2011 IEEE journal base paper of Applied Earth Observations And Remote Sensing. Download this IEEE base paper as free copy.
Base Paper Title :
A Multilevel Hierarchical Image segmentation Method for Urban Impervious Surface Mapping Using Very High Resolution Imagery
Paper Authors :
- Peijun Li, Senior Member, IEEE,
- Jiancong Guo,
- Benqin Song, and
- Xiaobai Xiao
IEEE Base Papers Abstract :
This document provides a ordered image segmentation method that brings together multichannel watershed transformation and characteristics of watershed shapes for the segmentation of very high Resolution (VHR) multispectral visuals. The picture gradient was first created from a multi-spectral picture using a multichannel morphological technique, followed by traditional watershed transformation to generate an preliminary segmentation outcome.
The resulting watershed shapes were then examined according to their relevance comparative to the minima of the nearby sinks to construct an picture containing details about their characteristics. By thresholding the picture of the shape characteristics at different stages, multilevel hierarchical segmentation outcomes with different stages of detail were obtained. The suggested technique was analyzed by comparing with current techniques through visible examination, quantitative measures and programs in downtown resistant area applying, using two places of VHR picture details.
The trial results showed that the suggested technique created more precise segmentation results in comparison to an current single-level segmentation method, with regards to visible and quantitative assessments. While used for downtown resistant area applying, the suggested method achieved an overall precision considerably greater than the pixel based category technique, and also greater than the item based classification using a single-level segmentation outcome. Compared with the most commonly used segmentation technique applied in the eCognition, the suggested technique obtained a similar efficiency, although they have different segmentation details. The proposed segmentation technique can be used in relevant VHR image processing and programs.
Hardware Requirements ;
- SYSTEM : Pentium IV 2.4 GHz
- HARD DISK : 40 GB
- MONITOR : 15 VGA colour
- MOUSE : Logitech.
- RAM : 256 MB
- KEYBOARD : 110 keys enhanced.
Software Requirements ;
- Operating system :- Windows XP
- Front End :- Microsoft Visual Studio .Net 2005.
- Coding Language : – C# 2005.