DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Combined Deep and Active Learning for Online 3D Object Recognition

Ullrich, Monika (2016) Combined Deep and Active Learning for Online 3D Object Recognition. DLR-Interner Bericht. DLR-IB-RM-OP-2016-364. Master's. Technische Universität München. 75 S.

[img] PDF - Only accessible within DLR


Deep learning methods have received lots of attention in research on 3D object recognition. Due to the lack of training data, many researchers use pre-trained Convolutional Neural Networks (CNNs) and either extract the output of one of the last layers as features or fine-tune the networks on their data. We achieve superior results with a method that fine-tunes a CNN before feature extraction for RGB data. Combined with extracted features from depth data and reducing the features’ dimensionalities, we improve the state-of-the-art accuracy on the University of Washington RGB-D Object dataset [Lai+11], using a support vector machine (SVM). Furthermore, we evaluate the impact of different learning rates (LRs) when fine-tuning a CNN. Our results show that the selection of a suitable LR is crucial to the success of a network. Instead of SVM as a classifier, we also use the Mondrian forest (MF), an online classifier, which can be updated over time as soon as more data is available.

Item URL in elib:https://elib.dlr.de/110280/
Document Type:Monograph (DLR-Interner Bericht, Master's)
Title:Combined Deep and Active Learning for Online 3D Object Recognition
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Refereed publication:No
Open Access:No
Number of Pages:75
Keywords:3D object recognition, vector machine, CNN, LR, Mondrian forest, SVM
Institution:Technische Universität München
Department:Department of Informatics
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space System Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Space System Technology
DLR - Research theme (Project):R - Vorhaben Multisensorielle Weltmodellierung (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013)
Deposited By: Schlögl, Birgit
Deposited On:10 Jan 2017 09:43
Last Modified:10 Jan 2017 09:43

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.