# Robust Building-based Registration of Airborne LiDAR Data and Optical Imagery on Urban Scenes

## TL;DR

This paper introduces a robust method for registering airborne LiDAR data with optical imagery of urban scenes by leveraging building region extraction and graph transformation matching, improving data alignment for better fusion.

## Contribution

The paper presents a novel building-based registration approach combining segmentation and graph matching to align LiDAR and optical data acquired from different platforms and times.

## Key findings

- Significantly reduces relative shifts between datasets
- Enables high-quality data fusion
- Improves registration robustness in urban scenes

## Abstract

The motivation of this paper is to address the problem of registering airborne LiDAR data and optical aerial or satellite imagery acquired from different platforms, at different times, with different points of view and levels of detail. In this paper, we present a robust registration method based on building regions, which are extracted from optical images using mean shift segmentation, and from LiDAR data using a 3D point cloud filtering process. The matching of the extracted building segments is then carried out using Graph Transformation Matching (GTM) which allows to determine a common pattern of relative positions of segment centers. Thanks to this registration, the relative shifts between the data sets are significantly reduced, which enables a subsequent fine registration and a resulting high-quality data fusion.