An Efficient Multi-stage Object-Based Classification to Extract Urban Building Footprints from HR Satellite Images

Abstract

Urban building information can be effectively extracted by applying object-based image segmentation and multi-stage thresholding on High Resolution (HR) remote sensing satellite imageries. This study provides the results obtained using this method on the images of Indian remote sensing satellite, CARTOSAT-2S launched by the Indian Space Research Organization (ISRO). In this study, a method is developed to extract urban building footprints from the HR remote sensing satellite images. The first step of the process consists of generating highly dense per pixel Digital Surface Model (DSM) by using semi global matching algorithm on HR satellite stereo images and applying robust ground filtering to generate Digital Terrain Model (DTM). In the second step, multi-stage object-based approach is adopted to extract building bases using the PAN sharpened image, normalized Digital Surface Model (nDSM) derived from DSM and DTM, and Normalised Difference Vegetation Index (NDVI). The results are compared with the manual method of drawing building footprints by cartographers. An average precision of 0.930, recall of 0.917, and f-score of 0.922 are obtained. The results are found to be in a match with the method using the high resolution Airborne LiDAR DSM by providing a solution for large areas, low cost and low time.

Review of Advanced Image Processing Techniques: Digital Elevation Model

“…In 2021, there are two more techniques used with Neural Networks namely, Generative Adversarial Networks (GANs) (21) and Triangulated Irregular Network (TIN) (9,19,22). Each of which help in the terrain generation of the created Digital Surface Models or the Remotely Sensed Images.…”

“…Each of which help in the terrain generation of the created Digital Surface Models or the Remotely Sensed Images. GANs were used for the height map construction and 3D Model construction (21). Whereas, TIN was used to create the classification of points on the surface (9,19,22).…”

Visualization of a Digital Elevation Model using Advanced Image Processing

“…The built (power lines, buildings, and towers) and natural (trees and other types of vegetation) aren't included in a DEM. 2) Digital Surface Model (DSM): In a LiDAR system (5,11,12,15,18), pulses of light travel to the ground. When the pulse of light bounces off its target and returns to the sensor, it gives the range (a variable distance) to the Earth.…”

“…Comparison of flood extents, hydrographs, depths, and impacts between hydrodynamic simulations, using five spaceborne GDEM products and an airborne LIDAR (5,11,12,15,18) product. Variability in the accuracy of models using different GDEMs.…”

“…The OS software is SAGA-GIS that can be used for any point cloud data.Final product is a high resolution DTM which has 30cm x 30cm grid spacing . [18] Urban building information can be effectively extracted by applying object-based image segmentation and multi-stage thresholding on High Resolution remote sensing satellite images. This study provides the results obtained using this method on the images of Indian remote sensing satellite, CARTOSAT-2S launched by the Indian Space Research Organization.…”