Assessment of urban growth dynamics in Mumbai Metropolitan Region, India using object-based image analysis for medium-resolution data

- Spatiotemporal land cover changes mapped by classification of EO images provide database to project urban growth trends.
- Reliable methodology to derive consistent multi-temporal land use classification hence assumes critical importance.
- This paper describes the application of Object-Based Image Analysis for classification of medium-resolution images.
- Classification as image objects obliterates the 'salt and pepper effects' for heterogeneous land uses.
- Inconsistent classification is identified as false land use class transitions in change matrix, and resolved using GIS.
- Higher increase in built-up area with respect to population causes population density to decline and urban form to fragment.
- Furthermore, the ecologically sensitive zones are split by the ribbon development along transportation corridors.
- The study demonstrates utility of Landsat archives to map land use transitions and identify urban growth trends.