Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

supervisd-hyperspectral-image-classification

null
by

nada ibrahim

on 15 February 2015

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of supervisd-hyperspectral-image-classification

NAME OF GROUP MEMBERS
SUPERVISED HYPERSPECTRAL IMAGE CLASSIFICATION
Wateen Abdullah Al-iady
Nada Ibrahim Al-rashed
Ghadah Ahmad Al-jarallah




OUT LINES
Introduction of hyperspectral imaging
INTRODUCTION
Implementation:
Preprocessing.
Processing:
Spectral Angel Mapper Classification(SAM).
Parallelepiped Classification.
Testing:
Conclusion

Introduction:
Problem Statement & Significance.
Proposed Solution.
Project Domain.
Requirement Determination and Analysis:
Requirement Determination & Collection.
Requirements Analysis
Problem Statement & Significant
The problem is need to classify, maintain, and manage the agricultural fields which are very huge, distributed everywhere and may miss certain areas when field searching. Also, time and effort needed to do this will be consumed.

Several techniques have been proposed in recent years for the supervised classification of hyperspectral data, such as: Spectral angel mapper and Parallelepiped classification that will be used as a proposed solution to hyperspectral image classification.

Proposed Solution
Requirement Determination
and Analysis
Our study area is Al-Kharj in Saudi Arabia.






The detected area for our study will be downloaded from the for United States Geological Survey website, which is: http://earthexplorer.usgs.gov/.
1. Requirement Determination
& Collection

The name of the image is: EO1H1650432007080110PY_PF1_01 which has the following information:
Location: in Path 165, and Row 43.
Acquisition date: Year 2007.Since Julian day is 80 so it was acquisitioned on 23/3 so we can tell that Al-Kharj was scanned in spring season.

2. Requirements Analysis


A. Hyperion Tool
B. Sub setting:
Spatial subset.
Spectral subset.
C. Atmospheric Correction.

1. Preprocessing
Atmospheric Correction
The spectral profile for a certain pixel in our image before and after the atmospheric correction.

2. Processing
Supervised algorithms:
Spectral Angle Mapper (SAM) algorithm.
Parallelepiped algorithm.

Implementation
Implementation
2. Processing
2- Parallelepiped Classifier

Result of Parallelepiped
classification
Testing
Conclusion
SUPERVISED BY:
Dr. Sahar Abdulrahmain Ismail
Project Domain
The project domain in the computer science field is an image processing.
There are different hyperspectral imaging applications such as:
THANKS FOR YOUR ATTENTION
Before
After
Implementation Flowchart
Our project has achieved the potential use of SAM, and Parallelepiped classifiers combined with the EO-1 Hyperion imagery analysis for deriving total wheat areas in our study region
the area of Al-Kharj in Saudi Arabia.

Conclusion
Future work
Saudi Arabia began its interest in the field of remote Sensing in King Abdul Aziz City for Science and Technology, where now it provides the necessary equipment to produce researches on hyperspectral imaging.
So, we might join King Abdul Aziz City to expand our work on several areas in Saudi Arabia.

1. Spectral Angel Mapper Classifier (SAM):
The SAM is a tool that permits rapid mapping of the spectral similarity of image spectra to reference spectra.



2. Processing
Result of SAM classification
Name of University:
Princess Noura bint Abdulrahman University
Reference
1. B. Salter, "kharj," Al Kharj: The Agri capetal saudi, vol. 15, no. 12, p. 2, 2006.
2. D. White, "Hyperion Tools User Guide," Hyperion Tools 2.0 Installation and User Guide, vol. 30, no. 13, p. 8, 2013.

3. ENVI, “ENVI User's Guide,” Research Systems, Inc.All Rights Reserved, Australia, 2007.

4. G. P. Petropoulos, K. P. Vadrevu, G. Xanthopoulos, G. Karantounias and M. Scholze, "A Comparison of Spectral Angle Mapper and Artificial Neural Network classifier," Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area Mapping, no. 1424-8220, p. 19, 2010.

5. H. Z. Shafri, A. Suhaili and S. Mansor, "The Performance of classification," The Performance of Maximum Likelihood, Spectral Angle Mapper, Neural Network and Decision Tree Classifiers in Hyperspectral Image Analysis, no. 15, p. 5, 2007.

6. U. Cluster, "SUBSET," Implementation of the SVDSS in the ENVI/IDL Environment, vol. 15, no. 12, p. 4, 2002.
Full transcript