A novel framework for extraction of landscape areas and automatic building detection in satellite images

Abstract

Identification and Classification of satellite image for the extraction of landscapes and automatic extraction of building remains a critical issues in digital photogrammetric. It plays a challenging role for the remote sensing application. Many approaches for extraction of building provides less satisfactory concert with high-resolution satellite images. In this proposal a novel framework for consistent and correct structure extraction of landscape from high-resolution panchromatic images were obtained. The proposed approach uses classification and automatic detection process for finding out accurate extraction of building and also to analyze the landscape areas using internal image gray variance (IGV). Detection process is carried out using Image shadow detection and False alarm reduction technique. The evaluation of classification and detection algorithm is demonstrated and the proposed algorithm provides the quality of services in accuracy and efficiency for remote sensing application.