Izvorni znanstveni članak

NEW INFORMATION TECHNOLOGY OF PERFORMANCE EVALUATION OF ROAD EXTRACTION FROM HIGH RESOLUTION SATELLITE IMAGES BASED ON PCNN AND C-V MODEL

Ganesh Kumar ; Sveučilište Manonmaniam Sundaranar, Tirunelveli, Indija; Institut za tehnologiju Unnamalai, Kovilpatti, Indija
D. Murugan ; Sveučilište Manonmaniam Sundaranar, Tirunelveli, Indija; Institut za tehnologiju Unnamalai, Kovilpatti, Indija
R. Kavitha ; Sveučilište Manonmaniam Sundaranar, Tirunelveli, Indija; Institut za tehnologiju Unnamalai, Kovilpatti, Indija
T.I. Manish ; Sveučilište Manonmaniam Sundaranar, Tirunelveli, Indija; Institut za tehnologiju Unnamalai, Kovilpatti, Indija

Sažetak

Road extraction from high resolution satellite images has been an important research topic for analysis of urban areas. In this paper road extraction based on PCNN and Chan-Vese active contour model are compared. It is difficult and computationally expensive to extract roads from the original image due to presences of other road-like features with straight edges. The image is pre-processed using median filter to reduce the noise. Then road extraction is performed using PCNN and Chan-Vese active contour model. Nonlinear segments are removed using morphological operations. Finally the accuracy for the road extracted images is evaluated based on quality measures.

Ključne riječi

Image Segmentation; Road Extraction; Morphological operations

Hrčak ID:

125805

URI

https://hrcak.srce.hr/125805

Datum izdavanja:

8.8.2014.

Podaci na drugim jezicima: hrvatski

Posjeta: 1.363 *