Visual place recognition: A survey from deep learning perspective. (May 2021)

• Record Type: Journal Article
• Authors: Zhang, Xiwu; Wang, Lei; Su, Yan
• Is Part Of: Pattern recognition. Volume 113(2021)
• Publication Date: 2021-05
• Subjects: Visual place recognition -- Deep learning -- Visual SLAM -- Survey; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2020.107760
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We provide a whole picture about deep learning-based visual place recognition. The differences and similarities between VPR and image retrieval are included. We review different kinds of CNN-based methods, novel CNN features and datasets for VPR. New tools such as GANs and multi-modality feature fusion are discussed for VPR. We discuss challenges, open issues and future directions of visual place recognition. Abstract: Visual place recognition has attracted widespread research interest in multiple fields such as computer vision and robotics. Recently, researchers have employed advanced deep learning techniques to tackle this problem. While an increasing number of studies have proposed novel place recognition methods based on deep learning, few of them has provided a whole picture about how and to what extent deep learning has been utilized for this issue. In this paper, by delving into over 200 references, we present a comprehensive survey that covers various aspects of place recognition from deep learning perspective. We first present a brief introduction of deep learning and discuss its opportunities for recognizing places. After that, we focus on existing approaches built upon convolutional neural networks, including off-the-shelf and specifically designed models as well as novel image representations. We also discuss challenging problems in place recognition and present an extensive review of the corresponding datasets. To explore the future directions, we describe open issues and some new tools, for instance, generative adversarial networks, semantic scene understanding and multi-modality feature learning for this research topic. Finally, a conclusion is drawn for this paper.