[Detecting land use change using PCA-enhancement and multi-source classifier from SPOT images]

Area of Science:

• Remote Sensing
• Geospatial Analysis
• Urban Studies

Context:

• Rapid global urbanization necessitates accurate land use change detection.
• Urban expansion monitoring is crucial for sustainable development and resource management.
• Existing methods for land use change detection require refinement for urban environments.

Purpose:

• To develop and validate a novel methodology for precise land use change detection in urban areas.
• To integrate Principal Component Analysis (PCA) enhancement with a multi-source classifier for improved accuracy.
• To compare the performance of the proposed method against traditional post-classification comparison techniques.

Summary:

• Rigorous orthorectification of SPOT-5 data ensured precise geometric correction and image registration.
• A methodology combining PCA-enhancement and a multi-source classifier (ISODATA and Maximum Likelihood) was employed.
• The first three PCs from multi-temporal PCA highlighted spectral information, with PC3 enhancing changed land use.

Impact:

• The proposed method achieved an overall accuracy of 92.58% and a KAPPA coefficient of 0.92.
• Demonstrated superior accuracy compared to traditional post-classification comparison approaches.
• Provides a robust and accurate tool for urban land use change monitoring and planning.