Multi-Temporal Aerial Image Registration Using Semantic Features

TL;DR

This paper introduces a semantic feature extraction method for multitemporal aerial image registration that improves robustness and accuracy by focusing on invariant objects like roads, addressing challenges posed by seasonal foliage changes.

Contribution

The paper presents a novel semantic feature extraction approach using a segmentation network for improved multitemporal aerial image registration.

Findings

Robust registration across different years and seasons

Semantic features outperform classical handcrafted features

High accuracy in multitemporal aerial image alignment

Abstract

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.