|
|
Object Detection in the Laser Scans Using Convolutional Neural Networks
Zelenák, Michal ; Kodym, Oldřich (referee) ; Veľas, Martin (advisor)
This work is focused on road segmentation in laser scans, using a convolutional neural network. To achieve this goal, which will find application in the field of road maintenance, convolutional neural networks have been used for their flexibility and speed. The work brings implementation and modifications of the existing method, which solves the problem by using a fully connected convolutional neural network. Used modifications include, for example using of various parameters for the loss function, the use of a different number of classes in the network model and dataset. The effect of the modification was experimentally verified and the accuracy of 96.12%, and the value for F-measure 95.02% were achieved.
|
|
|
Object Detection Using Kinect
Němec, Lukáš ; Veľas, Martin (referee) ; Španěl, Michal (advisor)
This paper address the problem of object recognition using Microsoft Kinect in the fi eld of computer vision. The objective of this work was to evaluate current methods of detection of objects using depth map (RGB-D sensor). The work deals with the enviroment of point cloud and Viewpoint Feature method. It also describes the use of binary classifi er in the context of object recognition. Object detection was implemented and performed experiments with it.
|
|
|
Navigation Using Deep Convolutional Networks
Skácel, Dalibor ; Veľas, Martin (referee) ; Hradiš, Michal (advisor)
This thesis studies navigation and autonomous driving using convolutional neural networks. It presents main approaches to this problem used in literature. It describes theory of neural networks and imitation and reinforcement learning. It also describes tools and methods suitable for a driving system. There are two simulation driving models created using learning algorithms DAGGER and DDPG. The models are then tested in car racing simulator TORCS.
|
|
|
I Offer/Seek Local Help. How to Connect These People Effectively and Safely?
Kohútová, Alena ; Veľas, Martin (referee) ; Beran, Vítězslav (advisor)
The aim of this bachelor thesis is to design a system that will connect people seeking help with those who need it, focusing on the effectiveness of use and motivation of users using gamification techniques. The system allows you to add contribution, start user collaboration, add ratings to other users and more. The resulting web system is implemented using modern web design techniques. The output of the work is an implemented prototype, which is evaluated by user testing.
|
|
|
3D Objects Detection in Images
Bordovský, Gabriel ; Veľas, Martin (referee) ; Španěl, Michal (advisor)
This bachelors thesis deals with detection of a known 3D object in images and its pose estimation. The method uses the ORB-type keypoints and their location on the surface of a bounding box. By using solve of PnP problem a pose of the object is obtained using the points 2D coordinates from the image and the 3D coordinates of the very points from the registered model. This thesis expands a detection method for simple box-shaped objects, which is a part of OpenCV library, for the usage on more complex objects. In experiments, the detector reached a detection success rate of 85 % and the computed pose matches the real one approximately for 88 %.
|
|
|
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.
|
|
|
I Offer/Seek Local Help. How to Connect These People Effectively and Safely?
Kohútová, Alena ; Veľas, Martin (referee) ; Beran, Vítězslav (advisor)
The aim of this bachelor thesis is to design a system that will connect people seeking help with those who need it, focusing on the effectiveness of use and motivation of users using gamification techniques. The system allows you to add contribution, start user collaboration, add ratings to other users and more. The resulting web system is implemented using modern web design techniques. The output of the work is an implemented prototype, which is evaluated by user testing.
|
|
|
3D Mapping from Sparse LiDAR Data
Veľas, Martin ; Hofierka,, Jaroslav (referee) ; Kaartinen,, Harri (referee) ; Herout, Adam (advisor)
Tato práce se zabývá návrhem nových algoritmů pro zpracování řídkých 3D dat senzorů LiDAR, včetně kompletního návrhu batohovího mobilního mapovacího řešení. Tento výzkum byl motivován potřebou takových řešení v oblasti geodézie, mobilního průzkumu a výstavby. Nejprve je prezentován iterační algoritmus pro spolehlivou registraci mračen bodů a odhad odometrie z měření 3D LiDARu. Problém řídkosti a velikosti těchto dat je řešen pomocí náhodného vzorkování pomocí Collar Line Segments (CLS). Vyhodnocení na standardní datové sadě KITTI ukázalo vynikající přesnost oproti známému algoritmu General ICP. Konvoluční neuronové sítě hrají důležitou roli ve druhé metodě odhadu odometrie, která zpracovává kódovaná data LiDARu do 2D matic. Metoda je schopna online výkonu, zatímco je zachována přesnost, když požadujeme pouze parametry posunu. To může být užitečné v situacích, kdy je vyžadován online náhled mapování a parametry rotace mohou být spolehlivě poskytnuty např. senzorem IMU. Na základě algoritmu CLS bylo navrženo a implementováno batohové mobilní mapovací řešení 4RECON. S využitím kalibrovaného a synchronizovaného páru LiDARů Velodyne a s nasazením řešení GNSS/INS s duální anténou, byl vyvinut univerzální systém poskytující přesné 3D modelování malých vnitřních i velkých otevřených prostředí. Naše hodnocení prokázalo, že požadavky stanovené pro tento systém byly splněny -- relativní přesnost do $5$~cm a průměrná chyba georeferencí pod $12$~cm. Poslední stránky obsahují popis a vyhodnocení další metody založené na konvolučních neuronových sítích -- navržených pro segmentaci země v mračnech bodů 3D LiDARu. Tato metoda překonala současný stav techniky v této oblasti a představuje způsob, jakým může být sémantická informace vložena do 3D laserových dat.
|
|
|
Object Detection in the Laser Scans Using Convolutional Neural Networks
Zelenák, Michal ; Kodym, Oldřich (referee) ; Veľas, Martin (advisor)
This work is focused on road segmentation in laser scans, using a convolutional neural network. To achieve this goal, which will find application in the field of road maintenance, convolutional neural networks have been used for their flexibility and speed. The work brings implementation and modifications of the existing method, which solves the problem by using a fully connected convolutional neural network. Used modifications include, for example using of various parameters for the loss function, the use of a different number of classes in the network model and dataset. The effect of the modification was experimentally verified and the accuracy of 96.12%, and the value for F-measure 95.02% were achieved.
|
|
|
Navigation Using Deep Convolutional Networks
Skácel, Dalibor ; Veľas, Martin (referee) ; Hradiš, Michal (advisor)
This thesis studies navigation and autonomous driving using convolutional neural networks. It presents main approaches to this problem used in literature. It describes theory of neural networks and imitation and reinforcement learning. It also describes tools and methods suitable for a driving system. There are two simulation driving models created using learning algorithms DAGGER and DDPG. The models are then tested in car racing simulator TORCS.
|
guest ::
RSS feed.