000 02212n a2200289#a 4500
001 39556
003 P5A
005 20221213140630.0
007 cr cuuuuuauuuu
008 200122s20202020bl por d
035 _aocm51338542
040 _aP5A
_cP5A
090 _acs
100 1 _aSoares, João Carlos Virgolino
_u(PUC-Rio, Brazil)
_9425
245 1 0 _aVisual SLAM in Human Populated Environments:
_bExploring the Trade-off between Accuracy and Speed of YOLO and Mask R-CNN/
_cJ. C. V. Soares.
246 1 1 _aSeminário de Computação Gráfica:
260 _aRio de Janeiro:
_bIMPA,
_c2020.
300 _avideo online
505 2 _aAbstract: 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 0 4 _aMatematica.
_2larpcal
_919899
697 _aCongressos e Seminários.
_923755
700 1 _aGattass, Marcelo
_u(PUC-Rio, Brazil)
_9426
700 1 _aMeggiolaro, Marco
_u(PUC-Rio, Brazil)
_9427
856 4 _zVIDEO
_uhttps://www.youtube.com/watch?v=uKANJfw2ZP4&list=PLo4jXE-LdDTRkCsaH7C2rGXQg0wqKVYxp&index=2&t=0s
856 4 _zEVENTO
_uhttp://seminarios.impa.br/visualizar/9128
942 _2ddc
_cBK
999 _aVISUAL SLAM in Human Populated Environments: Exploring the Trade-off between Accuracy and Speed of YOLO and Mask R-CNN. J. C. V. Soares. Rio de Janeiro: IMPA, 2020. video online. Disponível em: <https://www.youtube.com/watch?v=uKANJfw2ZP4&list=PLo4jXE-LdDTRkCsaH7C2rGXQg0wqKVYxp&index=2&t=0s>. Acesso em: 22 jan. 2020.
_c38092
_d38092