Extraction of Urban Tree Canopy using Multiresolution Segmentation of Very High Resolution Satellite Imagery

Sujata R. Kadu,Balaji G. Hogade,Imdad Rizvi

Tree canopy detection has an indispensable role to play in the planning of an urban area, while addressing the ecological processes and issues, more so in case of developing countries. Traditional classification methods are pixel based that do not utilize spatial information around an object. In Object- Based Image Analysis (OBIA), pixels are first grouped into objects based on Spectral or external aspects like geological unit or soil. OBIA increases the accuracy of classification Significantly in Very High Resolution (VHR) satellite images. The aim of this research is to illustrate how object-based method can be applied to the available data to accurately find out vegetation, which can be further sub-classified to obtain area under tree canopy. The result thus obtained gives area under tree canopy with an accuracy of 88.82 % and a Kappa coefficient of 0.72. Results obtained through OBIA are also compared with existing Gaussian Mixture Model (GMM) method.

Volume 11 | 08-Special Issue

Pages: 98-107