algorithms, suitable for vehicle re-identification. Simple urban traffic analysis system is also proposed. Multiple stages of this system was developed and tested. Specifically - vehicle detection, license plate detection and recognition. Vehicle detection is based on background substraction method, which results in an average hit rate of ~92%. License plate detection is done by cascade classifiers and achieves an average hit rate of 81.92% and precision rate of 94.42%. License plate recognition based on Template matching results in an average precission rate of 60.55%. Therefore the new license plate recognition method based on license plate scanning using the sliding window principle and neural network recognition was introduced. Neural network achieves a precision rate of 64.47% for five input features. Low precision rate of neural network is caused by small amount of training sample for some specific license plate characters.
|
|
|
Vehicle Speed Measurement by a Stationary Camera
Juřica, Tomáš ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
This Bachelor's thesis deals with the problematic of car speed measurement from video footage captured by a stationary camera. Development of a tool focused on reaching maximum accuracy of measurements with minimal user effort has been covered in this work. Perception of scene dimensions is acquired by using known points in the scene, which are manually marked. The influence of the way of annotating car position and input video quality on maximal reachable accuracy has also been discussed in this work.
|
|
|
Detection of Graffiti Tags in Image
Molisch, Marek ; Herout, Adam (referee) ; Špaňhel, Jakub (advisor)
The goal of this work is to compare today's architecture of object detection models and use them for the purpose of graffiti tag detection. State-of-the-art models, which are compatible with the Tensorflow framework, were used. Faster R-CNN architecture was found to be the most accurate and SSD architecture to be the fastest. Experiments with graffiti tags from Athens in the STORM dasater showed, that it is better to approach graffiti tags as objects rather than writings.
|
|
|
Graffiti Tags Re-Identification
Pavlica, Jan ; Beran, Vítězslav (referee) ; Špaňhel, Jakub (advisor)
This thesis focuses on the possibility of using current methods in the field of computer vision to re-identify graffiti tags. The work examines the possibility of using convolutional neural networks to re-identify graffiti tags, which are the most common type of graffiti. The work experimented with various models of convolutional neural networks, the most suitable of which was MobileNet using the triplet loss function, which managed to achieve a mAP of 36.02%.
|
|
|
Automatic Trafic Scene Analysis Using Image Processing
Válek, Lukáš ; Špaňhel, Jakub (referee) ; Zemčík, Pavel (advisor)
Tato práce se zabývá problematikou analýzy scény pomocí metod počítačového vidění. Cílem této práce je vytvořit systém schopný automaticky detekovat anomálie nacházející se ve video záznamech. Práce se zabývá systémy pro detekci a sledování objektů v obraze, tvorbou grafického uživatelského rozhraní a algoritmem pro detekci porušení uživatelem definovaných pravidel. Výsledkem práce je webová aplikace, která uživateli umožňuje správu videozáznamů, definování pravidel pro scénu, zahájení detekce anomálií a zobrazení výsledků analýzy. Systém pracuje v reálném čase, upozorňuje uživatele o dokončení operace a uchovává výsledky analýzy pro další zpracovaní.
|
guest ::
