Visual SLAM in Human Populated Environments: (Record no. 38092)

MARC details
000 -LEADER
fixed length control field 02212n a2200289#a 4500
001 - CONTROL NUMBER
control field 39556
003 - CONTROL NUMBER IDENTIFIER
control field P5A
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20221213140630.0
007 - PHYSICAL DESCRIPTION FIXED FIELD--GENERAL INFORMATION
fixed length control field cr cuuuuuauuuu
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 200122s20202020bl por d
035 ## - SYSTEM CONTROL NUMBER
System control number ocm51338542
040 ## - CATALOGING SOURCE
Original cataloging agency P5A
Transcribing agency P5A
090 ## - IMPA CODE FOR CLASSIFICATION SHELVES
IMPA CODE FOR CLASSIFICATION SHELVES Congressos e Seminários.
100 1# - MAIN ENTRY--PERSONAL NAME
Personal name Soares, João Carlos Virgolino
Affiliation (PUC-Rio, Brazil)
9 (RLIN) 425
245 10 - TITLE STATEMENT
Title Visual SLAM in Human Populated Environments:
Remainder of title Exploring the Trade-off between Accuracy and Speed of YOLO and Mask R-CNN/
Statement of responsibility, etc. J. C. V. Soares.
246 11 - VARYING FORM OF TITLE
Title proper/short title Seminário de Computação Gráfica:
260 ## - PUBLICATION, DISTRIBUTION, ETC.
Place of publication, distribution, etc. Rio de Janeiro:
Name of publisher, distributor, etc. IMPA,
Date of publication, distribution, etc. 2020.
300 ## - PHYSICAL DESCRIPTION
Extent video online
505 2# - FORMATTED CONTENTS NOTE
Formatted contents note Abstract: Simultaneous Localization and Mapping (SLAM) is a fundamental problem in mobile robotics. However, the majority of Visual SLAM algorithms assume a static scenario, limiting their applicability in real-world environments. Dealing with dynamic content in Visual SLAM is still an open problem, with solutions usually relying on direct or feature-based methods. Deep learning techniques can improve the SLAM solution in environments with a priori dynamic objects, providing high-level information of the scene. This paper presents a new approach to SLAM in human populated environments using deep learning-based techniques. The system is built on ORB-SLAM2, a state-of-the-art SLAM system. The proposed methodology is evaluated using a benchmark dataset, outperforming other Visual SLAM methods in highly dynamic scenarios .
650 04 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element Matematica.
Source of heading or term larpcal
9 (RLIN) 19899
697 ## - LOCAL SUBJECT
Local Subject Congressos e Seminários.
Linkage 23755
700 1# - ADDED ENTRY--PERSONAL NAME
Personal name Gattass, Marcelo
Affiliation (PUC-Rio, Brazil)
9 (RLIN) 426
700 1# - ADDED ENTRY--PERSONAL NAME
Personal name Meggiolaro, Marco
Affiliation (PUC-Rio, Brazil)
9 (RLIN) 427
856 4# - ELECTRONIC LOCATION AND ACCESS
Public note VIDEO
Uniform Resource Identifier <a href="https://www.youtube.com/watch?v=uKANJfw2ZP4&list=PLo4jXE-LdDTRkCsaH7C2rGXQg0wqKVYxp&index=2&t=0s">https://www.youtube.com/watch?v=uKANJfw2ZP4&list=PLo4jXE-LdDTRkCsaH7C2rGXQg0wqKVYxp&index=2&t=0s</a>
856 4# - ELECTRONIC LOCATION AND ACCESS
Public note EVENTO
Uniform Resource Identifier <a href="http://seminarios.impa.br/visualizar/9128">http://seminarios.impa.br/visualizar/9128</a>
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme Dewey Decimal Classification
Koha item type Books

No items available.

© 2023 IMPA Library | Customized & Maintained by Sérgio Pilotto


Powered by Koha