Online Visual Place Recognition via Saliency Re-identification

Abstract

As an essential component of visual simultaneous localization and mapping (SLAM), place recognition is crucial for robot navigation and autonomous driving. Existing methods often formulate visual place recognition as feature matching, which is computationally expensive for many robotic applications with limited computing power, e.g., autonomous driving and cleaning robot. Inspired by the fact that human beings always recognize a place by remembering salient regions or landmarks that are more attractive or interesting than others, we formulate visual place recognition as saliency re-identification. In the meanwhile, we propose to perform both saliency detection and re-identification in frequency domain, in which all operations become element-wise. The experiments show that our proposed method achieves competitive accuracy and much higher speed than the state-of-the-art feature-based methods. The proposed method is open-sourced and available at https://github.com/wh200720041/SRLCD.git.

Accepted by IEEE/RSJ International Conference on Intelligent Robots and Systems 2020 (IROS)

References in corpus (9)

• ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
• Review of Visual Saliency Detection with Comprehensive Information
• Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection
• iBoW-LCD: An Appearance-based Loop Closure Detection Approach using Incremental Bags of Binary Words
• Multi-Process Fusion: Visual Place Recognition Using Multiple Image Processing Methods
• HBST: A Hamming Distance embedding Binary Search Tree for Visual Place Recognition
• Kervolutional Neural Networks
• Visual Place Recognition with Probabilistic Vertex Voting
• Correlation Flow: Robust Optical Flow Using Kernel Cross-Correlators

Cited by in corpus (5)

• Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution
• SymbioLCD: Ensemble-Based Loop Closure Detection using CNN-Extracted Objects and Visual Bag-of-Words
• AirCode: A Robust Object Encoding Method
• Saliency for free: Saliency prediction as a side-effect of object recognition
• Spectrum-inspired Low-light Image Translation for Saliency Detection