|
|
System for People Detection and Localization Using Thermal Imaging Cameras
Charvát, Michal ; Kempter, Guido (referee) ; Drahanský, Martin (advisor)
V dnešním světě je neustále se zvyšující poptávka po spolehlivých automatizovaných mechanismech pro detekci a lokalizaci osob pro různé účely -- od analýzy pohybu návštěvníků v muzeích přes ovládání chytrých domovů až po hlídání nebezpečných oblastí, jimiž jsou například nástupiště vlakových stanic. Představujeme metodu detekce a lokalizace osob s pomocí nízkonákladových termálních kamer FLIR Lepton 3.5 a malých počítačů Raspberry Pi 3B+. Tento projekt, navazující na předchozí bakalářský projekt "Detekce lidí v místnosti za použití nízkonákladové termální kamery", nově podporuje modelování komplexních scén s polygonálními okraji a více termálními kamerami. V této práci představujeme vylepšenou knihovnu řízení a snímání pro kameru Lepton 3.5, novou techniku detekce lidí používající nejmodernější YOLO (You Only Look Once) detektor objektů v reálném čase, založený na hlubokých neuronových sítích, dále novou automaticky konfigurovatelnou termální jednotku, chráněnou schránkou z 3D tiskárny pro bezpečnou manipulaci, a v neposlední řadě také podrobný návod instalace detekčního systému do nového prostředí a další podpůrné nástroje a vylepšení. Výsledky nového systému demonstrujeme příkladem analýzy pohybu osob v Národním muzeu v Praze.
|
|
|
Person Detection in Video
Marek, Lukáš ; Goldmann, Tomáš (referee) ; Dyk, Tomáš (advisor)
This bachelor thesis deals with the implementation of an application for detecting people in video footage. Both the application and the detection are implemented in Python. TKinter library is used to create the application. The OpenCV library and the YOLOv4 detection algorithm, which runs on a CUDA backend but can also run on the CPU, are used for detection.
|
|
|
Advanced image analysis using deep neural networks
Hynek, Vojtěch ; Přinosil, Jiří (referee) ; Kiac, Martin (advisor)
This bachelor thesis deals with the problem of object detection in images using a convolutional neural network. The result of this work is a custom dataset, a neural network model YOLOv4 and a script used to process the resulting model data. The dataset contains 8080 images on which 14 objects are annotated. The neural network model was reduced in depth, which significantly increased the speed of the detection itself. The script processing the resulting data calculates the 3D and GPS coordinates of the detected object in space. The paper concludes by summarizing the results of the model and at the same time suggesting how the quality of the dataset could be improved.
|
|
|
Counting of characteristic scales of sand lizards in colour images
Maršala, Štěpán ; Štursa, Dominik (referee) ; Škrabánek, Pavel (advisor)
The diploma thesis describes the design and implementation of a program for counting secondary scales in the image data of the ventral sides of the bodies of sand lizards. The program respects the requirements of scientists from the Institute of Vertebrate Biology of the Czech Academy of Sciences and the Faculty of Education at Masaryk University for the controllability and accuracy of results. The program consists of several parts. In input receives photos of sand lizards, in which he cuts out an area of interest. Unifies the orientation of these sections using detected objects. Object detection is provided by YOLOv4. Another part of the program called the Centroid Detector determines the position of the centers of the secondary scales in the unified sections. This part uses the U-Net convolutional neural network, which is specially modified to detect the centers of objects in close proximity. The other parts of the program divide the detected positions of the scale centers into left and right secondary rows and write their numbers to the output file.
|
|
|
Vehicle Detection in Image and Video
Rozprým, Dalimil ; Juránek, Roman (referee) ; Špaňhel, Jakub (advisor)
The goal of this thesis is comparison of available multiclass detectors abilities to detect road vehicles on purposely created dataset. As multiclass detectors are chosen neural networks for detection and classification of objects in image. Detectors described in this text and used for experimentation are Mask R-CNN, YOLOv4 and YOLACT++. This selection encompasses multiple different architectures and approaches to object detection. Created dataset used for learning and testing is thoroughly described in this text. Detection capability of detectors is tested on images from casual traffic and separately on partially covered objects. The outcome of this thesis is reusable and expandable dataset, measured performance values and their deeper exploration in this text.
|
|
|
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.
|
|
|
Unique Car Counting
Uhrín, Peter ; Špaňhel, Jakub (referee) ; Juránek, Roman (advisor)
Current systems for counting cars on parking lots usually use specialized equipment, such as barriers at the parking lot entrance. Usage of such equipment is not suitable for free or residential parking areas. However, even in these car parks, it can help keep track of their occupancy and other data. The system designed in this thesis uses the YOLOv4 model for visual detection of cars in photos. It then calculates an embedding vector for each vehicle, which is used to describe cars and compare whether the car has changed over time at the same parking spot. This information is stored in the database and used to calculate various statistical values like total cars count, average occupancy, or average stay time. These values can be retrieved using REST API or be viewed in the web application.
|
|
|
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.
|
|
|
Person Detection in Video
Marek, Lukáš ; Goldmann, Tomáš (referee) ; Dyk, Tomáš (advisor)
This bachelor thesis deals with the implementation of an application for detecting people in video footage. Both the application and the detection are implemented in Python. TKinter library is used to create the application. The OpenCV library and the YOLOv4 detection algorithm, which runs on a CUDA backend but can also run on the CPU, are used for detection.
|
|
|
Advanced image analysis using deep neural networks
Hynek, Vojtěch ; Přinosil, Jiří (referee) ; Kiac, Martin (advisor)
This bachelor thesis deals with the problem of object detection in images using a convolutional neural network. The result of this work is a custom dataset, a neural network model YOLOv4 and a script used to process the resulting model data. The dataset contains 8080 images on which 14 objects are annotated. The neural network model was reduced in depth, which significantly increased the speed of the detection itself. The script processing the resulting data calculates the 3D and GPS coordinates of the detected object in space. The paper concludes by summarizing the results of the model and at the same time suggesting how the quality of the dataset could be improved.
|
guest ::
