image pattern matching and optimization using simulated
TRANSCRIPT
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
1 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
MatlabExpo, 2014 1 By Vandita Srivastava, IIRS, Dehradun
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
Presented by
By,
Vandita Srivastava
Scientist ‘SE’,
Geoinformatics Department, IIRS Dehradun
Department of Space, Govt. of India
Authors: Vandita
Srivastava Alfred Stein,
D.G. Rossiter
P.K. Garg
R.D. Garg
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
2 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
MatlabExpo, 2014 2 By Vandita Srivastava, IIRS, Dehradun
Contents of Presentation
Background Motivation
Research Questions
Research Objectives
Methodology & Programme Logic
Resources Used
Results & Discussion
Conclusion
Future Recommendations
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
3 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Motivation for pattern matching
Advent of ever increasing spatio-temporal resolutions.
Lack of quick, automated and reliable information mining
methods.
Image pattern matching – a key research area in CBIR
Simulated annealing (SA) – a widely applied technique for
optimization, now applied to spatial domain also.
Geostatistics –represents spatial structure in the best
possible manner
MatlabExpo, 2014 3 By Vandita Srivastava, IIRS, Dehradun
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
4 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Research Questions
Can we obtain similar matching patterns in objects of
images through process of optimization of images through
SA?
Can we use variogram as an optimization function in SA
process?
How to execute this in Matlab?
How to optimize the code for performance (processing time,
memory)
What all issues to consider to make the code generic and
flexible?
MatlabExpo, 2014 4 By Vandita Srivastava, IIRS, Dehradun
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
5 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Research Objectives
Main Objectives:
Given a satellite image, obtain another image with similar
matching pattern
Explore potential of variogram as an optimization function
Implement the whole methodology of SA in Matlab
Sub Objectives:
A flexible & generic SA implementation w.r.t inputs & outputs
Code optimization for performance w.r.t processing time and memory
Evaluation of SA implementation on several images from several sites/times/trees/ areas / configurations / no. of objects.
MatlabExpo, 2014 5 By Vandita Srivastava, IIRS, Dehradun
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
6 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
4 stage Implementation
Image pre-preprocessing
Binarization of tree canopy boundaries.
Image rotation and cropping image area.
Image Simulation
Extraction of information on number and inter-spacing
between objects
Variogram Calculation
Omni & Directional variograms
Angle & Distance tolerances, Cutoff range definition
Simulated Annealing MatlabExpo, 2014 6 By Vandita Srivastava, IIRS, Dehradun
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
7 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Simulated Annealing
Motivated by the physical annealing process
Material is heated and slowly cooled into a uniform structure
Simulated annealing mimics this process
The first SA algorithm was developed in 1953
(Metropolis)
MatlabExpo, 2014 7 By Vandita Srivastava, IIRS, Dehradun
Metropolis, Nicholas; Rosenbluth, Arianna W.; Rosenbluth, Marshall N.; Teller, Augusta H.; Teller, Edward (1953). "Equation of State Calculations by Fast Computing Machines". The Journal of Chemical Physics 21 (6): 1087.
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
8 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Spatial Simulated Annealing
SA carried out for Spatially Explicit Processes
Kirkpatrick (1982) applied SA to optimisation
problems
SSA requirements
Initial Temperature
Initial solution
Cooling schedule
Acceptance criterion
Stopping criterion
Spatial Optimization function
MatlabExpo, 2014 8 By Vandita Srivastava, IIRS, Dehradun
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
9 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
SSA Parameters in our case
MatlabExpo, 2014 9 By Vandita Srivastava, IIRS, Dehradun
S. No. Parameter Name Value 1 h (decay factor) 1024
2 Cooling Rate 0.9995
3 dmax Diagonal distance normalized by square root of number of circles
4 Precision (for stopping criteria) 6 places after decimal (0.000001)
5
Max iterations with allowed moves (for stopping criteria) 3000
6
Number of worse moves to decide in equation probability threshold (in turn to decide initial temperature t0 ) 200
7 Initial temperature t0 0.039
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
10 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Image simulation Logic
MatlabExpo, 2014 10 By Vandita Srivastava, IIRS, Dehradun
Optimization Function
Probability Calculation
Simulated Image adjustment
If Not satisfied Probability Checking
If Satisfied
Accept Image
Real Image Simulated Image
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
11 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Resources used
MatlabExpo, 2014 11 By Vandita Srivastava, IIRS, Dehradun
Dehradun
Saharanpur
Study Area:
Dehradun, Saharanpur (City & Periphery)
Satellite Images:
Quick Bird
Temporal data used (March, May, December)
Software Used:
Matlab (IP & Mapping Toolboxes)
Additional tools:
Questionnaire Survey (Horticulture department)
Experts opinion (Simulated Annealing Parameters)
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
12 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Field work
Field measurements
Extent of tree
Tree Species
Approximate age
MatlabExpo, 2014 12 By Vandita Srivastava, IIRS, Dehradun
Survey details 10 sites surveyed
50 trees measured
2 areas (DDN, Saharanpur)
3 arrangements (linear, sparse, regular)
Sampling scheme: stratified random
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
13 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
MatlabExpo, 2014 13 By Vandita Srivastava, IIRS, Dehradun
Programme Issues Dealt With
High radiometric resolution of input image.
Memory space
optimisation during run.
Code vectorisation used for faster calculations
Flexible w.r.t input image & parameters
Generic w.r.t. image resolution & size,
number of objects, SA parameters
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
14 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
MatlabExpo, 2014 14 By Vandita Srivastava, IIRS, Dehradun
Programme Issues Dealt With
Outputs as mat & xls files, graphs, in one single folder generated
automatically, customized names based on parameters in a run
Time performance profiles used to reduce time consuming processes
Customized folder and file names
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
15 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Results
MatlabExpo, 2014 15 By Vandita Srivastava, IIRS, Dehradun
Sparse arrangement
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
16 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Results
MatlabExpo, 2014 16 By Vandita Srivastava, IIRS, Dehradun
Linear arrangement
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
17 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Results
MatlabExpo, 2014 17 By Vandita Srivastava, IIRS, Dehradun
Regular arrangement
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
18 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Results
MatlabExpo, 2014 18 By Vandita Srivastava, IIRS, Dehradun
Variograms in iterations
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
19 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Results
Behaviour of Fitness function
MatlabExpo, 2014 19 By Vandita Srivastava, IIRS, Dehradun
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
20 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Evaluation of Results
MatlabExpo, 2014 20 By Vandita Srivastava, IIRS, Dehradun
Evaluation on:
several images from two sites (DDN & Saharanpur),
different times (March, May & December),
Different species (Litchi & Mango Orchards)
3 configurations (linear, regular & sparse)
varying number of objects.
Evaluation Methods:
Visual analysis of patterns
Nearest Neighbour Index/Polygon pattern analysis
Evaluation stages:
Binarisation
Image pattern matching
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
21 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Research outcomes
An algorithm for Spatial Simulated Annealing (developed,
implemented and evaluated)
Demonstrated potential use of variogram as an optimization
function
A flexible SA implementation w.r.t input images & SA
parameters
A generic SA implementation w.r.t image products, type of
objects
Outcome of a SA run reported as mat & xls files, figures &
graphs
Code optimization for performance w.r.t processing time and
memory space
MatlabExpo, 2014 21 By Vandita Srivastava, IIRS, Dehradun
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
22 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Potential Applications
Pattern Recognition and matching
Find images having clusters of similarly configured
objects
Content based image retrieval(CBIR)
Get several choices for arrangements with similar
spatial configuration (low object density) (think of
example and put)-good for planners as a tool.
MatlabExpo, 2014 22 By Vandita Srivastava, IIRS, Dehradun
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
23 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Potential Application Areas
Image mining & CBIR
Agro-forestry, Horticulture, Forestry
Carbon budgeting/ sequestration studies
Global warming & environmental pollution studies
Planning & Management studies
MatlabExpo, 2014 23 By Vandita Srivastava, IIRS, Dehradun
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
24 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Conclusion
Usefulness of variogram as an optimization
demonstrated
Spatial Simulated Annealing implemented for image pattern matching
Success of SA demonstrated on binarised images
of individual trees for obtaining images with similar patterns.
The methodology is put forward for further
evaluation by application scientists and other researchers for its benefits.
MatlabExpo, 2014 24 By Vandita Srivastava, IIRS, Dehradun
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
25 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Future recommendations/Further Work
Extend for other type of objects of varying
shapes.
Extend for gray images
Overlapping objects.
MatlabExpo, 2014 25 By Vandita Srivastava, IIRS, Dehradun
Image Pattern Matching and optimization using simulated annealing: a Matlab Implementation
26 Matlab Expo 2014 By, Vandita Srivastava, IIRS, Dehradun
Thank You
MatlabExpo, 2014 26 By Vandita Srivastava, IIRS, Dehradun
Questions?
Vandita Srivastava
Scientist ‘SE’, Geoinformatics Department, IIRS Dehradun
Department of Space, Govt. of India
Research Interest: Advanced Image Processing for
information mining of geospatial data