The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLVIII-2-2024
https://doi.org/10.5194/isprs-archives-XLVIII-2-2024-25-2024
https://doi.org/10.5194/isprs-archives-XLVIII-2-2024-25-2024
11 Jun 2024
 | 11 Jun 2024

ESTATE: A Large Dataset of Under-Represented Urban Objects for 3D Point Cloud Classification

Onur Can Bayrak, Zhenyu Ma, Elisa Mariarosaria Farella, Fabio Remondino, and Melis Uzar

Keywords: point cloud, deep learning, dataset, object classification, under-represented urban object

Abstract. Cityscapes contain a variety of objects, each with a particular role in urban administration and development. With the rapid growth and implementation of 3D imaging technology, urban areas are increasingly surveyed with high-resolution point clouds. This technical advancement extensively improves our ability to capture and analyse urban environments and their small objects. Deep learning algorithms for point cloud data have shown considerable capacity in 3D object classification but still face problems with generally under-represented objects (such as light poles or chimneys). This paper introduces the ESTATE dataset (https://github.com/3DOM-FBK/ESTATE), which combines available datasets of various sensors, densities, regions, and object types. It includes 13 classes featuring intensity and/or colour attributes. Tests using ESTATE demonstrate that the dataset improves the classification performance of deep learning techniques and could be a game-changer to advance in the 3D classification of urban objects.