Premium
67‐4: Visual Simultaneous Localization and Mapping with Deep Neural Network Based Loop Detection for Augmented Reality
Author(s) -
Li Yang,
Chen Chao Ping,
Liu Yuan,
Chen Jie,
Zhu Changzhao,
Peng Ziqi
Publication year - 2020
Publication title -
sid symposium digest of technical papers
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.351
H-Index - 44
eISSN - 2168-0159
pISSN - 0097-966X
DOI - 10.1002/sdtp.14042
Subject(s) - loop (graph theory) , artificial intelligence , augmented reality , computer science , artificial neural network , computer vision , set (abstract data type) , trajectory , deep neural networks , tracking (education) , human in the loop , pattern recognition (psychology) , mathematics , physics , combinatorics , psychology , pedagogy , astronomy , programming language
We present a visual simultaneous localization and mapping, in which a deep neural network is adopted for the loop detection. Its working principles, including the tracking, local mapping, loop detection, and global optimization, are set forth in detail. Its overall performance regarding the loop detection and trajectory estimation is investigated.