Condition-invariant and compact visual place description by convolutional autoencoder

Ye, Hanjing1,2; Chen, Weinan3; Yu, Jingwen1,2; He, Li1,2; Guan, Yisheng3; Zhang, Hong1,2

2023-03-01

10.1017/S0263574723000085

ROBOTICA   Impact Factor & Quartile

0263-5747

1469-8668

Visual place recognition (VPR) in condition-varying environments is still an open problem. Popular solutions are convolutional neural network (CNN)-based image descriptors, which have been shown to outperform traditional image descriptors based on hand-crafted visual features. However, there are two drawbacks of current CNN-based descriptors: (a) their high dimension and (b) lack of generalization, leading to low efficiency and poor performance in real robotic applications. In this paper, we propose to use a convolutional autoencoder (CAE) to tackle this problem. We employ a high-level layer of a pre-trained CNN to generate features and train a CAE to map the features to a low-dimensional space to improve the condition invariance property of the descriptor and reduce its dimension at the same time. We verify our method in four challenging real-world datasets involving significant illumination changes, and our method is shown to be superior to the state-of-the-art. The code of our work is publicly available at https://github.com/MedlarTea/CAE-VPR.

visual place recognition dimension reduction convolutional autoencoder visual navigation

SCI

English

First ; Corresponding

Leading Talents Program of Guangdong Province[2019QN01X761] ; National Nature Science Foundation of China[62103179]

Robotics

Robotics

WOS:000950064500001

CAMBRIDGE UNIV PRESS

ENGINEERING

Web of Science

1.Southern Univ Sci & Technol, Shenzhen Key Lab Robot & Comp Vis, Shenzhen, Peoples R China
2.Southern Univ Sci & Technol, Dept Elect & Elect Engn, Shenzhen, Peoples R China
3.Guangdong Univ Technol, Sch Mech & Elect Engn, Guangzhou, Peoples R China

Ye, Hanjing,Chen, Weinan,Yu, Jingwen,et al. Condition-invariant and compact visual place description by convolutional autoencoder[J]. ROBOTICA,2023.

Ye, Hanjing,Chen, Weinan,Yu, Jingwen,He, Li,Guan, Yisheng,&Zhang, Hong.(2023).Condition-invariant and compact visual place description by convolutional autoencoder.ROBOTICA.

Ye, Hanjing,et al."Condition-invariant and compact visual place description by convolutional autoencoder".ROBOTICA (2023).