Click for new scientific resources and news about Corona[COVID-19]

Paper Information

Journal:   MODARRES HUMAN SCIENCES   SUMMER 2006 , Volume 10 , Number 2 (TOME 45); Page(s) 123 To 138.
 
Paper: 

USING EDGE DENSITY INFORMATION IN CLASSIFICATION OF RURAL-URBAN REGION BY REMOTELY-SENSED DATA

 
 
Author(s):  SAMADI Z., ALI MOHAMMADI A.*
 
* DEPARTMENT OF GIS, FACULTY OF GEOMANTIC ENGINEERING, KHAGE NASIR UNIVERSITY, TEHRAN, IRAN
 
Abstract: 

Operation manner in most of the conventional classification algorithms in remote sensing is based on pixels spectral information. Classification of these data ignores information obtained from adjacent pixels. In addition, the increase of spatial resolution in satellites, increases harmful information (noise) and spectral similarity between classes, and consequently increases internal variance of classes and finally decreases classification accuracy. To remove or decrease these problems, the proper incorporation and use of spectral and contextual information can efficiently help distinguish land-uses which are similar spectrally.
In this study, effectiveness of incorporating structural information with classification procedures has been investigated. The technique is based on the use of edge-density information generated from the classified data.
"Maximum Likelihood" (ML), "Minimum Distance to Means" (MD) and "Mahalanobis" classification procedures have been used to classify data together with the edge-density information as an additional band.
The performance of using edge-density data has been evaluated using the data of SPOT-XS and aerial photographs of the Anzali Wetlands (Anzali Talab) located in Gilan province north of Iran. This region is very heterogeneous. Results show that use of the structural information leads to the increase in accuracy of some classes particularly those with low spectral separabilities. Mahalanobis classifier using spatial and spectral information in rural-urban (74/60) and river and channel (66/87) classes show 14/06 and 6/57 percent increase respectively in accuracy as compared to the spectral classification of satellite data. Application of this approach also in aerial photographs for patches of trees, river, agricultural and residential classes show 11/78, 36/61, 28/09 and 53/29 percent increase in accuracy respectively.
Results show that considering the complex environmental conditions of the study site, the proper incorporation and use of spectral and spatial information can result in more efficient discrimination of some spectrally similar classes. The information of edge-density seems to be more promising in high resolution imagery and heterogeneous classes such as urban features.

 
Keyword(s): EDGE-DENSITY INFORMATION, SPECTRAL RESOLUTION, SPOT, CLASSIFICATION OF RURAL-URBAN REGION, SATELLITE IMAGES
 
References: 
  • ندارد
 
  Persian Abstract Yearly Visit 58
 
Latest on Blog
Enter SID Blog