|
|
Advanced analysis of moving objects in transport
Hora, Adam ; Dejdar, Petr (referee) ; Kiac, Martin (advisor)
This thesis solves the problem of monitoring objects from live streams or camera recordings. The aim is also to create your own data set usable in solving traffic situations and analysis for object recognition and classification. The YOLO method with OpenCV support was used for evaluation purposes. The result is a program in which road recordings can be inserted or live broadcasts can be used from a camera positioned so that it captures the road. The output of the program is to find out the number of motor vehicles at any given moment and the average number of vehicles that were on the road during given periods of time. The videos from which the data set is created were provided by the thesis supervisor. The main benefit of this work is the ability to monitor traffic density at given time intervals.
|
|
|
Detection of Vehicle License Plates in Video
Líbal, Tomáš ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
This thesis deals with preparation of training dataset and training of convolutional neural network for licence plate detection in video. Darknet technology was used for detection, specifically the YOLOv3-tiny neural network model. The solution was focused on the most accurate detection and the smallest number of false positives per image, thus minimizing overall model error. Dataset was prepared from existing freely available datasets, from the dataset provided by the GRAPH@FIT research group, and from self-annotated images created from downloaded YouTube videos. Furthermore, this dataset has been processed using data augmentation, extending it to twice the size. The YOLO Mark tool was used to create annotations. An ROC curve was used to visualize the detection success. Created solution reaches minimum total error 10,849%. Part of the solution is already mentioned dataset.
|
|
|
Automatic Webpage Content Categorisation and Extraction
Rein, Michal ; Koutenský, Michal (referee) ; Dolejška, Daniel (advisor)
Tato práce popisuje vývoj flexibilního systému pro automatickou kategorizaci a extrakci obsahu z webových stránek, se zaměřením na prostředí darknetu. Navrhli jsme vysoce přizpůsobitelný a škálovatelný systém, který dokáže zpracovávat různorodý typ obsahu, přičemž jsme dbali na kvalitu návrhu celkové architektury, struktury databáze a samotného algoritmu pro zpracování dat. Použitím nejmodernějšího jazykového modelu trénovaného na úkolu inference přirozeného jazyka demonstrujeme potenciál modelu efektivně kategorizovat obsah v zcela neznámém prostředí, přičemž jsme provedli analýzu výkonu daného modelu za použití různých hypotetických šablon. Dále jsme do systému integrovali model pro rozpoznávání pojmenovaných entit a metodologii šablonování pro extrakci obsahu, přičemž jsme navrhli automatizovaný přístup k segmentaci obsahu webových stránek za pomocí modelu ChatGPT od společnosti OpenAI. V neposlední řadě jsme vyvinuli uživatelsky přívětivou webovou aplikaci pro zlepšení dostupnosti a snadné použití systému, zhodnotili dosažené výsledky a navrhli možnosti pro další výzkum a vývoj v dané oblasti.
|
|
|
Vehicle Location Detection and Distribution from Camera Images
Stryk, Filip ; Götthans, Jakub (referee) ; Götthans, Tomáš (advisor)
Tato bakalářská práce se zabývá detekcí a sledováním polohy vozidel. Nejdříve jsou představeny základní principy hlubokého učení a konvolučních neuronových sítí. Jsou popsány detektory objektů fungující na principu konvolučních neuronových sítí se zaměřením především na YOLO, které jsou následně porovnány z hlediska přesnosti a rychlosti. Je navržen, implementován a vyhodnocen systém pro detekci a sledování polohy vozidel s pomocí YOLOv4-tiny a SORT.
|
|
|
Detekce objektů na včelím plástu a spadových podložkách mobilním telefonem
DĚD, Lukáš
This thesis deals with the improvement of the adopted solutions, dealing with the detection of the bee queen and the calculation of the fall of the Varroa destructor mite. These advanced solutions are implemented in a mobile application for Android devices. Furthermore, this work deals with the investigation of methods for the detection of short-lived and long-lived bees. The theoretical part contains a description of the methods used in the field of computer vision and convolutional neural networks. The practical part describes the environment and technologies, which were used to implement the methods described in the theoretical part, as well as the process of porting the results to the mobile platform.
|
|
|
Analýza Darknetu se zaměřením na forenzní zkoumání
RÝC, Tomáš
This bachelor thesis aims to analyse the DARKNET with focus on forensic research. This paper describes a variety of illegal actions which occur in the DARKNET and possible form of their forensic research. A forms of identification of the illegal actions, possibilities of their documentation and analysis of the identification of the perpetrator are suggested. By the suggested methodology is designed a cybercrime solution, which can be used by the authorities active in the criminal proceedings.
|
|
|
Advanced analysis of moving objects in transport
Hora, Adam ; Dejdar, Petr (referee) ; Kiac, Martin (advisor)
This thesis solves the problem of monitoring objects from live streams or camera recordings. The aim is also to create your own data set usable in solving traffic situations and analysis for object recognition and classification. The YOLO method with OpenCV support was used for evaluation purposes. The result is a program in which road recordings can be inserted or live broadcasts can be used from a camera positioned so that it captures the road. The output of the program is to find out the number of motor vehicles at any given moment and the average number of vehicles that were on the road during given periods of time. The videos from which the data set is created were provided by the thesis supervisor. The main benefit of this work is the ability to monitor traffic density at given time intervals.
|
|
|
Advanced analysis of moving objects in transport
Hora, Adam ; Dejdar, Petr (referee) ; Kiac, Martin (advisor)
This thesis solves the problem of monitoring objects from live streams or camera recordings. The aim is also to create your own data set usable in solving traffic situations and analysis for object recognition and classification. The YOLO method with OpenCV support was used for evaluation purposes. The result is a program in which road recordings can be inserted or live broadcasts can be used from a camera positioned so that it captures the road. The output of the program is to find out the number of motor vehicles at any given moment and the average number of vehicles that were on the road during given periods of time. The videos from which the data set is created were provided by the thesis supervisor. The main benefit of this work is the ability to monitor traffic density at given time intervals.
|
|
|
Detection of Vehicle License Plates in Video
Líbal, Tomáš ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
This thesis deals with preparation of training dataset and training of convolutional neural network for licence plate detection in video. Darknet technology was used for detection, specifically the YOLOv3-tiny neural network model. The solution was focused on the most accurate detection and the smallest number of false positives per image, thus minimizing overall model error. Dataset was prepared from existing freely available datasets, from the dataset provided by the GRAPH@FIT research group, and from self-annotated images created from downloaded YouTube videos. Furthermore, this dataset has been processed using data augmentation, extending it to twice the size. The YOLO Mark tool was used to create annotations. An ROC curve was used to visualize the detection success. Created solution reaches minimum total error 10,849%. Part of the solution is already mentioned dataset.
|
|
|
Analýza DARKNETu se zaměřením na forenzní zkoumání
RÝC, Tomáš
This bachelor thesis aims to analyse the DARKNET with focus on forensic research. This paper describes a variety of illegal actions which occur in the DARKNET and possible form of their forensic research. A forms of identification of the illegal actions, possibilities of their documentation and analysis of the identification of the perpetrator are suggested. By the suggested methodology is designed a cybercrime solution, which can be used by the authorities active in the criminal proceedings.
|
guest ::
