Pregled bibliografske jedinice broj: 294507
Detection of mistletoe in digital colour infrared images of infested fir trees
Detection of mistletoe in digital colour infrared images of infested fir trees // Periodicum Biologorum, 109 (2007), 1; 67-75 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 294507 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Detection of mistletoe in digital colour infrared images of infested fir trees
Autori
Pernar, Renata ; Bajić, Milan ; Ančić, Mario ; Seletković, Ante ; Idžojtić, Marilena
Izvornik
Periodicum Biologorum (0031-5362) 109
(2007), 1;
67-75
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
silver fir; mistletoe; detection; classification; digital near infrared camera; error matrix
Sažetak
Silver fir (Abies alba Mill.) is the most widely distributed and the most important commercial conifer species in Croatia. However, silver fir is also the most endangered tree species in these regions. The results of field research show a significant presence of mistletoe (Viscum album L. ssp. abietis (Wiesb.) Abrom.) on silver firs in Croatia. The current work deals with the issue of mistletoe detection, while our previous research was aimed at developing an efficient method of mistletoe imagery acquisition. Ground-based tests, were aimed at formulating a method that will be implemented in the aerial acquisition system. A digital camera MS-3100 and a hyperspectral line scanner V9 covering visible and near infrared bands were used with the acquisition systems. In this article we analyse the suitability of the supervised classification, unsupervised classification combined by interactive manual merging of classes for the detection of mistletoe on fir. While the spectral resolution of available sensors is limited to three channels in visible wavelengths (blue, green and red) and one in near infrared (NIR) wavelengths, several enhancement methods were used with the aim of increasing the probability of the detection of mistletoe. The achieved overall classification accuracy was in the range of 62.50 to 70.56%. The results confirm the expectation that mistletoe can be detected using a digital visible near infrared (VNIR) camera and hybrid interpretation that consists of unsupervised classification and the manual merging of clusters. The hyperspectral mistletoe analysis provided the first images of the mistletoe reflection spectrum.
Izvorni jezik
Engleski
Znanstvena područja
Šumarstvo
POVEZANOST RADA
Projekti:
068-0681966-2786 - Praćenje zdravstvenog stanja šuma metodama daljinskih istraživanja (Pernar, Renata, MZOS ) ( CroRIS)
Ustanove:
Geodetski fakultet, Zagreb,
Fakultet šumarstva i drvne tehnologije
Profili:
Milan Bajić
(autor)
Mario Ančić
(autor)
Renata Pernar
(autor)
Ante Seletković
(autor)
Marilena Idžojtić
(autor)
Citiraj ovu publikaciju:
Časopis indeksira:
- Web of Science Core Collection (WoSCC)
- Science Citation Index Expanded (SCI-EXP)
- SCI-EXP, SSCI i/ili A&HCI
- Scopus
Uključenost u ostale bibliografske baze podataka::
- Geobase