SlideShare a Scribd company logo
ISAR Image Sequence based Automatic Target
Recognition by using a Multi-frame Marked Point
                Process Model

          Csaba Benedek1                Marco Martorella2

            1 Distributed Events Analysis Research Group

         Computer and Automation Research Institute, Hungary
       2 University   of Pisa, Department of Information Engineering

            Work partially funded by the APIS Project of EDA




            IGARSS 2011, Vancouver, Canada
Content


1    Introduction

2    Multiframe Marked Point Process Model
       Model elements and configuration energy
       Optimization

3    Experiments

4    Future steps and conclusions




Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences   28 July 2011   2 / 19
Introduction


Content


1    Introduction

2    Multiframe Marked Point Process Model
       Model elements and configuration energy
       Optimization

3    Experiments

4    Future steps and conclusions




Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences   28 July 2011   3 / 19
Introduction


Introduction


        Extracting ship scattering centers in airborne Inverse Synthetic
        Aperture Radar (ISAR) image sequences
               Framework: “Array Passive ISAR Adaptive Processing” (APIS)
               Project of EDA
        ISAR images in Automatic Target Recognition (ATR) systems
               applicable where other imaging techniques (e.g. SAR) fail
               post processing step after detection & imaging
               frames have different quality parameters (e.g. image focus)
        Goals:
               Measuring relevant features for target identification and behaviour
               analysis



Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences   28 July 2011   4 / 19
Introduction


Proposed approach

        Robust multi-frame technique, integrating the noisy image
        information with prior constraints of target shape persistency and
        smooth motion.
               Multiframe Marked Point Process model
        Input:
               ISAR image sequence of the detected target
        Output:
               center line segment parameters of the target in each frame
                      length and orientation
               positions of permanent characteristic feature points




Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences   28 July 2011   5 / 19
Multiframe Marked Point Process Model


Content


1    Introduction

2    Multiframe Marked Point Process Model
       Model elements and configuration energy
       Optimization

3    Experiments

4    Future steps and conclusions




Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences   28 July 2011   6 / 19
Multiframe Marked Point Process Model   Model elements and configuration energy


Configuration model: notations


      Observation: n-frame-long ISAR
      image sequence
              S: joint pixel lattice of the ISAR
              frames, s ∈ S: a single pixel
              Bt : binarized input image observed
              at time frame t ∈ {1, 2, . . . , n}
              Bt (s) ∈ {0, 1}: value of pixel s in Bt
      ut ∈ H: a target candidate in frame t
      Goal: extract a sequence of objects:
              ω = {u1 , u2 , . . . , un } ∈ H n




Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences                 28 July 2011   7 / 19
Multiframe Marked Point Process Model   Model elements and configuration energy


Target modeling in a single ISAR frame

        Parameters describing a target u:
               c(u) = [x (u), y (u)] center pixel, l(u) length and θ(u) orientation




        Misalignment problem
               periodicity of ISAR images both in horizontal and vertical directions
               target may break into two/four pieces
               using a duplicated mosaic image


Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences                 28 July 2011   8 / 19
Multiframe Marked Point Process Model     Model elements and configuration energy


Fm MPP energy function
        Object sequence or configuration:

                                              ω = {u1 , u2 , . . . , un }

        Configuration energy:
                                                n                        n−1
                              ΦD (ω) =              AD (ut ) +γ ·              I (ut , ut+1 )
                                              t=1                        t=1


               AD (ut ): D-data dependent unary object potential
               I (ut , ut+1 ) prior interaction potential function between objects of
               consecutive frames
        Maximum Likelihood (ML) configuration estimate:

                                               ω = argmin ΦD (ω)
                                                            ω∈H n

Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences                   28 July 2011   9 / 19
Multiframe Marked Point Process Model     Model elements and configuration energy


Data term



      Unary potentials:
              evaluation of proposed ship
              candidates in independent frames


        Calculation:
                                                                                                               
                                            1
           AD (ut ) = Q                                                Bt (s) +            (1 − Bt (s))
                                      Area{Rut ∪ Tut }
                                                               s∈Rut                s∈Tut


               Q(ζ) : R → [−1, 1]: a non-linear monotonously decreasing function



Benedek & Martorella (SZTAKI, CNIT)     Target Extraction in ISAR Image Sequences                28 July 2011   10 / 19
Multiframe Marked Point Process Model   Model elements and configuration energy


Interaction potentials

        Key role: enforcing prior geometrical constraints.
               persistent frame rate → small object displacements between two
               consecutive frames
        Feature: length and angle difference (center is not relevant)

                I (ut , ut+1 ) = δθ · |θ (ut ) − θ (ut+1 )| + δl · |l (ut ) − l (ut+1 ) |




                                             Penalized configuration ×



                                                                            √
                                              Favored configuration


Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences                28 July 2011   11 / 19
Multiframe Marked Point Process Model   Optimization


Optimization: iterative stochastic algorithms

        The algorithm
           1   Start with a frame-by-frame initialization process
                      Hough transform based line estimation in each binarized frame Bt ,
                      t = 1...n
           2   Iterate object perturbation and acceptance steps till convergence is
               obtained in the extracted object sequence
                      Object perturbation: for each t we propose an object u ∗ which is the
                      random perturbation of ut−1 OR ut OR ut+1
                      Acceptance: we accept or reject a move replacing ut width u ∗
        Important properties:
               Acceptance: inverse approach considering simultaneously data
               and prior features
               Stochastic process both for object perturbation and acceptance
               (unlike in conventional hypothesis generation-acceptance
               techniques)
               Simulated annealing framework to ensure convergence

Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences   28 July 2011   12 / 19
Multiframe Marked Point Process Model   Optimization


Optimization: iterative stochastic algorithms

        The algorithm
           1   Start with a frame-by-frame initialization process
                      Hough transform based line estimation in each binarized frame Bt ,
                      t = 1...n
           2   Iterate object perturbation and acceptance steps till convergence is
               obtained in the extracted object sequence
                      Object perturbation: for each t we propose an object u ∗ which is the
                      random perturbation of ut−1 OR ut OR ut+1
                      Acceptance: we accept or reject a move replacing ut width u ∗
        Important properties:
               Acceptance: inverse approach considering simultaneously data
               and prior features
               Stochastic process both for object perturbation and acceptance
               (unlike in conventional hypothesis generation-acceptance
               techniques)
               Simulated annealing framework to ensure convergence

Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences   28 July 2011   12 / 19
Multiframe Marked Point Process Model   Optimization


Target identification
Permanent scatterer extraction and counting

      Permanent scatterer
      responses: characteristic
      target features
              high false/missing alarm rate
              in the individual frames
              (>50%)
              histograming technique for
              extracting the permanent
              scatters




Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences   28 July 2011   13 / 19
Experiments


Content


1    Introduction

2    Multiframe Marked Point Process Model
       Model elements and configuration energy
       Optimization

3    Experiments

4    Future steps and conclusions




Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences   28 July 2011   14 / 19
Experiments


Experiments - qualitative results


        Center alignment and target line extraction results




Top: input sequence. Center: frame-by-frame detection. Bottom: detection by the
proposed Fm MPP model



Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences   28 July 2011   15 / 19
Experiments


Experiments - quantitative results
        Test sequences:
               four airborne ISAR image sequences (each has 15-40 frames)
               different ship targets.
        Error measure:
                                            n
                E ({ut }, {utgt })     =           |x(ut ) − x(utgt )| + |y(ut ) − y(utgt )|+
                                           t=1

                                           + |l(ut ) − l(utgt )| + |θ(ut ) − θ(utgt )|

                      Sequence Frames                     Init Err.        Fm MPP Err.
                      Ship 1     13                         52.0               7.5
                      Ship 2     13                         67.1              37.8
                      Ship 3     13                         17.2              12.8
                      Ship 4     54                         43.7              12.6

Benedek & Martorella (SZTAKI, CNIT)   Target Extraction in ISAR Image Sequences          28 July 2011   16 / 19
Future steps and conclusions


Content


1    Introduction

2    Multiframe Marked Point Process Model
       Model elements and configuration energy
       Optimization

3    Experiments

4    Future steps and conclusions




Benedek & Martorella (SZTAKI, CNIT)    Target Extraction in ISAR Image Sequences   28 July 2011   17 / 19
Future steps and conclusions


Generalization for various objects

      Identifying Airplanes in ISAR sequences
              Cross shaped model
              Shadowed wing

        Result by the two step process




Benedek & Martorella (SZTAKI, CNIT)    Target Extraction in ISAR Image Sequences   28 July 2011   18 / 19
Future steps and conclusions


Conclusions




        Detecting and featuring ship/airplane targets in ISAR image
        sequences through energy minimization
        Proposed Multi-frame Marked Point Process schema
               advantages versus a frame-by-frame direct detection technique
        Towards target classification
               permanent scatterer detection algorithm based on histograming




Benedek & Martorella (SZTAKI, CNIT)    Target Extraction in ISAR Image Sequences   28 July 2011   19 / 19

More Related Content

What's hot

Image Splicing Detection involving Moment-based Feature Extraction and Classi...
Image Splicing Detection involving Moment-based Feature Extraction and Classi...Image Splicing Detection involving Moment-based Feature Extraction and Classi...
Image Splicing Detection involving Moment-based Feature Extraction and Classi...
IDES Editor
 
Fourier descriptors & moments
Fourier descriptors & momentsFourier descriptors & moments
Fourier descriptors & moments
rajisri2
 
Performance Evaluation of Object Tracking Technique Based on Position Vectors
Performance Evaluation of Object Tracking Technique Based on Position VectorsPerformance Evaluation of Object Tracking Technique Based on Position Vectors
Performance Evaluation of Object Tracking Technique Based on Position Vectors
CSCJournals
 
Kq3518291832
Kq3518291832Kq3518291832
Kq3518291832
IJERA Editor
 
Kernel methods in machine learning
Kernel methods in machine learningKernel methods in machine learning
Kernel methods in machine learning
butest
 
PSIVT2015_slide
PSIVT2015_slidePSIVT2015_slide
PSIVT2015_slide
norikinishida
 
An enhanced fireworks algorithm to generate prime key for multiple users in f...
An enhanced fireworks algorithm to generate prime key for multiple users in f...An enhanced fireworks algorithm to generate prime key for multiple users in f...
An enhanced fireworks algorithm to generate prime key for multiple users in f...
journalBEEI
 
Rigorous Pack Edge Detection Fuzzy System
Rigorous Pack Edge Detection Fuzzy SystemRigorous Pack Edge Detection Fuzzy System
Rigorous Pack Edge Detection Fuzzy System
inventy
 
Fn2611681170
Fn2611681170Fn2611681170
Fn2611681170
IJERA Editor
 
Block Matching Project
Block Matching ProjectBlock Matching Project
Block Matching Project
dswazalwar
 
Image segmentation in Digital Image Processing
Image segmentation in Digital Image ProcessingImage segmentation in Digital Image Processing
Image segmentation in Digital Image Processing
DHIVYADEVAKI
 
Illustration Clamor Echelon Evaluation via Prime Piece Psychotherapy
Illustration Clamor Echelon Evaluation via Prime Piece PsychotherapyIllustration Clamor Echelon Evaluation via Prime Piece Psychotherapy
Illustration Clamor Echelon Evaluation via Prime Piece Psychotherapy
IJMER
 
[Download] rev chapter-8-june26th
[Download] rev chapter-8-june26th[Download] rev chapter-8-june26th
Unsupervised multispectral image Classification By fuzzy hidden Markov chains...
Unsupervised multispectral image Classification By fuzzy hidden Markov chains...Unsupervised multispectral image Classification By fuzzy hidden Markov chains...
Unsupervised multispectral image Classification By fuzzy hidden Markov chains...
CSCJournals
 
Background Subtraction Based on Phase and Distance Transform Under Sudden Ill...
Background Subtraction Based on Phase and Distance Transform Under Sudden Ill...Background Subtraction Based on Phase and Distance Transform Under Sudden Ill...
Background Subtraction Based on Phase and Distance Transform Under Sudden Ill...
Shanghai Jiao Tong University(上海交通大学)
 
Semantic Video Segmentation with Using Ensemble of Particular Classifiers and...
Semantic Video Segmentation with Using Ensemble of Particular Classifiers and...Semantic Video Segmentation with Using Ensemble of Particular Classifiers and...
Semantic Video Segmentation with Using Ensemble of Particular Classifiers and...
ITIIIndustries
 
N018219199
N018219199N018219199
N018219199
IOSR Journals
 
PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additi...
PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additi...PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additi...
PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additi...
Taiji Suzuki
 
Design and implementation of video tracking system based on camera field of view
Design and implementation of video tracking system based on camera field of viewDesign and implementation of video tracking system based on camera field of view
Design and implementation of video tracking system based on camera field of view
sipij
 
B070306010
B070306010B070306010
B070306010
IJERD Editor
 

What's hot (20)

Image Splicing Detection involving Moment-based Feature Extraction and Classi...
Image Splicing Detection involving Moment-based Feature Extraction and Classi...Image Splicing Detection involving Moment-based Feature Extraction and Classi...
Image Splicing Detection involving Moment-based Feature Extraction and Classi...
 
Fourier descriptors & moments
Fourier descriptors & momentsFourier descriptors & moments
Fourier descriptors & moments
 
Performance Evaluation of Object Tracking Technique Based on Position Vectors
Performance Evaluation of Object Tracking Technique Based on Position VectorsPerformance Evaluation of Object Tracking Technique Based on Position Vectors
Performance Evaluation of Object Tracking Technique Based on Position Vectors
 
Kq3518291832
Kq3518291832Kq3518291832
Kq3518291832
 
Kernel methods in machine learning
Kernel methods in machine learningKernel methods in machine learning
Kernel methods in machine learning
 
PSIVT2015_slide
PSIVT2015_slidePSIVT2015_slide
PSIVT2015_slide
 
An enhanced fireworks algorithm to generate prime key for multiple users in f...
An enhanced fireworks algorithm to generate prime key for multiple users in f...An enhanced fireworks algorithm to generate prime key for multiple users in f...
An enhanced fireworks algorithm to generate prime key for multiple users in f...
 
Rigorous Pack Edge Detection Fuzzy System
Rigorous Pack Edge Detection Fuzzy SystemRigorous Pack Edge Detection Fuzzy System
Rigorous Pack Edge Detection Fuzzy System
 
Fn2611681170
Fn2611681170Fn2611681170
Fn2611681170
 
Block Matching Project
Block Matching ProjectBlock Matching Project
Block Matching Project
 
Image segmentation in Digital Image Processing
Image segmentation in Digital Image ProcessingImage segmentation in Digital Image Processing
Image segmentation in Digital Image Processing
 
Illustration Clamor Echelon Evaluation via Prime Piece Psychotherapy
Illustration Clamor Echelon Evaluation via Prime Piece PsychotherapyIllustration Clamor Echelon Evaluation via Prime Piece Psychotherapy
Illustration Clamor Echelon Evaluation via Prime Piece Psychotherapy
 
[Download] rev chapter-8-june26th
[Download] rev chapter-8-june26th[Download] rev chapter-8-june26th
[Download] rev chapter-8-june26th
 
Unsupervised multispectral image Classification By fuzzy hidden Markov chains...
Unsupervised multispectral image Classification By fuzzy hidden Markov chains...Unsupervised multispectral image Classification By fuzzy hidden Markov chains...
Unsupervised multispectral image Classification By fuzzy hidden Markov chains...
 
Background Subtraction Based on Phase and Distance Transform Under Sudden Ill...
Background Subtraction Based on Phase and Distance Transform Under Sudden Ill...Background Subtraction Based on Phase and Distance Transform Under Sudden Ill...
Background Subtraction Based on Phase and Distance Transform Under Sudden Ill...
 
Semantic Video Segmentation with Using Ensemble of Particular Classifiers and...
Semantic Video Segmentation with Using Ensemble of Particular Classifiers and...Semantic Video Segmentation with Using Ensemble of Particular Classifiers and...
Semantic Video Segmentation with Using Ensemble of Particular Classifiers and...
 
N018219199
N018219199N018219199
N018219199
 
PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additi...
PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additi...PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additi...
PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additi...
 
Design and implementation of video tracking system based on camera field of view
Design and implementation of video tracking system based on camera field of viewDesign and implementation of video tracking system based on camera field of view
Design and implementation of video tracking system based on camera field of view
 
B070306010
B070306010B070306010
B070306010
 

Viewers also liked

ISAR presentation-Dr. Gahakwa
ISAR presentation-Dr. GahakwaISAR presentation-Dr. Gahakwa
ISAR presentation-Dr. Gahakwa
cenafrica
 
Ancortek IEEE 2015 Radar Conference Presentation
Ancortek IEEE 2015 Radar Conference PresentationAncortek IEEE 2015 Radar Conference Presentation
Ancortek IEEE 2015 Radar Conference Presentation
ancortek
 
FR4.L09 - OPTIMAL SENSOR POSITIONING FOR ISAR IMAGING
FR4.L09 - OPTIMAL SENSOR POSITIONING FOR ISAR IMAGINGFR4.L09 - OPTIMAL SENSOR POSITIONING FOR ISAR IMAGING
FR4.L09 - OPTIMAL SENSOR POSITIONING FOR ISAR IMAGING
grssieee
 
Extrapolation
ExtrapolationExtrapolation
Extrapolation
Alkesh Goyal
 
4-IGARSS_2011_v4.ppt
4-IGARSS_2011_v4.ppt4-IGARSS_2011_v4.ppt
4-IGARSS_2011_v4.ppt
grssieee
 
Isar to VR
Isar to VRIsar to VR
Isar to VR
M Denniey Snyder
 
اکسیری
اکسیریاکسیری
اکسیری
Nwab Sadozai
 
14. doppler radar and mti 2014
14. doppler radar and mti 201414. doppler radar and mti 2014
14. doppler radar and mti 2014
Lohith Kumar
 
Schlenker.lobell.2010.erl 2
Schlenker.lobell.2010.erl 2Schlenker.lobell.2010.erl 2
Schlenker.lobell.2010.erl 2
cenafrica
 
radar-ppt
radar-pptradar-ppt
Radar Application
Radar ApplicationRadar Application
Radar Application
mathurrohitji
 

Viewers also liked (11)

ISAR presentation-Dr. Gahakwa
ISAR presentation-Dr. GahakwaISAR presentation-Dr. Gahakwa
ISAR presentation-Dr. Gahakwa
 
Ancortek IEEE 2015 Radar Conference Presentation
Ancortek IEEE 2015 Radar Conference PresentationAncortek IEEE 2015 Radar Conference Presentation
Ancortek IEEE 2015 Radar Conference Presentation
 
FR4.L09 - OPTIMAL SENSOR POSITIONING FOR ISAR IMAGING
FR4.L09 - OPTIMAL SENSOR POSITIONING FOR ISAR IMAGINGFR4.L09 - OPTIMAL SENSOR POSITIONING FOR ISAR IMAGING
FR4.L09 - OPTIMAL SENSOR POSITIONING FOR ISAR IMAGING
 
Extrapolation
ExtrapolationExtrapolation
Extrapolation
 
4-IGARSS_2011_v4.ppt
4-IGARSS_2011_v4.ppt4-IGARSS_2011_v4.ppt
4-IGARSS_2011_v4.ppt
 
Isar to VR
Isar to VRIsar to VR
Isar to VR
 
اکسیری
اکسیریاکسیری
اکسیری
 
14. doppler radar and mti 2014
14. doppler radar and mti 201414. doppler radar and mti 2014
14. doppler radar and mti 2014
 
Schlenker.lobell.2010.erl 2
Schlenker.lobell.2010.erl 2Schlenker.lobell.2010.erl 2
Schlenker.lobell.2010.erl 2
 
radar-ppt
radar-pptradar-ppt
radar-ppt
 
Radar Application
Radar ApplicationRadar Application
Radar Application
 

Similar to igarss11benedek.pdf

Medial axis transformation based skeletonzation of image patterns using image...
Medial axis transformation based skeletonzation of image patterns using image...Medial axis transformation based skeletonzation of image patterns using image...
Medial axis transformation based skeletonzation of image patterns using image...
International Journal of Science and Research (IJSR)
 
Implementation and performance evaluation of
Implementation and performance evaluation ofImplementation and performance evaluation of
Implementation and performance evaluation of
ijcsa
 
Ph.D. Presentation
Ph.D. PresentationPh.D. Presentation
Ph.D. Presentation
matteodefelice
 
Multi-core GPU – Fast parallel SAR image generation
Multi-core GPU – Fast parallel SAR image generationMulti-core GPU – Fast parallel SAR image generation
Multi-core GPU – Fast parallel SAR image generation
Mahesh Khadatare
 
BMC 2012 - Invited Talk
BMC 2012 - Invited TalkBMC 2012 - Invited Talk
BMC 2012 - Invited Talk
BOUWMANS Thierry
 
L-3 classification.pdf
L-3 classification.pdfL-3 classification.pdf
L-3 classification.pdf
sureshkumarsaini8
 
Scrdet++ analysis
Scrdet++ analysisScrdet++ analysis
Scrdet++ analysis
NEHA Kapoor
 
Single layer perceptron in python
Single layer perceptron in pythonSingle layer perceptron in python
Single layer perceptron in python
Tahmina Zebin
 
Landuse Classification from Satellite Imagery using Deep Learning
Landuse Classification from Satellite Imagery using Deep LearningLanduse Classification from Satellite Imagery using Deep Learning
Landuse Classification from Satellite Imagery using Deep Learning
DataWorks Summit
 
Enhancement of genetic image watermarking robust against cropping attack
Enhancement of genetic image watermarking robust against cropping attackEnhancement of genetic image watermarking robust against cropping attack
Enhancement of genetic image watermarking robust against cropping attack
ijfcstjournal
 
Comparative analysis and implementation of structured edge active contour
Comparative analysis and implementation of structured edge active contour Comparative analysis and implementation of structured edge active contour
Comparative analysis and implementation of structured edge active contour
IJECEIAES
 
Reading_0413_var_Transformers.pptx
Reading_0413_var_Transformers.pptxReading_0413_var_Transformers.pptx
Reading_0413_var_Transformers.pptx
congtran88
 
Threshold adaptation and XOR accumulation algorithm for objects detection
Threshold adaptation and XOR accumulation algorithm for  objects detectionThreshold adaptation and XOR accumulation algorithm for  objects detection
Threshold adaptation and XOR accumulation algorithm for objects detection
IJECEIAES
 
APPLICATION OF IMAGE FUSION FOR ENHANCING THE QUALITY OF AN IMAGE
APPLICATION OF IMAGE FUSION FOR ENHANCING THE QUALITY OF AN IMAGEAPPLICATION OF IMAGE FUSION FOR ENHANCING THE QUALITY OF AN IMAGE
APPLICATION OF IMAGE FUSION FOR ENHANCING THE QUALITY OF AN IMAGE
cscpconf
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
ijceronline
 
Large scale landuse classification of satellite imagery
Large scale landuse classification of satellite imageryLarge scale landuse classification of satellite imagery
Large scale landuse classification of satellite imagery
Suneel Marthi
 
Phd Defense 2007
Phd Defense 2007Phd Defense 2007
Phd Defense 2007
Claudio Siviero
 
Low complexity features for jpeg steganalysis using undecimated dct
Low complexity features for jpeg steganalysis using undecimated dctLow complexity features for jpeg steganalysis using undecimated dct
Low complexity features for jpeg steganalysis using undecimated dct
Pvrtechnologies Nellore
 
Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...
Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...
Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...
Dongmin Choi
 
Index Determination in DAEs using the Library indexdet and the ADOL-C Package...
Index Determination in DAEs using the Library indexdet and the ADOL-C Package...Index Determination in DAEs using the Library indexdet and the ADOL-C Package...
Index Determination in DAEs using the Library indexdet and the ADOL-C Package...
Dagmar Monett
 

Similar to igarss11benedek.pdf (20)

Medial axis transformation based skeletonzation of image patterns using image...
Medial axis transformation based skeletonzation of image patterns using image...Medial axis transformation based skeletonzation of image patterns using image...
Medial axis transformation based skeletonzation of image patterns using image...
 
Implementation and performance evaluation of
Implementation and performance evaluation ofImplementation and performance evaluation of
Implementation and performance evaluation of
 
Ph.D. Presentation
Ph.D. PresentationPh.D. Presentation
Ph.D. Presentation
 
Multi-core GPU – Fast parallel SAR image generation
Multi-core GPU – Fast parallel SAR image generationMulti-core GPU – Fast parallel SAR image generation
Multi-core GPU – Fast parallel SAR image generation
 
BMC 2012 - Invited Talk
BMC 2012 - Invited TalkBMC 2012 - Invited Talk
BMC 2012 - Invited Talk
 
L-3 classification.pdf
L-3 classification.pdfL-3 classification.pdf
L-3 classification.pdf
 
Scrdet++ analysis
Scrdet++ analysisScrdet++ analysis
Scrdet++ analysis
 
Single layer perceptron in python
Single layer perceptron in pythonSingle layer perceptron in python
Single layer perceptron in python
 
Landuse Classification from Satellite Imagery using Deep Learning
Landuse Classification from Satellite Imagery using Deep LearningLanduse Classification from Satellite Imagery using Deep Learning
Landuse Classification from Satellite Imagery using Deep Learning
 
Enhancement of genetic image watermarking robust against cropping attack
Enhancement of genetic image watermarking robust against cropping attackEnhancement of genetic image watermarking robust against cropping attack
Enhancement of genetic image watermarking robust against cropping attack
 
Comparative analysis and implementation of structured edge active contour
Comparative analysis and implementation of structured edge active contour Comparative analysis and implementation of structured edge active contour
Comparative analysis and implementation of structured edge active contour
 
Reading_0413_var_Transformers.pptx
Reading_0413_var_Transformers.pptxReading_0413_var_Transformers.pptx
Reading_0413_var_Transformers.pptx
 
Threshold adaptation and XOR accumulation algorithm for objects detection
Threshold adaptation and XOR accumulation algorithm for  objects detectionThreshold adaptation and XOR accumulation algorithm for  objects detection
Threshold adaptation and XOR accumulation algorithm for objects detection
 
APPLICATION OF IMAGE FUSION FOR ENHANCING THE QUALITY OF AN IMAGE
APPLICATION OF IMAGE FUSION FOR ENHANCING THE QUALITY OF AN IMAGEAPPLICATION OF IMAGE FUSION FOR ENHANCING THE QUALITY OF AN IMAGE
APPLICATION OF IMAGE FUSION FOR ENHANCING THE QUALITY OF AN IMAGE
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
 
Large scale landuse classification of satellite imagery
Large scale landuse classification of satellite imageryLarge scale landuse classification of satellite imagery
Large scale landuse classification of satellite imagery
 
Phd Defense 2007
Phd Defense 2007Phd Defense 2007
Phd Defense 2007
 
Low complexity features for jpeg steganalysis using undecimated dct
Low complexity features for jpeg steganalysis using undecimated dctLow complexity features for jpeg steganalysis using undecimated dct
Low complexity features for jpeg steganalysis using undecimated dct
 
Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...
Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...
Review : PolarMask: Single Shot Instance Segmentation with Polar Representati...
 
Index Determination in DAEs using the Library indexdet and the ADOL-C Package...
Index Determination in DAEs using the Library indexdet and the ADOL-C Package...Index Determination in DAEs using the Library indexdet and the ADOL-C Package...
Index Determination in DAEs using the Library indexdet and the ADOL-C Package...
 

More from grssieee

Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...
Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...
Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...grssieee
 
SEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODEL
SEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODELSEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODEL
SEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODEL
grssieee
 
TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...
TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...
TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...
grssieee
 
THE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIES
THE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIESTHE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIES
THE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIES
grssieee
 
GMES SPACE COMPONENT:PROGRAMMATIC STATUS
GMES SPACE COMPONENT:PROGRAMMATIC STATUSGMES SPACE COMPONENT:PROGRAMMATIC STATUS
GMES SPACE COMPONENT:PROGRAMMATIC STATUS
grssieee
 
PROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETER
PROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETERPROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETER
PROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETER
grssieee
 
DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...
DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...
DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...
grssieee
 
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
grssieee
 
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
grssieee
 
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
grssieee
 
Test
TestTest
Test
grssieee
 
test 34mb wo animations
test  34mb wo animationstest  34mb wo animations
test 34mb wo animationsgrssieee
 
2011_Fox_Tax_Worksheets.pdf
2011_Fox_Tax_Worksheets.pdf2011_Fox_Tax_Worksheets.pdf
2011_Fox_Tax_Worksheets.pdf
grssieee
 
DLR open house
DLR open houseDLR open house
DLR open housegrssieee
 
DLR open house
DLR open houseDLR open house
DLR open housegrssieee
 
DLR open house
DLR open houseDLR open house
DLR open housegrssieee
 
Tana_IGARSS2011.ppt
Tana_IGARSS2011.pptTana_IGARSS2011.ppt
Tana_IGARSS2011.ppt
grssieee
 
Solaro_IGARSS_2011.ppt
Solaro_IGARSS_2011.pptSolaro_IGARSS_2011.ppt
Solaro_IGARSS_2011.ppt
grssieee
 

More from grssieee (20)

Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...
Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...
Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...
 
SEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODEL
SEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODELSEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODEL
SEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODEL
 
TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...
TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...
TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...
 
THE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIES
THE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIESTHE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIES
THE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIES
 
GMES SPACE COMPONENT:PROGRAMMATIC STATUS
GMES SPACE COMPONENT:PROGRAMMATIC STATUSGMES SPACE COMPONENT:PROGRAMMATIC STATUS
GMES SPACE COMPONENT:PROGRAMMATIC STATUS
 
PROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETER
PROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETERPROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETER
PROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETER
 
DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...
DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...
DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...
 
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
 
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
 
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
 
Test
TestTest
Test
 
test 34mb wo animations
test  34mb wo animationstest  34mb wo animations
test 34mb wo animations
 
Test 70MB
Test 70MBTest 70MB
Test 70MB
 
Test 70MB
Test 70MBTest 70MB
Test 70MB
 
2011_Fox_Tax_Worksheets.pdf
2011_Fox_Tax_Worksheets.pdf2011_Fox_Tax_Worksheets.pdf
2011_Fox_Tax_Worksheets.pdf
 
DLR open house
DLR open houseDLR open house
DLR open house
 
DLR open house
DLR open houseDLR open house
DLR open house
 
DLR open house
DLR open houseDLR open house
DLR open house
 
Tana_IGARSS2011.ppt
Tana_IGARSS2011.pptTana_IGARSS2011.ppt
Tana_IGARSS2011.ppt
 
Solaro_IGARSS_2011.ppt
Solaro_IGARSS_2011.pptSolaro_IGARSS_2011.ppt
Solaro_IGARSS_2011.ppt
 

Recently uploaded

Y-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PPY-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PP
c5vrf27qcz
 
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
Edge AI and Vision Alliance
 
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development ProvidersYour One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
akankshawande
 
Essentials of Automations: Exploring Attributes & Automation Parameters
Essentials of Automations: Exploring Attributes & Automation ParametersEssentials of Automations: Exploring Attributes & Automation Parameters
Essentials of Automations: Exploring Attributes & Automation Parameters
Safe Software
 
Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Biomedical Knowledge Graphs for Data Scientists and BioinformaticiansBiomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Neo4j
 
Leveraging the Graph for Clinical Trials and Standards
Leveraging the Graph for Clinical Trials and StandardsLeveraging the Graph for Clinical Trials and Standards
Leveraging the Graph for Clinical Trials and Standards
Neo4j
 
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
saastr
 
Skybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoptionSkybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoption
Tatiana Kojar
 
Dandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity serverDandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity server
Antonios Katsarakis
 
Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024
Jason Packer
 
Taking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdfTaking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdf
ssuserfac0301
 
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectorsConnector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
DianaGray10
 
"Choosing proper type of scaling", Olena Syrota
"Choosing proper type of scaling", Olena Syrota"Choosing proper type of scaling", Olena Syrota
"Choosing proper type of scaling", Olena Syrota
Fwdays
 
AppSec PNW: Android and iOS Application Security with MobSF
AppSec PNW: Android and iOS Application Security with MobSFAppSec PNW: Android and iOS Application Security with MobSF
AppSec PNW: Android and iOS Application Security with MobSF
Ajin Abraham
 
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving
 
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge GraphGraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
Neo4j
 
June Patch Tuesday
June Patch TuesdayJune Patch Tuesday
June Patch Tuesday
Ivanti
 
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
Energy Efficient Video Encoding for Cloud and Edge Computing InstancesEnergy Efficient Video Encoding for Cloud and Edge Computing Instances
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
Alpen-Adria-Universität
 
Nordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptxNordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptx
MichaelKnudsen27
 
Introduction of Cybersecurity with OSS at Code Europe 2024
Introduction of Cybersecurity with OSS  at Code Europe 2024Introduction of Cybersecurity with OSS  at Code Europe 2024
Introduction of Cybersecurity with OSS at Code Europe 2024
Hiroshi SHIBATA
 

Recently uploaded (20)

Y-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PPY-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PP
 
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
 
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development ProvidersYour One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
 
Essentials of Automations: Exploring Attributes & Automation Parameters
Essentials of Automations: Exploring Attributes & Automation ParametersEssentials of Automations: Exploring Attributes & Automation Parameters
Essentials of Automations: Exploring Attributes & Automation Parameters
 
Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Biomedical Knowledge Graphs for Data Scientists and BioinformaticiansBiomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
 
Leveraging the Graph for Clinical Trials and Standards
Leveraging the Graph for Clinical Trials and StandardsLeveraging the Graph for Clinical Trials and Standards
Leveraging the Graph for Clinical Trials and Standards
 
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
 
Skybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoptionSkybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoption
 
Dandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity serverDandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity server
 
Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024
 
Taking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdfTaking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdf
 
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectorsConnector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
 
"Choosing proper type of scaling", Olena Syrota
"Choosing proper type of scaling", Olena Syrota"Choosing proper type of scaling", Olena Syrota
"Choosing proper type of scaling", Olena Syrota
 
AppSec PNW: Android and iOS Application Security with MobSF
AppSec PNW: Android and iOS Application Security with MobSFAppSec PNW: Android and iOS Application Security with MobSF
AppSec PNW: Android and iOS Application Security with MobSF
 
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024
 
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge GraphGraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
 
June Patch Tuesday
June Patch TuesdayJune Patch Tuesday
June Patch Tuesday
 
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
Energy Efficient Video Encoding for Cloud and Edge Computing InstancesEnergy Efficient Video Encoding for Cloud and Edge Computing Instances
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
 
Nordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptxNordic Marketo Engage User Group_June 13_ 2024.pptx
Nordic Marketo Engage User Group_June 13_ 2024.pptx
 
Introduction of Cybersecurity with OSS at Code Europe 2024
Introduction of Cybersecurity with OSS  at Code Europe 2024Introduction of Cybersecurity with OSS  at Code Europe 2024
Introduction of Cybersecurity with OSS at Code Europe 2024
 

igarss11benedek.pdf

  • 1. ISAR Image Sequence based Automatic Target Recognition by using a Multi-frame Marked Point Process Model Csaba Benedek1 Marco Martorella2 1 Distributed Events Analysis Research Group Computer and Automation Research Institute, Hungary 2 University of Pisa, Department of Information Engineering Work partially funded by the APIS Project of EDA IGARSS 2011, Vancouver, Canada
  • 2. Content 1 Introduction 2 Multiframe Marked Point Process Model Model elements and configuration energy Optimization 3 Experiments 4 Future steps and conclusions Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 2 / 19
  • 3. Introduction Content 1 Introduction 2 Multiframe Marked Point Process Model Model elements and configuration energy Optimization 3 Experiments 4 Future steps and conclusions Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 3 / 19
  • 4. Introduction Introduction Extracting ship scattering centers in airborne Inverse Synthetic Aperture Radar (ISAR) image sequences Framework: “Array Passive ISAR Adaptive Processing” (APIS) Project of EDA ISAR images in Automatic Target Recognition (ATR) systems applicable where other imaging techniques (e.g. SAR) fail post processing step after detection & imaging frames have different quality parameters (e.g. image focus) Goals: Measuring relevant features for target identification and behaviour analysis Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 4 / 19
  • 5. Introduction Proposed approach Robust multi-frame technique, integrating the noisy image information with prior constraints of target shape persistency and smooth motion. Multiframe Marked Point Process model Input: ISAR image sequence of the detected target Output: center line segment parameters of the target in each frame length and orientation positions of permanent characteristic feature points Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 5 / 19
  • 6. Multiframe Marked Point Process Model Content 1 Introduction 2 Multiframe Marked Point Process Model Model elements and configuration energy Optimization 3 Experiments 4 Future steps and conclusions Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 6 / 19
  • 7. Multiframe Marked Point Process Model Model elements and configuration energy Configuration model: notations Observation: n-frame-long ISAR image sequence S: joint pixel lattice of the ISAR frames, s ∈ S: a single pixel Bt : binarized input image observed at time frame t ∈ {1, 2, . . . , n} Bt (s) ∈ {0, 1}: value of pixel s in Bt ut ∈ H: a target candidate in frame t Goal: extract a sequence of objects: ω = {u1 , u2 , . . . , un } ∈ H n Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 7 / 19
  • 8. Multiframe Marked Point Process Model Model elements and configuration energy Target modeling in a single ISAR frame Parameters describing a target u: c(u) = [x (u), y (u)] center pixel, l(u) length and θ(u) orientation Misalignment problem periodicity of ISAR images both in horizontal and vertical directions target may break into two/four pieces using a duplicated mosaic image Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 8 / 19
  • 9. Multiframe Marked Point Process Model Model elements and configuration energy Fm MPP energy function Object sequence or configuration: ω = {u1 , u2 , . . . , un } Configuration energy: n n−1 ΦD (ω) = AD (ut ) +γ · I (ut , ut+1 ) t=1 t=1 AD (ut ): D-data dependent unary object potential I (ut , ut+1 ) prior interaction potential function between objects of consecutive frames Maximum Likelihood (ML) configuration estimate: ω = argmin ΦD (ω) ω∈H n Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 9 / 19
  • 10. Multiframe Marked Point Process Model Model elements and configuration energy Data term Unary potentials: evaluation of proposed ship candidates in independent frames Calculation:   1 AD (ut ) = Q  Bt (s) + (1 − Bt (s)) Area{Rut ∪ Tut } s∈Rut s∈Tut Q(ζ) : R → [−1, 1]: a non-linear monotonously decreasing function Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 10 / 19
  • 11. Multiframe Marked Point Process Model Model elements and configuration energy Interaction potentials Key role: enforcing prior geometrical constraints. persistent frame rate → small object displacements between two consecutive frames Feature: length and angle difference (center is not relevant) I (ut , ut+1 ) = δθ · |θ (ut ) − θ (ut+1 )| + δl · |l (ut ) − l (ut+1 ) | Penalized configuration × √ Favored configuration Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 11 / 19
  • 12. Multiframe Marked Point Process Model Optimization Optimization: iterative stochastic algorithms The algorithm 1 Start with a frame-by-frame initialization process Hough transform based line estimation in each binarized frame Bt , t = 1...n 2 Iterate object perturbation and acceptance steps till convergence is obtained in the extracted object sequence Object perturbation: for each t we propose an object u ∗ which is the random perturbation of ut−1 OR ut OR ut+1 Acceptance: we accept or reject a move replacing ut width u ∗ Important properties: Acceptance: inverse approach considering simultaneously data and prior features Stochastic process both for object perturbation and acceptance (unlike in conventional hypothesis generation-acceptance techniques) Simulated annealing framework to ensure convergence Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 12 / 19
  • 13. Multiframe Marked Point Process Model Optimization Optimization: iterative stochastic algorithms The algorithm 1 Start with a frame-by-frame initialization process Hough transform based line estimation in each binarized frame Bt , t = 1...n 2 Iterate object perturbation and acceptance steps till convergence is obtained in the extracted object sequence Object perturbation: for each t we propose an object u ∗ which is the random perturbation of ut−1 OR ut OR ut+1 Acceptance: we accept or reject a move replacing ut width u ∗ Important properties: Acceptance: inverse approach considering simultaneously data and prior features Stochastic process both for object perturbation and acceptance (unlike in conventional hypothesis generation-acceptance techniques) Simulated annealing framework to ensure convergence Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 12 / 19
  • 14. Multiframe Marked Point Process Model Optimization Target identification Permanent scatterer extraction and counting Permanent scatterer responses: characteristic target features high false/missing alarm rate in the individual frames (>50%) histograming technique for extracting the permanent scatters Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 13 / 19
  • 15. Experiments Content 1 Introduction 2 Multiframe Marked Point Process Model Model elements and configuration energy Optimization 3 Experiments 4 Future steps and conclusions Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 14 / 19
  • 16. Experiments Experiments - qualitative results Center alignment and target line extraction results Top: input sequence. Center: frame-by-frame detection. Bottom: detection by the proposed Fm MPP model Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 15 / 19
  • 17. Experiments Experiments - quantitative results Test sequences: four airborne ISAR image sequences (each has 15-40 frames) different ship targets. Error measure: n E ({ut }, {utgt }) = |x(ut ) − x(utgt )| + |y(ut ) − y(utgt )|+ t=1 + |l(ut ) − l(utgt )| + |θ(ut ) − θ(utgt )| Sequence Frames Init Err. Fm MPP Err. Ship 1 13 52.0 7.5 Ship 2 13 67.1 37.8 Ship 3 13 17.2 12.8 Ship 4 54 43.7 12.6 Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 16 / 19
  • 18. Future steps and conclusions Content 1 Introduction 2 Multiframe Marked Point Process Model Model elements and configuration energy Optimization 3 Experiments 4 Future steps and conclusions Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 17 / 19
  • 19. Future steps and conclusions Generalization for various objects Identifying Airplanes in ISAR sequences Cross shaped model Shadowed wing Result by the two step process Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 18 / 19
  • 20. Future steps and conclusions Conclusions Detecting and featuring ship/airplane targets in ISAR image sequences through energy minimization Proposed Multi-frame Marked Point Process schema advantages versus a frame-by-frame direct detection technique Towards target classification permanent scatterer detection algorithm based on histograming Benedek & Martorella (SZTAKI, CNIT) Target Extraction in ISAR Image Sequences 28 July 2011 19 / 19