| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:NAPOVED PRIDELKA JABOLK V ŠVICI S POMOČJO OBDELAVE DIGITALNE FOTOGRAFIJE
Authors:ID Dorič, Martin (Author)
ID STAJNKO, DOC. DR. DENIS (Mentor) More about this mentor... New window
Files:.pdf UNI_Doric_Martin_2009.pdf (4,87 MB)
MD5: CBA20024271647B2274C922B75F1E543
PID: 20.500.12556/dkum/be58d77e-e403-4b5c-8f76-5754d1f50925
 
Language:Slovenian
Work type:Undergraduate thesis
Organization:FKBV - Faculty of Agriculture and Life Sciences
Abstract:Poskus napovedovanja pridelka jabolk s pomočjo obdelave digitalne fotografije je potekal med leti 2005 in 2008 v sklopu napovedi pridelka jabolk v treh kantonih Švice (Thurgau, Wallis in Waadt). V poskus so bile vključene sorte Gala, Braeburn, Jonagold, Maigold, Idared in Zlati delišes. Namen poskusa je bil proučiti natančnost napovedi pridelka jabolk s pomočjo obdelave digitalne fotografije. Hkrati pa s statističnim vrednotenjem ugotoviti morebitne vplive regije in sorte na natančnost napovedi pridelka jabolk in možnosti izboljšanja napovedi v prihodnje. Vsako leto smo v juliju najprej fotografirali vzorčna drevesa, nato pa s pomočjo računalniške obdelave napovedali pričakovani pridelek. Statistična analiza je pokazala vpliv regije na natančnost napovedi pridelka jabolk (Thurgau Io = 0,9 do 1,17; Wallis Io = 0,98 do 1,37; Waadt Io = 0,92 do 1,06). Najboljšo napoved smo dosegli pri sorti Gala (Io = 0,99), najslabšo pa pri sorti Braeburn (Io = 1,19) Standardni odklon razlike N-T je pokazal, da se pri nekaterih sortah pojavljajo občutne razlike med napovedanim in dejanskim pridelkom ob obiranju (najmanjši pri sorti Jonagold σr = 3.798 kg/ha, največji pri sorti Gala σr = 18.718 kg/ha). Ugotavljamo da metoda omogoča precej uspešno napovedovanje, vendar obstaja še precej nepojasnjenih faktorjev.
Keywords:Ključne besede: jabolka / število plodov / vizualizacija / obdelava fotografije / napoved pridelka
Place of publishing:Maribor
Year of publishing:2009
PID:20.500.12556/DKUM-9852 New window
NUK URN:URN:SI:UM:DK:IGVWWEPS
Publication date in DKUM:02.03.2009
Views:3389
Downloads:162
Metadata:XML DC-XML DC-RDF
Categories:FKBV
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:APPLE YIELD FORECAST WITH PROCESSING OF DIGITAL PHOTOGRAPHY IN SWITZERLAND
Abstract:Experiment of apple yield forecast with processing of digital photography took place from year 2005 to 2008 in three cantons of Switzerland (Thurgau, Wallis and Waadt). Gala, Braeburn, Jonagold, Maigold, Idared and Golden Delicious were included in the experiment. The main purpose was to examine accuracy of apple yield forecast in different cantons. At the same time we conducted a statistic evaluation of region and variety influencing apple yield forcast accuracy, leading to improvements of the method in the future. Trees were photographed each year in July and data were processed for yield prediction. Results from statistic analysis point out the influence of region on apple yield forecast accuracy (Thurgau Io = 0,9 do 1,17; Wallis Io = 0,98 do 1,37; Waadt Io = 0,92 do 1,06). The best results were achived by Gala (Io = 0,99), the worst by Braeburn (Io = 1,19). Standard deviation of distinction N-T shows the lowest value by Jonagold σr = 3.798 kg/ha and the highest by Gala σr = 18.718 kg/ha. The method looks promising, but there are still many more unknown factors.
Keywords:Key words: apple / fruit number / vizualization / picture processing / yield forcast


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica