TerraMobilita/iQmulus urban point cloud analysis benchmark

• Published in: Computers & graphics Vol. 49; pp. 126 - 133
• Main Authors: Vallet, Bruno, Brédif, Mathieu, Serna, Andres, Marcotegui, Beatriz, Paparoditis, Nicolas
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.06.2015; Elsevier
• Series: Computers and Graphics
• Subjects: Benchmark; Benchmarking; Categories; Classification; Computer Science; Ground truth; Image Processing; Laser scanning; Lasers; Mobile mapping; Scene analysis; Segmentation; Semantics; Three dimensional models; Urban scene; Benchmark; Mobile mapping; Laser scanning; Segmentation; Urban scene; Classification; detection; urban scene; segmentation; mobile mapping; classification; analysis; laser scanning
• ISSN: 0097-8493; 1873-7684
• DOI: 10.1016/j.cag.2015.03.004

The objective of the TerraMobilita/iQmulus 3D urban analysis benchmark is to evaluate the current state of the art in urban scene analysis from mobile laser scanning (MLS) at large scale. A very detailed semantic tree for urban scenes is proposed. We call analysis the capacity of a method to separate the points of the scene into these categories (classification), and to separate the different objects of the same type for object classes (detection). A very large ground truth is produced manually in two steps using advanced editing tools developed especially for this benchmark. Based on this ground truth, the benchmark aims at evaluating the classification, detection and segmentation quality of the submitted results. [Display omitted] •Very rich data: high accuracy, high resolution, many attributes.•Massive data: 160 million annotated points thanks to a performant web based annotation tool (and many hours of work).•Rich semantics organized in a semantic tree with various levels of generalization.•Very objective evaluation metrics.