Pregled bibliografske jedinice broj: 387159
Two-stage segmentation for detection of suspicious objects in aerial and long-range surveillance applications
Two-stage segmentation for detection of suspicious objects in aerial and long-range surveillance applications // Recent Advances in Automation & Information, Proceedings of the 10th WSEAS Int. Conf. on Automation & Information (ICAI'09) / Nikos E.Mastorakis (ur.).
Prag: WSEAS Press, 2009. str. 152-156 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 387159 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Two-stage segmentation for detection of suspicious objects in aerial and long-range surveillance applications
Autori
Papić, Vladan ; Turić, Hrvoje ; Dujmić, Hrvoje
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Recent Advances in Automation & Information, Proceedings of the 10th WSEAS Int. Conf. on Automation & Information (ICAI'09)
/ Nikos E.Mastorakis - Prag : WSEAS Press, 2009, 152-156
ISBN
978-960-474-064-2
Skup
Int. Conf. on Automation & Information (ICAI'09)
Mjesto i datum
Prag, Češka Republika, 23.03.2009. - 25.03.2009
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Image segmentation; mean shift; object detection; aerial images
Sažetak
This paper presents a novel two-stage data segmentation approach for detection of artificial materials and objects in non-urban terrain. High resolution image of the unknown terrain taken with the digital camera from relatively large distance is divided into smaller sub-images for further processing. Each sub-image is segmented and information about obtained cluster centers is transferred to the next stage. Second segmentation stage uses information about cluster centers from all sub-images and applies the same clustering method to this data set. Finally, decision-making module evaluates all potential candidate segments and eventually proposes segments that have high possibility of presenting artificial material or object in the input image.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo
POVEZANOST RADA
Projekti:
023-0231924-1661 - ICT sustavi i usluge temeljeni na integraciji informacija (Rožić, Nikola, MZOS ) ( CroRIS)
023-0232006-1662 - Računalni vid u identifikaciji kinematike sportskih aktivnosti (Papić, Vladan, MZOS ) ( CroRIS)
177-0232006-1662 - Računalni vid u identifikaciji kinematike sportskih aktivnosti
Ustanove:
Fakultet elektrotehnike, strojarstva i brodogradnje, Split,
Prirodoslovno-matematički fakultet, Split
