Research Repository

Indoor Relocalization in Challenging Environments With Dual-Stream Convolutional Neural Networks

Li, Ruihao and Liu, Qiang and Gui, Jianjun and Gu, Dongbing and Hu, Huosheng (2018) 'Indoor Relocalization in Challenging Environments With Dual-Stream Convolutional Neural Networks.' IEEE Transactions on Automation Science and Engineering, 15 (2). 651 - 662. ISSN 1042-296X

FINAL VERSION.pdf - Accepted Version

Download (19MB) | Preview


This paper presents an indoor relocalization system using a dual-stream convolutional neural network (CNN) with both color images and depth images as the network inputs. Aiming at the pose regression problem, a deep neural network architecture for RGB-D images is introduced, a training method by stages for the dual-stream CNN is presented, different depth image encoding methods are discussed, and a novel encoding method is proposed. By introducing the range information into the network through a dual-stream architecture, we not only improved the relocalization accuracy by about 20% compared with the state-of-the-art deep learning method for pose regression, but also greatly enhanced the system robustness in challenging scenes such as large-scale, dynamic, fast movement, and night-time environments. To the best of our knowledge, this is the first work to solve the indoor relocalization problems based on deep CNNs with RGB-D camera. The method is first evaluated on the Microsoft 7-Scenes data set to show its advantage in accuracy compared with other CNNs. Large-scale indoor relocalization is further presented using our method. The experimental results show that 0.3 m in position and 4° in orientation accuracy could be obtained. Finally, this method is evaluated on challenging indoor data sets collected from motion capture system. The results show that the relocalization performance is hardly affected by dynamic objects, motion blur, or night-time environments.

Item Type: Article
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Elements
Date Deposited: 02 Mar 2020 11:51
Last Modified: 02 Mar 2020 11:51

Actions (login required)

View Item View Item