Dynamic-SLAM: Semantic monocular visual localization and mapping based on deep learning in dynamic environment

• Published in: Robotics and autonomous systems Vol. 117; pp. 1 - 16
• Main Authors: Xiao, Linhui, Wang, Jinge, Qiu, Xiaosong, Rong, Zheng, Zou, Xudong
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.07.2019
• Subjects: Dynamic environment; Object detection; Semantics; Simultaneous localization and mapping (SLAM); Simultaneous localization and mapping (SLAM); Semantics; Object detection; Dynamic environment

When working in dynamic environment, traditional SLAM framework performs poorly due to interference from dynamic objects. By taking advantages of deep learning in object detection, a semantic simultaneous localization and mapping framework named Dynamic-SLAM is proposed, in order to solve the proble...