Visual Mapping in Light-Crowded Indoor Environments

Jan Helge Klüssendorff, Kristian Ehlers, Erik Maehle


Due to the recent success of affordable RGBD cameras, solutionsKlüssendorff, Jan Helgeto the Visual Simultaneous Localization and Mapping (VSLAM) problem has experienced a huge leap. To enableEhlers, Kristianaccurate mappingMaehle, Eriksolutions, most of the proposed solutions expect static environments. Thinking of industrial applications, there is no guarantee for static environments. The SLAM algorithm has to cope with moving objects like human beings. We present an approach to detect moving objects in RGBD camera images. The approach is based on point cloud and image filtering techniques. We present test results using publicly available datasets. We further show the performance and influence of the algorithm on mapping and on the accuracy of a visual SLAM system.
Original languageEnglish
Title of host publicationIntelligent Autonomous Systems 13
EditorsEmanuele Menegatti, Nathan Michael, Karsten Berns, Hiroaki Yamaguchi
Number of pages10
Place of PublicationCham
PublisherSpringer International Publishing
Publication date03.09.2015
ISBN (Print)978-3-319-08337-7
ISBN (Electronic)978-3-319-08338-4
Publication statusPublished - 03.09.2015
Event13th International Conference on Intelligent Autonomous Systems - Padova, Italy
Duration: 14.07.201418.07.2014
Conference number: 140839


Dive into the research topics of 'Visual Mapping in Light-Crowded Indoor Environments'. Together they form a unique fingerprint.

Cite this