June 11, 2024Open Access

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

Key Points

The ESTATE dataset significantly improves classification performance for urban objects, enhancing deep learning applications.
Tests revealed improvements of up to 20% in accuracy for under-represented objects like light poles and chimneys.
Analysis involved using diverse datasets from various sensors, with a focus on improving object representation in urban scenes for deep learning algorithms. According to preliminary tests, the dataset includes 13 distinct classes of urban objects with specific attributes.

Abstract

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.

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

Key Points

Abstract

Cite This Study

Also Consider

Also Consider