Home About Browse Search

Segmentation and classification of individual tree crowns

in high spatial resolution aerial images

Erikson, Mats (2004). Segmentation and classification of individual tree crowns. Diss. (sammanfattning/summary) Uppsala : Sveriges lantbruksuniv., Acta Universitatis Agriculturae Sueciae. Silvestria, 1401-6230 ; 320
ISBN 91-576-6704-7
[Doctoral thesis]

[img] PDF


By segmentation and classification of individual tree crowns in high spatial resolution aerial images, information about the forest can be automatically extracted. Segmentation is about finding the individual tree crowns and giving each of them a unique label. Classification, on the other hand, is about recognising the species of the tree. The information of each individual tree in the forest increases the knowledge about the forest which can be useful for managements, biodiversity assessment, etc. Different algorithms for segmenting individual tree crowns are presented and also compared to each other in order to find their strengths and weaknesses. All segmentation algorithms developed in this thesis focus on preserving the shape of the tree crown. Regions, representing the segmented tree crowns, grow according to certain rules from seed points. One method starts from many regions for each tree crown and searches for the region that fits the tree crown best. The other methods start from a set of seed points, representing the locations of the tree crowns, to create the regions. The segmentation result varies from 73 to 95 % correctly segmented visual tree crowns depending on the type of forest and the method. The former value is for a naturally generated mixed forest and the latter for a non-mixed forest. The classification method presented uses shape information of the segments and colour information of the corresponding tree crown in order to decide the species. The classification method classifies 77 % of the visual trees correctly in a naturally generated mixed forest, but on a forest stand level the classification is over 90 %.

Authors/Creators:Erikson, Mats
Title:Segmentation and classification of individual tree crowns
Subtitle:in high spatial resolution aerial images
Series Name/Journal:Acta Universitatis Agriculturae Sueciae. Silvestria
Year of publishing :November 2004
Number of Pages:45
ALLI. Erikson, M., Segmentation of individual tree crowns in colour aerial photographs using region growing supported by fuzzy rules, Canadian Journal of Forest Research, Vol. 33, No. 8, 2003, pp. 1557-1563. Reprinted with permission from NRC Research Press. II. Erikson, M., Structure-preserving segmentation of individual tree crowns by brownian motion, in Proc. of the 13th Scandinavian Conference on Image Analysis (eds. J. Bigun, T. Gustavsson), 29 June - 2 July, 2003, Gothenburg, Sweden, Lecture Notes in Computer Science 2749, Springer-Verlag, Berlin, Germany, 2003, pp. 283-289. Reprinted with permission from Springer-Verlag. III. Erikson, M., Two preprocessing techniques based on grey level and geometric thickness to improve segmentation results, submitted for journal publication. IV. Erikson, M., Olofsson, K., Comparison of three individual tree crown detection methods, submitted for journal publication. V. Erikson, M., Species classification of individually segmented tree crowns in high-resolution aerial images using radiometric and morphologic image measures, Remote Sensing of Environment, Vol. 91, No. 3-4, 2004, pp. 469-477. Reprinted with permission from Elsevier.
Place of Publication:Uppsala
ISBN for printed version:91-576-6704-7
Publication Type:Doctoral thesis
Full Text Status:Public
Agris subject categories.:U Auxiliary disciplines > U40 Surveying methods
Subjects:Not in use, please see Agris categories
Agrovoc terms:aerial surveying, image analysis, crown, trees, remote sensing, species, classification
Keywords:aerial photography, high spatial resolution, image analysis, individual tree crown, remote sensing, segmentation, species classification
Permanent URL:
ID Code:676
Department:(S) > Centrum för bildanalys (900701-031231?)
Deposited By: Mats Erikson
Deposited On:02 Nov 2004 00:00
Metadata Last Modified:02 Dec 2014 10:06

Repository Staff Only: item control page


Downloads per year (since September 2012)

View more statistics