CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 12800 > Article
Paper
11 October 2023 Semantic object assisted loop closure detection for indoor UAV
Lin Wang, Bo Jiang, Hong Xu, Dandan Luo
Author Affiliations +
Proceedings Volume 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023); 128006I (2023) https://doi.org/10.1117/12.3004093
Event: 6th International Conference on Computer Information Science and Application Technology (CISAT 2023), 2023, Hangzhou, China
Abstract
Loop closure detection is an important means to reduce the accumulated errors in visual SLAM (Simultaneous Localization and Mapping) systems. The change in the viewpoint of a UAV (Unmanned Air Vehicle) while navigating autonomously using SLAM poses a great challenge for loop closure detection. Compared to traditional appearance features, objects are a high-level semantic information that can be easily observed from different viewpoints. In this paper, a semantic object assisted loop closure detection method is proposed for indoor UAV. Firstly, the image color histogram and object histogram are used to initially filter and sort the loop closure candidate frames. Then, the spatial relationship of objects is described by semantic topology graph, and the semantic nodes are described by semantic histogram. Finally, the bag-of-words model and graph matching are combined for the verification of loop closure detection to achieve accurate and robust loop closure detection. Experiments on publicly available data show that the method in this paper has better precision and recall compared with other classical methods.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Lin Wang, Bo Jiang, Hong Xu, and Dandan Luo "Semantic object assisted loop closure detection for indoor UAV", Proc. SPIE 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023), 128006I (11 October 2023); https://doi.org/10.1117/12.3004093
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
INSTITUTIONAL
Select your institution to access the SPIE Digital Library.
SELECT YOUR INSTITUTION
PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
PERSONAL SIGN IN
No SPIE Account? Create one
PURCHASE THIS CONTENT
SUBSCRIBE TO DIGITAL LIBRARY
50 downloads per 1-year subscription
Members: $195
Non-members: $335 ADD TO CART
25 downloads per 1 - year subscription
Members: $145
Non-members: $250 ADD TO CART
PURCHASE SINGLE ARTICLE
Includes PDF, HTML & Video, when available
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 11 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Semantics
Unmanned aerial vehicles
Visualization
Detection and tracking algorithms
Target detection
Image processing
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top