Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloTarget recognition by components for mobile robot navigation
Anno di pubblicazione2003
FormatoCartaceo
Autore/iCicirelli, G.; D'Orazio, T.; Distante, A.
Affiliazioni autoriIstituto Di Studi Sui Sistemi Intelligenti Per L'automazione, Bari
Autori CNR e affiliazioni
  • ARCANGELO DISTANTE
  • TIZIANA RITA D'ORAZIO
  • GRAZIA CICIRELLI
Lingua/e
  • inglese
AbstractThis paper presents a vision-based technique for detecting targets of the environment which have to be reached by an autonomous mobile robot during its navigational tasks. The targets the robot has to reach are the doors of the authors' office building. The detection of the door has been performed by detecting its most significant components in the image and it is based on data classification. Two neural classifiers have been trained for recognizing single components of the door. Then a combining algorithm, based on heuristic considerations, checks that they are in the proper geometric configuration of the structure of the door. The novelty of this work is to use together colour and shape information for identifying features and for detecting the components of the target. The approach, based on learning by components, is able to cleverly solve the problems of scale changes, perspective variations and partial occlusions. The obtained detecting system has been tested on a large test set of real images showing a high reliability and robustness: doors of different rooms, under different illumination conditions and by different viewpoints have been successfully recognized. Results in terms of door detection rate and false positive rate are presented throughout the paper.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da281
Pagine a297
Pagine totali-
RivistaJournal of experimental and theoretical artificial intelligence (Print)
Attiva dal 1989
Editore: Taylor & Francis, - London
Paese di pubblicazione: Regno Unito
Lingua: inglese
ISSN: 0952-813X
Titolo chiave: Journal of experimental and theoretical artificial intelligence (Print)
Titolo proprio: Journal of experimental and theoretical artificial intelligence. (Print)
Titolo abbreviato: J. exp. theor. artif. intell. (Print)
Titolo alternativo: JETAI (London) (Print)
Numero volume della rivista15
Fascicolo della rivista3
DOI10.1080/0952813021000039430
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • Scopus (Codice:2-s2.0-0038044819)
Parole chiaveDoor-detection, Learning by components, Neural network
Link (URL, URI)http://www.scopus.com/record/display.url?eid=2-s2.0-0038044819&origin=inward
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione-
Note/Altre informazioniPublication on Taylor & Francis international journal, cited in INSPEC; Elsevier Bibliographic Data Base; Zentralblatt MATH; Ebsco Publishing; ISI Current Contents; Cambridge Scientific Abstracts; American Psychological Association; New Jour; Compumath Citation Index; Research Alert; Sci Search; Computers & Artificial Intelligence; Artificial Intelligence Abstracts; The Computer Literature Index; SciBase and Zetoc. The current impact factor is 0.302.
Strutture CNR
  • ISSIA — Istituto di studi sui sistemi intelligenti per l'automazione
Moduli/Attività/Sottoprogetti CNR-
Progetti Europei-
Allegati

Dati storici
I dati storici non sono modificabili, sono stati ereditati da altri sistemi (es. Gestione Istituti, PUMA, ...) e hanno solo valore storico.
Area disciplinareAI, Robotics & Automatic Control
Area valutazione CIVRScienze matematiche e informatiche
Rivista ISIJOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE [10277J0]
Descrizione sintetica del prodottoThe journal publication deals with the recognition of a target of the environment for the navigation of a mobile robot. The capability of recognizing particular objects is very important in robot navigation framework either in indoor or in outdoor environments. The challenging issue faced in the work is the detection of a natural occurring object of the environment: no intervention on the working environment is needed. The second novel aspect of the detection approach is its autoconsistency: it is a robust and reliable system able to deal with scale changes, lighting conditions and viewpoint variations without any parameter adjustment.