Improved Hyperspectral Vegetation Detection Using Neural Networks with Spectral Angle Mapper

Date

2017-04-13

Author

Özdemir, Okan Bilge
Çetin, Yasemin

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

126
views

0
downloads

Hyperspectral images have been used in many areas including city planning, mining and military decision support systems. Hyperspectral image analysis techniques have a great potential for vegetation detection and classification with their capability to identify the spectral differences across the electromagnetic spectrum due to their ability to provide information about the chemical compositions of materials. This study introduces a vegetation detection method employing Artificial Neural Network (ANN) over hyperspectral imaging. The algorithm employed backpropagation MLP algorithm for training neural networks. The performance of ANN is improved by the joint use with Spectral Angle Mapper (SAM). The algorithm first obtains the certainty measure from ANN, following the completion of this process, every pixels' angular distance is computed by SAM. The certainty measure is divided by angular distance. Results from ANN, SAM and Support Vector Machine (SVM) algorithms are compared and evaluated with the result of the algorithm. Limited number of training samples are used for training. The results demonstrate that joint use of ANN and SAM significantly improves classification accuracy for smaller training samples

Subject Keywords

Hyperspectral, Classification, SVM, Neural Networks, Spectral Angle Mapper

URI

https://hdl.handle.net/11511/51834

DOI

https://doi.org/10.1117/12.2262480

Collections

Graduate School of Informatics, Conference / Seminar

Suggestions

OpenMETU
Core

Automatic multi-scale-segmentation of high spatial resolution satellite images using watersheds Şahin, Kerem; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2013) Useful information extraction from satellite images for the use of other higher level applications such as road network extraction and update, city planning etc. is a very important and active research area. It is seen that pixel-based techniques becomes insufficient for this task with increasing spatial resolution of satellite imaging sensors day by day. Therefore, the use of object-based techniques becomes indispensable and the segmentation method selection is very crucial for object-based techniques. In ...
Development of a software suite for the structural analysis and design of concrete gravity dams Altuğ, Akman; Arıcı, Yalın; Binici, Barış; Kurç, Özgür (2015-06-13) In contrast to other infrastructure, there has been very limited cooperation between the industry and academia on developing the analytical tools for the design and evaluation of dams for seismic loading. This is mostly due to the complexity of the dam behavior as well as the size of these systems precluding the diffusion of academic information to the tools used by the practicing engineer due to time constraints. With the support of the Turkish National Sciences Foundation under the academia-industry coope...
Research on transfer alignment for increased speed and accuracy Kayasal, Uğur; Özgören, Mustafa Kemal; Department of Mechanical Engineering (2012) In this thesis, rapid transfer alignment algorithm for a helicopter launched guided munition is studied. Transfer alignment is the process of initialization of a guided munition’s inertial navigation system with the aid of the carrier platform’s navigation system, which is generally done by comparing the navigation data of missile and carrier’s navigation data. In the literature, there are different studies of transfer alignment, especially for aircraft launched munitions. One important problem in transfer ...
SCOUR AT REAR SIDE OF A COASTAL REVETMENT DUE TO SOLITARY-LIKE WAVE OVERTOPPING Yaman, Mert; Yalçıner, Ahmet Cevdet; Baykal, Cüneyt; Department of Civil Engineering (2022-5-11) Rubble mount coastal structures are commonly used for protecting coastal utilities. Under storm conditions or extreme conditions, long waves attack those structures and cause overtopping. This overtopping phenomenon often results in water flow at the back side of the structure which consequently causes scour. In this thesis, different solitary-like waves and the backfill conditions are studied to understand the level of overtopping and maximum scour depth behind the structure due to the solitary-like wave c...
COMPARISON OF REAL AND SIMULATED RECORDS IN TERMS OF SEISMIC INPUT ENERGY FOR A BASE ISOLATED STRUCTURE Özsaraç, Volkan; Karimzadeh, Shaghayegh; Askan Gündoğan, Ayşegül; Erberik, Murat Altuğ (2021-10-01) Base isolation systems have been recently employed for structures as retrofitting strategies especially in seismologically active zones. For such base isolated systems, one challenging task is the investigation of seismic demand parameters under destructive earthquakes. Since the number of recorded ground motions corresponding to large intensities is limited, use of simulated records is an alternative option to overcome this issue. There are several ground motion simulation approaches with various levels of...

Citation Formats

O. B. Özdemir and Y. Çetin, “Improved Hyperspectral Vegetation Detection Using Neural Networks with Spectral Angle Mapper,” 2017, vol. 10190, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/51834.