Transaction Management in Database Management System
Object based image analysis tools for opticks
1. OSGEO-India: FOSS4G 2012- First National Conference "Open Source Geospatial Resources
to Spearhead Development and Growth” 25-27th October 2012, @ IIIT Hyderabad
Object Based Image Analysis
Tools for Opticks
Mohit Kumar, KS Rajan, Dustan Adkins
http://osgeo.in/foss4g2012 1
2. OPTICKS ?
• Opticks is an open source, remote sensing application that supports imagery,
video (motion imagery), Synthetic Aperture Radar (SAR), multi-spectral, hyper-
spectral, and other types of remote sensing data.
• Opticks can also be used as a remote sensing software development framework.
Developers can extend Opticks functionality using its plug-in architecture and
public application programming interface
• http://opticks.org
Why object-based?
• Object based approach is better than conventional per-pixel analysis as it deals
with considerably reduced number of units. This approach is not that much
sensitive to noise and hence is spatially consistent.
http://osgeo.in/foss4g2012 2
4. Image Segmentation (Meanshift)
Input image
(CIELAB colour 5 Dimensional
Input image(RGB) feature space
space)
sing Modes(local
o lla p
space c ect. Clustering
ature ob j
maximas)
in fe form an
i n ts o d e
Po
em
to o n
Objects formed
Pruning (spatial Pruning (Spectral
(backtracking the
Bandwidth) Bandwidth)
modes)
Pruning ( Minimum
region area)
http://osgeo.in/foss4g2012 4
5. Object attribution
• Calculating textural, geometric and spectral features for the objects
made in the Segmentation step in a feature vector.
• Area, Perimeter, Roundness, Compactness, Centroid, Contrast,
Coarseness, Direction, Roughness, Mean red, Mean green, Mean
blue, std. deviation Red, std. deviation Green, std. deviation Blue.
Segmented Image For every object in the image
Initialize a vector having all 16
features
Calculate value for every feature
and save in the vector.
http://osgeo.in/foss4g2012 5
6. Classification
• Mahalanobis Distance
• Di,j2 = (x-µj)`S-1(x-µj)
• The class which has the least Mahalanobis
distance to the object i is the class of that object.
Vectorization
• Creates vector polygons for all connected regions of pixels in the
object image sharing a common pixel value.
• Polygon features are created on the output layer, with polygon
geometries representing the polygons.
• The class which has the least Mahalanobis distance to the object i is
the class of that object.
http://osgeo.in/foss4g2012 6
7. The Input Orbview3 (4m) data of a part of delhi (500X500) The output of the objects with area less than 100.
The shapefile(.shp) displaying the objects
Output of object having area 100-200 and classified as building.
http://osgeo.in/foss4g2012 7
8. Performance Analysis
Image Size Number of Running time
objects (sec)
512 X 512 153 3.1
1024 X 1024 435 24.55
Table 1 : Image segmentation
Image Size Number of objects Running time
(sec)
256 X 256 49 0.249
512 X 512 193 1.133
1024 X1024 752 5.359
2048 X 2048 2965 31.60
4096 X 4096 11922 286.59
Table 2 : Object Attribution
http://osgeo.in/foss4g2012 8
This paper describes a tool that implements Feature/Object Based This Image analysis for the Opticks remote sensing and image analysis software platform. These tools will partition remote sensing (RS) imagery into meaningful image-objects, and assess their characteristics through spatial, spectral and temporal scale. OSGEO-India: FOSS4G 2012- First National Conference "OPEN SOURCE GEOSPATIAL RESOURCES TO SPEARHEAD DEVELOPMENT AND GROWTH” 25-27TH OCTOBER 2012, @ IIIT HYDERABAD
OSGEO-India: FOSS4G 2012- First National Conference "OPEN SOURCE GEOSPATIAL RESOURCES TO SPEARHEAD DEVELOPMENT AND GROWTH” 25-27TH OCTOBER 2012, @ IIIT HYDERABAD