Multi-Temporal Aerial Image Registration Using Semantic Features
This work addresses image registration challenges in remote sensing for applications like environmental monitoring, but it is incremental as it builds on existing semantic segmentation techniques.
The paper tackles the problem of registering aerial images taken at different times by proposing a semantic feature extraction method that uses temporally invariant objects like roads to handle changes such as foliage, achieving good robustness and accuracy in experiments across years and seasons.
A semantic feature extraction method for multitemporal high resolution aerial image registration is proposed in this paper. These features encode properties or information about temporally invariant objects such as roads and help deal with issues such as changing foliage in image registration, which classical handcrafted features are unable to address. These features are extracted from a semantic segmentation network and have shown good robustness and accuracy in registering aerial images across years and seasons in the experiments.