|
|
Mapování trajektorií pohybu chodců v záznamu pořízeným dronem
Šťastný, Filip ; Tinka, Jan (oponent) ; Orság, Filip (vedoucí práce)
Tato práce se zabývá detekcí chodců ve videozáznamu pořízeném dronem pomocí neuronových sítí. Pro sledované osoby poté řeší určování jejich GPS souřadnic na základě aproximace jejich pozice s využitím nadmořské výšky zemského povrchu. Dále mapuje jejich trajektorie v čase pomocí re-identifikace a informací dostupných z dronu. Výsledné trajektorie pak umožňuje zobrazit v programu Google.
|
|
|
Robotic Tracking of a Person using Neural Networks
Zakarovský, Matúš ; Lázna, Tomáš (oponent) ; Žalud, Luděk (vedoucí práce)
The main goal of this thesis was to create a software solution based on a neural network to enable detection of a person and its subsequent following. This was achieved via completion of the points of the assignment. First, a hardware solution and used libraries and application programming interfaces were described as well as the robotic platform supplied by the Robotics and AI group of BUT Department of Control and Instrumentation upon which the robot was built on. Next, a research of various neural networks used for person detection was conducted. Four detectors were described in detail. Some of them were tested on either a PC or a NVIDIA Jetson Nano computer. Afterwards, a software solution consisting of five programs was created to achieve goals such as, detection of the person using ped-100 neural network, real-world position with reference to the robot estimation using monocular camera and robot control to successfully follow a target. The output of this thesis is a robotic platform able to detect and follow a person that can be used in a real-world applications.
|
|
|
Monitoring the Movement of Visitors in Museum Exhibitions
Viskupič, Matej ; Dyk, Tomáš (oponent) ; Drahanský, Martin (vedoucí práce)
The aim of this work is to propose a new system of monitoring visitors in museums. Incontrast to existing methods, the problem is solved here only using camera technology. This requires addressing three sub-problems: (1.) detection of visitors in camera streams using a convolutional neural network; (2.) camera configuration to exactly determine the position of the detected persons within the monitoring area; and (3.) identification and tracking the detected persons. The outcome of the proposed solution is the heatmap of most visited places, the map of visitor trajectories and the statistic of visits for individual exhibits. This monitoring method can contribute towards improved evaluation of visitor experience and more effective selection and positioning of the exhibits.
|
|
|
Návrh asistenčního mobilního robotu pro následování osob
Šamánek, Jan David ; Appel, Martin (oponent) ; Adámek, Roman (vedoucí práce)
V úvodu práce je představeno několik algoritmů pro detekci osob, detekci gest a sledování osob v obraze. Následující část se zaměřuje na popis vytvořeného programu. Jmenovitě realizaci detekce osob, detekce gest, sledování osob a aplikaci programu na robotickou platformu. V rámci této práce je taktéž řešeno řízení robotické platformy na základě výstupů z vytvořeného programu.
|
|
|
Detection and Recognition of Persons in a Multi-Camera System
Martinček, Ľuboš ; Beran, Jan (oponent) ; Goldmann, Tomáš (vedoucí práce)
This thesis deals with the detection and recognition of people in a multi-camera system. In this thesis I describe general camera systems and their development and methods used for detection and recognition of persons. Based on this information, in the second part of the project I describe the design and implementation of a multi-camera system that is able to detect and recognize people. This thesis implements a combination of a YOLO detector and an Omni-Scale neural network based feature extractor.
|
|
|
Monitoring the Movement of Visitors in Museum Exhibitions
Viskupič, Matej ; Dyk, Tomáš (oponent) ; Drahanský, Martin (vedoucí práce)
The aim of this work is to propose a new system of monitoring visitors in museums. Incontrast to existing methods, the problem is solved here only using camera technology. This requires addressing three sub-problems: (1.) detection of visitors in camera streams using a convolutional neural network; (2.) camera configuration to exactly determine the position of the detected persons within the monitoring area; and (3.) identification and tracking the detected persons. The outcome of the proposed solution is the heatmap of most visited places, the map of visitor trajectories and the statistic of visits for individual exhibits. This monitoring method can contribute towards improved evaluation of visitor experience and more effective selection and positioning of the exhibits.
|
|
|
Mapování trajektorií pohybu chodců v záznamu pořízeným dronem
Šťastný, Filip ; Tinka, Jan (oponent) ; Orság, Filip (vedoucí práce)
Tato práce se zabývá detekcí chodců ve videozáznamu pořízeném dronem pomocí neuronových sítí. Pro sledované osoby poté řeší určování jejich GPS souřadnic na základě aproximace jejich pozice s využitím nadmořské výšky zemského povrchu. Dále mapuje jejich trajektorie v čase pomocí re-identifikace a informací dostupných z dronu. Výsledné trajektorie pak umožňuje zobrazit v programu Google.
|
|
|
Robotic Tracking of a Person using Neural Networks
Zakarovský, Matúš ; Lázna, Tomáš (oponent) ; Žalud, Luděk (vedoucí práce)
The main goal of this thesis was to create a software solution based on a neural network to enable detection of a person and its subsequent following. This was achieved via completion of the points of the assignment. First, a hardware solution and used libraries and application programming interfaces were described as well as the robotic platform supplied by the Robotics and AI group of BUT Department of Control and Instrumentation upon which the robot was built on. Next, a research of various neural networks used for person detection was conducted. Four detectors were described in detail. Some of them were tested on either a PC or a NVIDIA Jetson Nano computer. Afterwards, a software solution consisting of five programs was created to achieve goals such as, detection of the person using ped-100 neural network, real-world position with reference to the robot estimation using monocular camera and robot control to successfully follow a target. The output of this thesis is a robotic platform able to detect and follow a person that can be used in a real-world applications.
|
host ::
RSS.