elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

CLASSIFICATION OF TREE SPECIES ON THE BASIS OF TREE BARK TEXTURE

Ganschow, Lene and Thiele, Tom and Deckers, Niklas and Reulke, Ralf (2019) CLASSIFICATION OF TREE SPECIES ON THE BASIS OF TREE BARK TEXTURE. In: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, XLII-2 (W13). ISPRS Geospatial Week 2019, 10.-14. Jun. 2019, Enschede, Niederlande. DOI: 10.5194/isprs-archives-XLII-2-W13-1855-2019 ISSN 0256-1840

[img] PDF
1MB

Abstract

Forest inventory is an important topic in forestry and a digital solution which works on the basis of tree images is looked for. Implementing a system which automatically classifies tree species is the overall goal. In this paper the implementation of a convolutional neural net for solving this classification problem is executed and evaluated. The objective is creating a System which works well on unseen data and deriving guidelines and constraints to guarantee good accuracy results. Images including tree segmentation and the corresponding labels are provided as training data. The tree species classification takes the segmentation results of a stereo vision based image segmentation algorithm as input. The basic idea consists of cropping the tree images into quadratic boxes before feeding them into the neural net. First, each box is classified separately and then the results are evaluated to get a classification for the whole tree. Methods for result improvement include altering box size, using overlapping boxes, artificially enlarging the training set, pretraining and finetuning. Cropping a tree image into boxes of a specific size and accumulating the single results to get a classification of the whole tree leads to an accuracy of 96.7% provided that specific constraints like minimum box number and the projected size of the tree on image plane are considered. Finally, ways to further improve performance are pointed out.

Item URL in elib:https://elib.dlr.de/126409/
Document Type:Conference or Workshop Item (Speech)
Title:CLASSIFICATION OF TREE SPECIES ON THE BASIS OF TREE BARK TEXTURE
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Ganschow, LeneVINS 3D GmbHUNSPECIFIED
Thiele, TomVINS 3D GmbHUNSPECIFIED
Deckers, NiklasHU BerlinUNSPECIFIED
Reulke, RalfInstitut für Optische SensorsystemeUNSPECIFIED
Date:June 2019
Journal or Publication Title:International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
Volume:XLII-2
DOI :10.5194/isprs-archives-XLII-2-W13-1855-2019
ISSN:0256-1840
Status:Published
Keywords:Convolutional Neural Network, Image Segmentation, Forest Inventory, Pretraining and Finetuning, Integrated Positioning System, Plant Classification
Event Title:ISPRS Geospatial Week 2019
Event Location:Enschede, Niederlande
Event Type:international Conference
Event Dates:10.-14. Jun. 2019
Organizer:ISPRS
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben Optische Technologien und Anwendungen
Location: Berlin-Adlershof
Institutes and Institutions:Institute of Optical Sensor Systems
Deposited By: Dombrowski, Ute
Deposited On:09 Jul 2019 07:07
Last Modified:11 Oct 2019 09:06

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.