Rs

1. Shape matching techniques for building change and
its detection using remote sensing
Objective
Buildings change detection has the ability to quantify the temporal effect, on urban area, for
urban evolution study or damage assessment in disaster cases. Since the object’s shape can be
extracted from remote sensing imagery and the shapes of corresponding objects in multi-scale
images are similar, it is practical for detecting buildings changes in multi-scale imagery using
shape analysis. Buildings change detection has many applications in updating geographic
information system database, urban evolution estimation and damage assessment in disaster
cases. It aims to present automatic analysis of satellite images for urban evolution or risk
management where decision-making processes require to have at its disposal reliable and fast
support tool that allows a precise monitoring of urban areas.
Methodology
BUILDINGS CHANGE DETECTION BASED ON SHAPE MATCHING FOR MULTIRESOLUTION
REMOTE SENSING IMAGERY.
This method is divided into the four following steps:
1. Image enhancement and edge detection.
2. Preliminary boundary detection of the buildings
3. Extraction of complete boundaries of buildings
4. Change detection using feature matching
After applying radiometric corrections and geometric rectifications using UTM projection to
align the images with a suitable average error (RMS) value. In order to extract buildings shape
using the classification hierarchy diagram below:

2. Description of data used
Extraction of linear man-made objects (especially buildings) in urban areas and the
determination of changes in these objects using high resolution satellite datasets.
Sentinel-2a and 2b have crisper spatial resolution (10 meters in the visible and near-infrared).
IKONOS Satellite Sensor (0.82m) - Decommissioned
SPOT-6 Satellite Sensor (1.5m)
Study Area
I am planning to do my project on Bengaluru or Mumbai city. But it depends on high resolution
data availability.