TerraMobilita/IQmulus Urban Point Cloud Classification Benchmark

Abstract : The object 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). A very detailed semantic tree for urban scenes is proposed (cf Figure 1). 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). The ground truth is produced manually in two steps using advanced editing tools developed especially for this benchmark. Base on this ground truth, the benchmark will aim at evaluating both the classification, detection and segmentation quality of the submitted results.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [5 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01101621
Contributor : Beatriz Marcotegui <>
Submitted on : Friday, January 9, 2015 - 10:37:23 AM
Last modification on : Monday, November 12, 2018 - 11:03:10 AM
Document(s) archivé(s) le : Friday, September 11, 2015 - 6:24:08 AM

File

2014-sgp-iqmulus.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01101621, version 1

Citation

Mathieu Brédif, Bruno Vallet, Andrés Serna, Beatriz Marcotegui, Nicolas Paparoditis. TerraMobilita/IQmulus Urban Point Cloud Classification Benchmark. Workshop on Processing Large Geospatial Data, Jul 2014, Cardiff, United Kingdom. ⟨hal-01101621⟩

Share

Metrics

Record views

244

Files downloads

232