SSA-Net: Spatial Scale Attention Network for Image-Based Geo-Localization
- 15 October 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 19 (1545598X) , 1-5
Abstract
Image-based geo-localization is estimating the location of a query image by matching it to a large amount of images in geo-tagged database. This matching task is very challenging due to the vast differences in visual appearance or modality of image pairs on different platforms, for example, one image from the RGB camera, the other from the light detection and ranging (LiDAR) sensor. The spatial layout of the scene can provide important clues and significantly reduce matching ambiguity. Therefore, we propose a novel deep network that embeds spatial configuration of the scenes into feature representation. Specifically, we design a spatial-scale attention (SSA) module to highlight the salience correspondence layout features at different scales. The encoded features not only represent the emergence of certain objects, but also reflect the relative locations of the objects. By this way, we learn more discriminative deep feature representations, leading to a higher recall. The experimental results on two standard cross-view benchmark datasets (CVUSA and CVACT) and a cross-modal dataset (GRAL) demonstrate that our method performs better than the state-of-the-art methods. Remarkably, the recall rate@top-1 improves from 27.6% to 40.5% on the GRAL dataset.Keywords
Funding Information
- National Natural Science Foundation of China (U19B2037)
- National Natural Science Foundation of China (61971356)
- National Natural Science Foundation of China (61801395)
- National Natural Science Foundation of China (61971273)
- National Natural Science Foundation of China (62071384)
- National Natural Science Foundation of Shaanxi Province (2020GM-137)
- Seed Foundation of Innovation and Creation for Graduate Students in Northwestern Polytechnical University (CX2020183)
This publication has 27 references indexed in Scilit:
- Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing DataIEEE Geoscience and Remote Sensing Letters, 2017
- Partial Randomness Hashing for Large-Scale Remote Sensing Image RetrievalIEEE Geoscience and Remote Sensing Letters, 2017
- Localizing and Orienting Street Views Using Overhead Imagery2016
- Wide-Area Image Geolocalization with Aerial Reference Imagery2015
- Deep feature learning with relative distance comparison for person re-identificationPattern Recognition, 2015
- Robust Face Recognition via Multimodal Deep Face RepresentationIEEE Transactions on Multimedia, 2015
- On the location dependence of convolutional neural network features2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- SURF: Speeded Up Robust Features2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004