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). pp. 651-662. DOI https://doi.org/10.1109/TASE.2017.2664920
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). pp. 651-662. DOI https://doi.org/10.1109/TASE.2017.2664920
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). pp. 651-662. DOI https://doi.org/10.1109/TASE.2017.2664920
Abstract
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 |
---|---|
Uncontrolled Keywords: | Convolutional neural network (CNN); deep learning; depth encoding; pose regression; relocalization |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 02 Mar 2020 11:51 |
Last Modified: | 30 Oct 2024 16:59 |
URI: | http://repository.essex.ac.uk/id/eprint/26982 |
Available files
Filename: FINAL VERSION.pdf