prikaz prve stranice dokumenta Tehnike hiperspektralne analize za rano otkrivanje i klasifikaciju uzročnika biljnih bolesti
  Download
PDF 941.46 KB
undergraduate thesis
Tehnike hiperspektralne analize za rano otkrivanje i klasifikaciju uzročnika biljnih bolesti
Zadar: University of Zadar, 2020. urn:nbn:hr:162:074515
Zdrilić, Anđelo
University of Zadar
Department of Ecology, Agronomy and Aquaculture

Institutional repository: University of Zadar Institutional Repository

Cite this document

Zdrilić, A. (2020). Tehnike hiperspektralne analize za rano otkrivanje i klasifikaciju uzročnika biljnih bolesti (Undergraduate thesis). Zadar: University of Zadar. Retrieved from https://urn.nsk.hr/urn:nbn:hr:162:074515

Zdrilić, Anđelo. "Tehnike hiperspektralne analize za rano otkrivanje i klasifikaciju uzročnika biljnih bolesti." Undergraduate thesis, University of Zadar, 2020. https://urn.nsk.hr/urn:nbn:hr:162:074515

Zdrilić, Anđelo. "Tehnike hiperspektralne analize za rano otkrivanje i klasifikaciju uzročnika biljnih bolesti." Undergraduate thesis, University of Zadar, 2020. https://urn.nsk.hr/urn:nbn:hr:162:074515

Zdrilić, A. (2020). 'Tehnike hiperspektralne analize za rano otkrivanje i klasifikaciju uzročnika biljnih bolesti', Undergraduate thesis, University of Zadar, accessed 30 November 2024, https://urn.nsk.hr/urn:nbn:hr:162:074515

Zdrilić A. Tehnike hiperspektralne analize za rano otkrivanje i klasifikaciju uzročnika biljnih bolesti [Undergraduate thesis]. Zadar: University of Zadar; 2020 [cited 2024 November 30] Available at: https://urn.nsk.hr/urn:nbn:hr:162:074515

A. Zdrilić, "Tehnike hiperspektralne analize za rano otkrivanje i klasifikaciju uzročnika biljnih bolesti", Undergraduate thesis, University of Zadar, Zadar, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:162:074515

Metadata
TitleTehnike hiperspektralne analize za rano otkrivanje i klasifikaciju uzročnika biljnih bolesti
Title (english)Techniques in hyperspectral analysis used for early detection and classifitation of plant pathogens
AuthorAnđelo Zdrilić
MentorTomislav Kos (mentor)
Committee memberSlaven Zjalić (predsjednik povjerenstva)
Committee memberTomislav Kos (član povjerenstva)
Committee memberZoran Šikić (član povjerenstva)
GranterUniversity of Zadar
(Department of Ecology, Agronomy and Aquaculture)
Zadar
Defense date and country2020-09-21, Croatia
Scientific / art field,
discipline and subdiscipline		BIOTECHNICAL SCIENCES
Agronomy
Phytomedicine
Abstract
Hiperspektralne analize slika omogućuju lakše određivanje stupnja razvoja biljnih bolesti, klasifikaciju biljaka na zdrave i zaražene, te otkrivanje biljnog stresa. Cilj ovih analiza je pregledati zdravlje većeg broja biljaka, predvidjeti mogućnost razvoja bolesti i stresa bilja, koristeći umjetnu inteligenciju, uz uvjet da su te tehnike brže, bolje i ekonomičnije od ljudskog rada. Ovaj rad bavi se tematikom detekcije biljnih bolesti i stresa biljaka. Poljoprivredna proizvodnja je od velike važnosti za prehranu ljudi i životinja. Budući da su potrebe za hranom svakim danom sve veće, potrebno je moći uzgajati kvalitetnu biljnu hranu u što većim količinama, s minimalnim štetama. Sa svakim uzgojem dolazi i problematika biljnih bolesti i stresa uzrokovanog vanjskim i unutrašnjim čimbenicima. Takve probleme nije više moguće nadgledati samo ljudskim okom, pogotovo na većim parcelama, pa su se kao rješenje postavile hiperspektralne tehnike, koje automatski analiziraju usjeve preko slika i tako uvelike skraćuju vrijeme i rad inače potreban za otkrivanje prvih simptoma bolesti i stresa.
Abstract (english)
Hyperspectral imaging and image analysis enable detection of early stages in development of plant dieseases and stress, as well as classification of healthy and diseased plants. The goal of these techniques is to evaluate level of health of plants, and to predict the possibility of development of plant diseases and stress, mostly using artificial intelligence, providing these techniques are faster, better and cheaper than human labour. This paper explores the themes of detecting plant pathogens and stress. Agricultural production is important in forms of food and feed. As the need for food increases daily, it is necessary to be able to grow quality plant food in as large quantities as possible, with minimal defects. With each cultivating process, comes the problem of plant diseases and stress caused by external and internal factors. Such problems can no longer be monitored by the human eye, especially on larger fields, so hyperspectral techniques have been set up as a solution. Their purpose is to automatically analyse the crops through imaging, and therefore shorten the time and work, otherwise required to detect the first symptoms of plant diseases and stress.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:162:074515
Study programmeTitle: Applied Ecology in Agronomy
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni prvostupnik/prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka primijenjene ekologije u poljoprivredi (sveučilišni prvostupnik/prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka primijenjene ekologije u poljoprivredi)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-11-06 12:33:23