Style Alignment based Dynamic Observation Method for UAV-View Geo-localization

Abstract

The task of UAV-view geo-localization is to estimate the localization of a query satellite/drone image by matching it against a reference dataset consisting of drone/satellite images. Though tremendous strides have been made in feature alignment between satellite and drone views, vast differences in both inter and intra-class due to changes in viewpoint, altitude, and lighting remain a huge challenge. In this paper, a style alignment based dynamic observation method for UAV-view geo-localization is proposed to meet the above challenges from two perspectives: visual style transformation and surrounding noise control. Specifically, we introduce a style alignment strategy to transfrom the diverse visual style of drone-view images into a unified satellite images visual style. Then a dynamic observation module is designed to evaluate the spatial distribution of images by mimicking human observation habits. It is featured by the hierarchical attention block (HAB) with a dual-square-ring stream structure, to reduce surrounding noise and geographical deformation. In addition, we propose a deconstruction loss to push away features of different geo-tags and squeeze knowledge from unmatched images by correlation calculation. The experimental results demonstrate the state-of-the-art performance of our model on benchmarked datasets. In particular, when compared to the prior art on University-1652, our results surpass the best of them (FSRA), while only requiring 2x fewer parameters. Code will be released at https://github.com/Xcco1/SA\_DOM

has published on IEEE Transactions on Geoscience and Remote Sensing, 2023

References in corpus (13)

• FaceNet: A Unified Embedding for Face Recognition and Clustering
• Graph Convolutional Networks for Hyperspectral Image Classification
• An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing
• A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification
• Dual-Path Convolutional Image-Text Embeddings with Instance Loss
• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization
• A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization
• Deep Learning for Person Re-identification: A Survey and Outlook
• Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval
• Parallel Structure from Motion for UAV Images via Weighted Connected Dominating Set
• Multiple-environment Self-adaptive Network for Aerial-view Geo-localization
• Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments