Badly-posed classification of remotely sensed images-an experimental comparison of existing data labelling systems (Articolo in rivista)

Type

• Articolo in rivista (Classe)
• Prodotto della ricerca (Classe)

Label

• Badly-posed classification of remotely sensed images-an experimental comparison of existing data labelling systems (Articolo in rivista) (literal)

Anno

• 2006-01-01T00:00:00+01:00 (literal)

Alternative label

• A. Baraldi, L. Bruzzone, P. Blonda and L. Carlin (2006)
  Badly-posed classification of remotely sensed images-an experimental comparison of existing data labelling systems
  in IEEE transactions on geoscience and remote sensing
  (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori

• A. Baraldi, L. Bruzzone, P. Blonda and L. Carlin (literal)

Pagina inizio

• 214 (literal)

Pagina fine

• 235 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#numeroVolume

• 44 (literal)

Rivista

• IEEE transactions on geoscience and remote sensing (Rivista)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#note

• This work was supported by the European Union under Contract EVG1-CT-2001-00055LEWIS. CNR-ISSIA was a partner of the project and Dr.ssa P. Blonda was the Scientific Responsible. (literal)

Note

• ISI Web of Science (WOS) (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni

• P. Blonda, primo ricercatore al CNR-ISSIA. A. Baraldi, assegno di ricerca al CNR-ISSIA al momento della sottomissione del lavoro (Aprile 2004). Attualmente lavora a contratto presso JRC di ISPRA. L. Bruzzone, Università di Trento. L. Carlin, Università di Trento. (literal)

Titolo

• Badly-posed classification of remotely sensed images-an experimental comparison of existing data labelling systems (literal)

Abstract

• Abstract—Although underestimated in practice, the small/unrepresentative sample problem is likely to affect a large segment of real-world remotely sensed (RS) image mapping applications where ground truth knowledge is typically expensive, tedious, or difficult to gather. Starting from this realistic assumption, subjective (weak) but ample evidence of the relative effectiveness of existing unsupervised and supervised data labeling systems is collected in two RS image classification problems. To provide a fair assessment of competing techniques, first the two selected image datasets feature different degrees of image fragmentation and range from poorly to ill-posed. Second, different initialization strategies are tested to pass on to the mapping system at hand the maximally informative representation of prior (ground truth) knowledge. For estimating and comparing the competing systems in terms of learning ability, generalization capability, and computational efficiency when little prior knowledge is available, the recently published data-driven map quality assessment (DAMA) strategy, which is capable of capturing genuine, but small, image details in multiple reference cluster maps, is adopted in combination with a traditional resubstitution method. Collected quantitative results yield conclusions about the potential utility of the alternative techniques that appear to be realistic and useful in practice, in line with theoretical expectations and the qualitative assessment of mapping results by expert photointerpreters. (literal)

Prodotto di

• Sistemi e modelli per l'estrazione dell'informazione da segnali ed immagini (TA.P06.007.002) (Modulo)
• Institute of intelligent systems for automation (ISSIA) (Istituto)

Autore CNR

• PALMA NICOLETTA BLONDA (Persona)

Incoming links:

Prodotto

• Institute of intelligent systems for automation (ISSIA) (Istituto)
• Sistemi e modelli per l'estrazione dell'informazione da segnali ed immagini (TA.P06.007.002) (Modulo)

Autore CNR di

• PALMA NICOLETTA BLONDA (Persona)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#rivistaDi

• IEEE transactions on geoscience and remote sensing (Rivista)