Classification of Urban Scenes from Geo-referenced Images in Urban Street-View Context

Corina Iovan 1 David Picard 2 Nicolas Thome 3 Matthieu Cord 3
1 DIGIPLANTE - Modélisation de la croissance et de l'architecture des plantes
MAS - Mathématiques Appliquées aux Systèmes - EA 4037, CIRAD - Centre de Coopération Internationale en Recherche Agronomique pour le Développement, Inria Saclay - Ile de France, Ecole Centrale Paris
2 MIDI
ETIS - Equipes Traitement de l'Information et Systèmes
3 MALIRE - Machine Learning and Information Retrieval
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : This paper addresses the challenging problem of scene classification in street-view georeferenced images of urban environments. More precisely, the goal of this task is semantic image classification, consisting in predicting in a given image, the presence or absence of a pre-defined class (e.g. shops, vegetation, etc.). The approach is based on the BOSSA representation, which enriches the Bag of Words (BoW) model, in conjunction with the Spatial Pyramid Matching scheme and kernel-based machine learning techniques. The proposed method handles problems that arise in large scale urban environments due to acquisition conditions (static and dynamic objects/pedestrians) combined with the continuous acquisition of data along the vehicle's direction, the varying light conditions and strong occlusions (due to the presence of trees, traffic signs, cars, etc.) giving rise to high intra-class variability. Experiments were conducted on a large dataset of high resolution images collected from two main avenues from the 12th district in Paris and the approach shows promising results.
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00794980
Contributor : David Picard <>
Submitted on : Tuesday, June 11, 2013 - 12:12:07 PM
Last modification on : Wednesday, May 15, 2019 - 3:41:28 AM
Long-term archiving on : Thursday, September 12, 2013 - 2:30:11 AM

File

icmla_19092012-1.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00794980, version 1

Citation

Corina Iovan, David Picard, Nicolas Thome, Matthieu Cord. Classification of Urban Scenes from Geo-referenced Images in Urban Street-View Context. Machine Learning and Applications (ICMLA), 2012 11th International Conference on, Dec 2012, Boca Raton, Florida, United States. pp.339--344. ⟨hal-00794980⟩

Share

Metrics

Record views

680

Files downloads

507