Aerial Map-Based Navigation Using Semantic Segmentation and Pattern Matching
This addresses the challenge of accurate localization for unmanned aircraft in scenarios where traditional methods might fail, representing an incremental improvement by applying existing deep learning techniques in a novel configuration.
The paper tackles the problem of map-based navigation for unmanned aircraft by reducing image-based localization to a pattern matching problem using semantic segmentation of aerial images, and demonstrates through feasibility analysis with simulated images that the system can provide positions without requiring altitude information or camera models.
This paper proposes a novel approach to map-based navigation system for unmanned aircraft. The proposed system attempts label-to-label matching, not image-to-image matching, between aerial images and a map database. The ground objects can be labelled by deep learning approaches and the configuration of the objects is used to find the corresponding location in the map database. The use of the deep learning technique as a tool for extracting high-level features reduces the image-based localization problem to a pattern matching problem. This paper proposes a pattern matching algorithm that does not require altitude information or a camera model to estimate the absolute horizontal position. The feasibility analysis with simulated images shows the proposed map-based navigation can be realized with the proposed pattern matching algorithm and it is able to provide positions given the labelled objects.