Logo image
Direct Aerial Visual Localization using Panoramic Synthetic Images and Domain Adaptation
Conference proceeding

Direct Aerial Visual Localization using Panoramic Synthetic Images and Domain Adaptation

Danial Sufiyan, Luke Soe Thura Win, Shane Kyi Hla Win, U-Xuan Tan, Shaohui Foong, IEEE and Danial Sufiyan Bin Shaiful
IEEE/ASME International Conference on Advanced Intelligent Mechatronics, pp.265-271
15/07/2024

Abstract

Adaptation models Location awareness Prototypes Satellite navigation systems Soft sensors Three-dimensional displays Visualization
In the realm of aerial vehicle navigation, the reliance on satellite-based and external localization methods presents vulnerabilities to various interferences. This drives the necessity for a self-sufficient absolute navigational system. Image-based localization methods, particularly Absolute Visual Localization (AVL), directly determine the pose in the global frame from a given image. A workflow using 360-degree panoramic images for image-based localization, driven by a Deep Convolutional Neural Network (DCNN), is proposed. Utilizing panoramic imagery offers the advantage of encompassing visual information from all angles. Synthetic data generated from multiple sources such as photogrammetry, Open Street Map (OSM), and official 3D building data are used to train the localization network. Domain adaptation using cycleGAN is also used to bridge the Sim2Real gap and enhance model performance. Utilizing OSM features are shown to improve localization performance (median Euclidean error) by at least 13%, and a further 20% with cycleGAN dataset augmentation. Closed loop control is also achieved using a trained model, enabling a quadrotor prototype to hover within a 1 m circle.

Metrics

1 Record Views

Details

Logo image