|
|
Tabletop Object Detection
Timko, Martin ; Veľas, Martin (referee) ; Kapinus, Michal (advisor)
The aim of this thesis is to design and create a module for robotic platform PR2. This module has to detect objects in front of the robot on a table and enable various operations with these objects. This thesis describes methods of object detection which were used in the implementation of the module. The thesis also describes the methods used for design and implementation of this module. The module testing and evaluation of results are mentioned at the end of the thesis.
|
|
|
Deep Learning Algorithms on Embedded Devices
Hadzima, Jaroslav ; Boštík, Ondřej (referee) ; Horák, Karel (advisor)
Táto práca popisuje v súčastnosti široko používané architektúry a modely pre Hlboké Učenie, riešiace úlohu detekcie a klasifikácie objektov vo videu. Dôraz tu bude kladený na ich použiteľnosť na vstavaných zariadeniach. Postupne preberieme kroky a odvôvodňovanie pri výbere najlepšieho vstavaného systému pre našu aplikáciu. Ukážková aplikáci pozostáva hlavne z detekcie vozidiel a detekcie voľných parkovacích miest s využitím algoritmov Hlbokého Učenia. Táto aplikácia umožňuje monitorovať počet vozidiel, nachádzajúcich sa na parkovisku a zároveň rozhodnúť, či sa nachádzajú na prakovacom mieste alebo nie. Následne tu budú prebrané kroky nutné ku konfigurácii zariadenia s dôrazom na optimalizáciu hardvéru pre dosiahnutie čo najväčšej rýchlosti. V ďaľšej časti bude poskytnuté porovnanie vybraných modelov, ktoré budú porovnávané hlavne v kategóriách ako rýchlosť alebo F1 skóre. Najlepší kandidát bude použitý na riešenie našej aplikácie a následné testovanie jej vlastností s názvom Inteligentné parkovisko.
|
|
|
Object Detection in the Laser Scans Using Convolutional Neural Networks
Marko, Peter ; Beran, Vítězslav (referee) ; Veľas, Martin (advisor)
This thesis is aimed at detection of lines of horizontal road markings from a point cloud, which was obtained using mobile laser mapping. The system works interactively in cooperation with user, which marks the beginning of the traffic line. The program gradually detects the remaining parts of the traffic line and creates its vector representation. Initially, a point cloud is projected into a horizontal plane, crating a 2D image that is segmented by a U-Net convolutional neural network. Segmentation marks one traffic line. Segmentation is converted to a polyline, which can be used in a geo-information system. During testing, the U-Net achieved a segmentation accuracy of 98.8\%, a specificity of 99.5\% and a sensitivity of 72.9\%. The estimated polyline reached an average deviation of 1.8cm.
|
|
|
Object detection
Baáš, Filip ; Petyovský, Petr (referee) ; Richter, Miloslav (advisor)
This bachelor thesis deals with detection of rigid objects in images. Chamfer matching algorithm, which is built for this kind of tasks is used as detection algorithm. First part of this work is dedicated to theoretical explanation of the algorithm. Most commonly used metrics of distance transform are explained, which is needed for the algorithm. Also explanation of chamfer distance calculation and pyramid representation of information is here. Next part is dedicated to development tools used in this work, which is integrated development environment Visual Studio and libraries OpenCV for image processing and Qt for graphical user interface creation. In last part of this work, practical implementation of object detection is described. This part explains the way objects are rendered, steps for creating a template from rendered image, method to create set of templates, comparison of speed of distance transformation calculation in different metrics, comparison of speed of common and pyramid detection and method of score calculation. The conclusion summarizes reached goals of this work.
|
|
|
Exploitation of GPU in graphics and image processing algorithms
Jošth, Radovan ; Svoboda, David (referee) ; Trajtel,, Ľudovít (referee) ; Herout, Adam (advisor)
Táto práca popisuje niekoľko vybraných algoritmov, ktoré boli primárne vyvinuté pre CPU procesory, avšak vzhľadom k vysokému dopytu po ich vylepšeniach sme sa rozhodli ich využiť v prospech GPGPU (procesorov grafického adaptéra). Modifikácia týchto algoritmov bola zároveň cieľom nášho výskumu, ktorý bol prevedený pomocou CUDA rozhrania. Práca je členená podľa troch skupín algoritmov, ktorým sme sa venovali: detekcia objektov v reálnom čase, spektrálna analýza obrazu a detekcia čiar v reálnom čase. Pre výskum detekcie objektov v reálnom čase sme zvolili použitie LRD a LRP funkcií. Výskum spektrálnej analýzy obrazu bol prevedný pomocou PCA a NTF algoritmov. Pre potreby skúmania detekcie čiar v reálnom čase sme používali dva rôzne spôsoby modifikovanej akumulačnej schémy Houghovej transformácie. Pred samotnou časťou práce venujúcej sa konkrétnym algoritmom a predmetu skúmania, je v úvodných kapitolách, hneď po kapitole ozrejmujúcej dôvody skúmania vybranej problematiky, stručný prehľad architektúry GPU a GPGPU. Záverečné kapitoly sú zamerané na konkretizovanie vlastného prínosu autora, jeho zameranie, dosiahnuté výsledky a zvolený prístup k ich dosiahnutiu. Súčasťou výsledkov je niekoľko vyvinutých produktov.
|
|
|
Basics of Pedestrians Detection in Image by Machine Learning
Lučanský, Peter ; Klečka, Jan (referee) ; Horák, Karel (advisor)
Táto Bakalárska práce sa zaoberá významnou problematikou v oblasti počítačového videnia, ktorou je detekcia osôb/chodcov v obraze, za pomoci metod strojového učenia, spolu s jej možným využitím, vývojom a vysvetlením princípov. Taktiež sa zaoberá testovaním dnes najlepšieho dostupného algoritmu, pričom sa porovnávajú faktory ktoré vplívajú na kvalitu jeho činnosti. Na začiatku je problematika stručne popísaná, potom sa prejde k podrobným popisom dosiahnutých pokrokov. V nasledujúcej časti sú popísané dostupné datasety, ktoré by sa dali použiť pri tréningu detekčného algoritmu. V poslednom rade sú vykonané trénovacie procesy za rozličných podmienok, pričom sú jednotlivé výsledky porovnávané.
|
|
|
Ball Tracking in Sports Video
Motlík, Matúš ; Špaňhel, Jakub (referee) ; Bartl, Vojtěch (advisor)
This master's thesis deals with automatic detection and tracking of a soccer ball in sports videos. Based on the introduced techniques focusing on tracking of small objects in high-resolution videos, effective convolutional neural networks are designed and used by a modified version of tracking algorithm SORT for automatic object detection. A set of experiments with the processing of images in different resolutions and with various frequencies of detection extraction is carried out in order to examine the trade-off between processing speed and tracking accuracy. The obtained results of experiments are presented and used to form proposals for future work, which could lead to improvements in tracking accuracy while maintaining reasonable processing speed.
|
|
|
Analysis of Surveillance Camera Recordings
Ščavnická, Šárka ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
This thesis deals with the systems for analyzing records from security cameras. It aims to create a functional solution that analyzes records and answers questions from the user. The created system combines the YOLO algorithm for object detection and DeepSORT for their subsequent tracking. It contains five models that detect specific situations. Individual models achieved varying degrees of success during testing, with the lowest success rate being 58 % for the getting out of car situation. The highest success rate, 83 %, was obtained by a model for detecting a meeting between two people.
|
|
|
Mobile Application Using Deep Convolutional Neural Networks
Poliak, Sebastián ; Herout, Adam (referee) ; Sochor, Jakub (advisor)
This thesis describes a process of creating a mobile application using deep convolutional neural networks. The process starts with proposal of the main idea, followed by product and technical design, implementation and evaluation. The thesis also explores the technical background of image recognition, and chooses the most suitable options for the purpose of the application. These are object detection and multi-label classification, which are both implemented, evaluated and compared. The resulting application tries to bring value from both user and technical point of view.
|
|
|
Recognizing People and Their Activities in Video from Security Cameras
Saloň, Juraj Samuel ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
The aim of this thesis is to design and develop a system capable of recognizing the activities of people from surveillance cameras. Special attention is paid to the concept of complex situations or events that are defined by relations between identified objects. The first part surveys state-of-the-art techniques for object recognition, object tracking, and recognition of activities relevant to the realized solution. The second part describes the design and implementation of the devised system. It takes advantage of specific relations among two or more objects that are identified in video recordings, such as "person getting out of the car" or "one or more people met with a person of interest and they left together". Results are evaluated on video data extracted from available datasets and manually annotated. The mean average precision metric (MAP) on the data is reported.
|
guest ::
