Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Comparison of Single Channel Indices for U-Net Based Segmentation of Vegetation in Satellite Images
Date
2020-01-01
Author
Ulku, Irem
Barmpoutis, Panagiotis
Stathaki, Tania
Akagündüz, Erdem
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
106
views
0
downloads
Cite This
Hyper-spectral satellite imagery, consisting of multiple visible or infrared bands, is extremely dense and weighty for deep operations. Regarding problems related to vegetation as, more specifically, tree segmentation, it is difficult to train deep architectures due to lack of large-scale satellite imagery. In this paper, we compare the success of different single channel indices, which are constructed from multiple bands, for the purpose of tree segmentation in a deep convolutional neural network ( CNN) architecture. The utilized indices are either hand-crafted such as excess green index (ExG) and normalized difference vegetation index (NDVI) or reconstructed from the visible bands using feature space transformation methods such as principle component analysis (PCA). For comparison, these features are fed to an identical CNN architecture, which is a standard U-Net-based symmetric encoder-decoder design with hierarchical skip connections and the segmentation success for each single index is recorded. Experimental results show that single bands, which are constructed from the vegetation indices and space transformations, can achieve similar segmentation performances as compared to that of the original multi-channel case.
URI
https://hdl.handle.net/11511/93891
DOI
https://doi.org/10.1117/12.2556374
Conference Name
12th International Conference on Machine Vision (ICMV)
Collections
Graduate School of Informatics, Conference / Seminar
Suggestions
OpenMETU
Core
Comparison of Outer Rotor Radial Flux and Axial Flux PM Motors for CMG Application
Ertan, Hulusi Bülent (2014-09-05)
Control moment gyroscopes (CMG) are used in modern satellite applications for attitude control of satellites. The volume and mass of the instruments is very important in such applications. In this context, integrating the mass of the CMG, on the stator of the motor, promises to save space and mass. Radial-flux outer-rotor motor is a promising configuration in that respect. In this paper, using such a PM motor is considered for control moment gyroscope applications. The design of the motor must be made such ...
Optimization of vibration characteristics of a radar antenna structure
Baran, İsmet; Özgen, Gökhan Osman; Ciğeroğlu, Ender; Department of Mechanical Engineering (2011)
Radar antenna structures especially array antennas which are integrated onto structures of aerial vehicles are subject to dynamic structural and aerodynamic loads. Due to occurrences of these dynamic loads there will be certain dynamic deformations which affect the antenna’s performance in an adverse manner. The influence of deformations and vibrations are important on array antenna structures, since they cause a change in orientation of elements of the phased array antenna which affects the gain of the ant...
Investigation of Estimation Methods for Time-varying Residual Magnetic Moment
Söken, Halil Ersin (2015-01-01)
Generally, the dominant attitude disturbance source for the low Earth orbit small satellites is the residual magnetic moment (RMM). The RMM should be estimated and compensated in orbit to increase the attitude estimation and control accuracy. Although the estimator is usually built with the assumption that these parameters are constant, the RMM changes with sudden shifts caused by the variations in the onboard electrical current. The estimator should quickly track these unobserved parameters in case of chan...
Forecasting of ionospheric electron density trough for characterization of aerospace medium
Kocabaş, Zeynep; Tulunay, Yurdanur; Department of Aerospace Engineering (2009)
Modeling the ionosphere, where the effects of solar dynamo becomes more effective to space based and ground borne activities, has an undeniable importance for telecommunication and navigation purposes. Mid-latitude electron density trough is an interesting phenomenon in characterizing the behavior of the ionosphere, especially during disturbed conditions. Modeling the mid-latitude electron density trough is a very popular research subject which has been studied by several researchers until now. In this work...
Comparison of the intercarrier interference cancellation methods in OFDM systems
Etiler, Burkay; Tuncer, Temel Engin; Department of Electrical and Electronics Engineering (2007)
In OFDM systems carrier frequency offset is observed due to Doppler shift and transmitter-receiver frequency mismatches. This offset induces ICI (Intercarrier Interference). In this thesis, repeated data methods and pilot-aided carrier frequency offset(CFO) estimation methods and windowing techniques are used to mitigate the frequency offset problem and a performance comparison is made between these ICI cancellation techniques. Repeated data methods use only half of the bandwidth for information transmissio...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
I. Ulku, P. Barmpoutis, T. Stathaki, and E. Akagündüz, “Comparison of Single Channel Indices for U-Net Based Segmentation of Vegetation in Satellite Images,” Amsterdam, Hollanda, 2020, vol. 11433, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/93891.