Authors : Dr. Kavita Mehra, Amit Desai
ABSTRACT : Change detection in multi-temporal remote sensing data is a fundamental technique for monitoring environmental changes, urban expansion, deforestation, agricultural dynamics, and disaster impacts over time. The availability of high-resolution satellite imagery, combined with advanced computational methods, has revolutionized the field, enabling precise and rapid detection of changes in land cover and land use. Various algorithms—ranging from traditional pixel-based techniques to modern object-based and machine learning approaches—offer different capabilities in terms of accuracy, processing speed, and applicability. This paper provides a detailed overview of advanced change detection algorithms, including image differencing, vegetation index differencing, principal component analysis (PCA), change vector analysis (CVA), and deep learning-based classification. The discussion emphasizes their mathematical foundations, implementation strategies, and case studies across diverse geographical regions. The paper also addresses common challenges such as atmospheric interference, sensor calibration discrepancies, and seasonal variability, while highlighting emerging trends like cloud-based processing and AI-driven automation. By evaluating algorithmic strengths and limitations, this study aims to guide researchers, urban planners, and environmental managers toward selecting optimal methods for their specific change detection needs.
Full Issue
| View or download the full issue | PDF 40-45 |