Detecting Building Changes between Airborne Laser Scanning and Photogrammetric Data

Detecting topographic changes in an urban environment and keeping city-level point clouds up-to-date are important tasks for urban planning and monitoring. In practice, remote sensing data are often available only in different modalities for two epochs. Change detection between airborne laser scanning data and photogrammetric data is challenging due to the multi-modality of the input data and dense matching errors. The data contain three sub-datasets: "ALS-g-raw.las" are the ground laser points. "ALS-u-raw.las" are the non-ground laser points. "RawPC(lasgrid)(39M).las" are the dense matching points. Our method proposes an end-to-end pseudo-Siamese convolutional neural network (PSI-CNN) for change detection between the two types of point clouds.

change detection; multimodal data; convolutional neural networks; Siamese networks; airborne laser scanning; dense image matching