| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font
First page > Show document

Show document Help

Title:Spremljanje vegetativne rasti jablan s pomočjo analize slike
Authors:ID Korošec, Matic (Author)
ID Stajnko, Denis (Mentor) More about this mentor... New window
Files:.pdf UNI_Korosec_Matic_2010.pdf (1,97 MB)
MD5: 2B9BE08C51A75C9EA67D34882BEC8B6E
PID: 20.500.12556/dkum/35e0356d-b351-4e49-a077-af228b5391e5
 
Language:Slovenian
Work type:Undergraduate thesis
Organization:FKBV - Faculty of Agriculture and Life Sciences
Abstract:V okviru diplomskega dela smo leta 2008 izvajali poskus — spremljanje vegetativne rasti jablan z analizo slike. Poskus je potekal na posestvu Benediktinskega dvora, d. o. o., v sadovnjaku v Limbušu. V poskus so bile vključene triletne jablane sort ´Fuji´ in ´Mairac´. Med vegetacijo smo trikrat fotografirali jablane in jim z računalniško analizo fotografije določili listno površino. Ugotavljali smo vpliv obremenitve dreves in terminov fotografiranja na listno površino. Pri sorti ´Mairac´ se je listna površina pri visoko obremenjenih drevesih (3,13 m2) statistično razlikovala od listnih površin pri srednje (3,23 m2) in nizko (3,26 m2) obremenjenih drevesih. Listna površina se je statistično razlikovala pri vseh terminih fotografiranja. 5. junija 2008 je znašala 3,24 m2, 27. junija 2008 3,29 m2 in 28. julija 2008 3,09 m2. Pri sorti ´Fuji´ se je listna površina pri visoko obremenjenih drevesih (3,17 m2) statistično razlikovala od listnih površin pri srednje (3,26 m2) in nizko (3,26 m2) obremenjenih drevesih. Listna površina pri drevesih fotografiranih 27. junija 2008 (3,11 m2) se statistično razlikuje od listnih površin fotografiranih 5. junija 2008 (3,29 m2) in 28. julija 2008 (3,29 m2). Ugotovili smo, da je z metodo računalniške analize slike mogoče določiti listno površino proučevanih dreves, vendar je za vsako naslednjo sorto in velikost dreves potrebno izdelati lasten algoritem.
Keywords:jabolka, vegetativna rast, pridelek, list, listna površina, obremenitev drevesa, digitalna fotografija
Place of publishing:Maribor
Year of publishing:2010
PID:20.500.12556/DKUM-15717 New window
NUK URN:URN:SI:UM:DK:ARNDC5P7
Publication date in DKUM:13.10.2010
Views:3080
Downloads:163
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:Vegetative apple tree growth observation by image analysing
Abstract:In the diploma work we made an experiment in observing vegetative apple tree growth in 2008 by using image analyses. The experiment was made on the Benediktinski dvor d.o.o. property in the orchard close to Limbuš. Three years old apple trees of ´Fuji´ and ´Mairac´ varieties were included in the experiment. We captured several series apple images during the vegetation from June to September. Later, we determined the leaf surface with image analysis algorithm in the laboratory. We investigated the effect of tree burdening and the time of capturing images on the leaf surface determined by the algorithm. In the variety ´Mairac´ statistical significant difference was found in the leaf surface between high (3,13 m2) and medium tree burdening (3,23 m2) and also low tree burdening (3,26 m2). The time of capturing images affected the measured leaf surface statistically significant for all three series of images. On June 5 2008 the leaf surface was 3,24 m2, on June 27 2008 3,29 m2 and on July 28 3,09 m2. In the variety ´Fuji´ statistical significant difference was found in the leaf surface between high tree burdening (3,17 m2) and medium tree burdening (3,26 m2) as well low tree burdening (3,26 m2). Regarding to the time of capturing images, the leaf surface shoved statistical significant difference for series of images captured on June 27 (3,11 m2) and June 5 (3,29 m2) as well July 28 (3,29 m2). We can conclude that this method is suitable for the leaf surface determination of specific trees, however for every additional variety and size of trees a separate algorithm is required.
Keywords:apples, vegetative growth, crop, leaf, leaf surface, tree burdening, digital image


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