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

Input Image Adaption for Robust Direct SLAM using Deep Learning

Wang, Sen (2020) Input Image Adaption for Robust Direct SLAM using Deep Learning. DLR-Interner Bericht. DLR-IB-RM-OP-2020-187. Master's. Technische Universität München (TUM). 60 S.

[img] PDF


Direct SLAM methods have drawn much attention in the recent years since they have achieved exceptional performance on visual odometry tasks. However, they are prone to suffer from lighting or weather changes. To overcome this, we employ an adapted U-Net that translates the colors of regular images into a high-dimensional feature space. The network is trained to be insensitive to lighting effects as a Siamese U-Net, using labels that are automatically generated from synthetic datasets, without any human intervention. To generate more consistent high-dimensional feature maps, we propose the Cross Triplet Loss utilizing cross information in two images under different domains, and a new sampling method which can generate a wider range of samples by adding weights while sampling. Experiments on different weather and sequences with different textures show that the proposed method outperforms classical feature extraction methods and state-of-art deep learned feature extraction methods.

Item URL in elib:https://elib.dlr.de/139103/
Document Type:Monograph (DLR-Interner Bericht, Master's)
Title:Input Image Adaption for Robust Direct SLAM using Deep Learning
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Wang, SenInstitut für Robotik und Mechatronikhttps://orcid.org/0000-0002-3610-7999UNSPECIFIED
Date:November 2020
Refereed publication:No
Open Access:Yes
Number of Pages:60
Keywords:SLAM, visual odometry, Deep Learning, Triplet Network, Neural Network
Institution:Technische Universität München (TUM)
Department:Human-centered Assistive Robotics
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: Geyer, Günther
Deposited On:07 Dec 2020 11:00
Last Modified:07 Dec 2020 11:00

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.