GSAP: A Global Structure Attention Pooling Method for Graph-Based Visual Place Recognition

• Published in: Remote sensing (Basel, Switzerland) Vol. 13; no. 8; p. 1467
• Main Authors: Yang, Yukun, Ma, Bo, Liu, Xiangdong, Zhao, Liang, Huang, Shoudong
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.04.2021
• Subjects: Accuracy; Classification; Construction; Deep learning; graph construction; graph convolution; graph global pooling; graph neural networks; Image retrieval; Information processing; Localization; Machine learning; Methods; Neural networks; Object recognition; Remote sensing; Robustness; Semantics; visual place recognition; Visual tasks
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs13081467

The Visual Place Recognition problem aims to use an image to recognize the location that has been visited before. In most of the scenes revisited, the appearance and view are drastically different. Most previous works focus on the 2-D image-based deep learning method. However, the convolutional features are not robust enough to the challenging scenes mentioned above. In this paper, in order to take advantage of the information that helps the Visual Place Recognition task in these challenging scenes, we propose a new graph construction approach to extract the useful information from an RGB image and a depth image and fuse them in graph data. Then, we deal with the Visual Place Recognition problem as a graph classification problem. We propose a new Global Pooling method—Global Structure Attention Pooling (GSAP), which improves the classification accuracy by improving the expression ability of the Global Pooling component. The experiments show that our GSAP method improves the accuracy of graph classification by approximately 2–5%, the graph construction method improves the accuracy of graph classification by approximately 4–6%, and that the whole Visual Place Recognition model is robust to appearance change and view change.