Automated Detection and Classification Models SAR Automatic Target Recognition Proposal J.Bell, Y. Petillot.

Slides:



Advertisements
Similar presentations
Applications of one-class classification
Advertisements

Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Interactive Evolutionary Computation Review of Applications Praminda Caleb-Solly Intelligent Computer Systems Centre University of the West of England.
Automated Detection and Classification Models A Model-Based Approach to the Detection and Classification of Mines in Side-scan Sonar S.Reed,
Segmentation In The Field Medicine Advanced Image Processing course By: Ibrahim Jubran Presented To: Prof. Hagit Hel-Or.
Texture Segmentation Based on Voting of Blocks, Bayesian Flooding and Region Merging C. Panagiotakis (1), I. Grinias (2) and G. Tziritas (3)
Object Detection at Different Resolutions in Archaeological Sidescan Sonar Images Louis Atallah and Changjing Shang Institute of Informatics The British.
Localization of Piled Boxes by Means of the Hough Transform Dimitrios Katsoulas Institute for Pattern Recognition and Image Processing University of Freiburg.
Relevance Feedback Content-Based Image Retrieval Using Query Distribution Estimation Based on Maximum Entropy Principle Irwin King and Zhong Jin Nov
Content Based Image Clustering and Image Retrieval Using Multiple Instance Learning Using Multiple Instance Learning Xin Chen Advisor: Chengcui Zhang Department.
CS292 Computational Vision and Language Pattern Recognition and Classification.
Pattern Classification All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John.
A Study of Approaches for Object Recognition
1 An Adaptive Nearest Neighbor Classification Algorithm for Data Streams Yan-Nei Law & Carlo Zaniolo University of California, Los Angeles PKDD, Porto,
Rodent Behavior Analysis Tom Henderson Vision Based Behavior Analysis Universitaet Karlsruhe (TH) 12 November /9.
Relevance Feedback based on Parameter Estimation of Target Distribution K. C. Sia and Irwin King Department of Computer Science & Engineering The Chinese.
Prénom Nom Document Analysis: Data Analysis and Clustering Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2005 with a lot of slides stolen from Steve Seitz and.
Evaluating the Quality of Image Synthesis and Analysis Techniques Matthew O. Ward Computer Science Department Worcester Polytechnic Institute.
E.G.M. PetrakisTexture1 Repeative patterns of local variations of intensity on a surface –texture pattern: texel Texels: similar shape, intensity distribution.
Active Appearance Models Suppose we have a statistical appearance model –Trained from sets of examples How do we use it to interpret new images? Use an.
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2006 with a lot of slides stolen from Steve Seitz and.
1 Probabilistic Formulation for Skin Detection Sanun Srisuk Seminar I.
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
Jacinto C. Nascimento, Member, IEEE, and Jorge S. Marques
Relevance Feedback Content-Based Image Retrieval Using Query Distribution Estimation Based on Maximum Entropy Principle Irwin King and Zhong Jin The Chinese.
KDD for Science Data Analysis Issues and Examples.
Learning to classify the visual dynamics of a scene Nicoletta Noceti Università degli Studi di Genova Corso di Dottorato.
Multi-resolution Arc Segmentation: Algorithms and Performance Evaluation Jiqiang Song Jan. 12 th, 2004.
MULTITEMP 2005 – Biloxi, Mississippi, USA, May 16-18, 2005 Remote Sensing Laboratory Dept. of Information and Communication Technology University of Trento.
Competence Centre on Information Extraction and Image Understanding for Earth Observation Matteo Soccorsi (1) and Mihai Datcu (1,2) A Complex GMRF for.
Gwangju Institute of Science and Technology Intelligent Design and Graphics Laboratory Multi-scale tensor voting for feature extraction from unstructured.
Bala Lakshminarayanan AUTOMATIC TARGET RECOGNITION April 1, 2004.
EADS DS / SDC LTIS Page 1 7 th CNES/DLR Workshop on Information Extraction and Scene Understanding for Meter Resolution Image – 29/03/07 - Oberpfaffenhofen.
Environmental Remote Sensing Lecture 5: Image Classification " Purpose: – categorising data – data abstraction / simplification – data interpretation –
1. Introduction Motion Segmentation The Affine Motion Model Contour Extraction & Shape Estimation Recursive Shape Estimation & Motion Estimation Occlusion.
Hierarchical Distributed Genetic Algorithm for Image Segmentation Hanchuan Peng, Fuhui Long*, Zheru Chi, and Wanshi Siu {fhlong, phc,
Lecture 3: Region Based Vision
INDEPENDENT COMPONENT ANALYSIS OF TEXTURES based on the article R.Manduchi, J. Portilla, ICA of Textures, The Proc. of the 7 th IEEE Int. Conf. On Comp.
Automated Face Detection Peter Brende David Black-Schaffer Veni Bourakov.
Intelligent Vision Systems ENT 496 Object Shape Identification and Representation Hema C.R. Lecture 7.
Automated Detection and Classification Models SAR Automatic Target Recognition Proposal J.Bell, Y. Petillot.
Forward-Scan Sonar Tomographic Reconstruction PHD Filter Multiple Target Tracking Bayesian Multiple Target Tracking in Forward Scan Sonar.
MURI: Integrated Fusion, Performance Prediction, and Sensor Management for Automatic Target Exploitation 1 Dynamic Sensor Resource Management for ATE MURI.
AUTOMATIC TARGET RECOGNITION OF CIVILIAN TARGETS September 28 th, 2004 Bala Lakshminarayanan.
Features-based Object Recognition P. Moreels, P. Perona California Institute of Technology.
Xu Huaping, Wang Wei, Liu Xianghua Beihang University, China.
Authors: Rupert Paget, John Homer, and David Crisp
CS654: Digital Image Analysis Lecture 25: Hough Transform Slide credits: Guillermo Sapiro, Mubarak Shah, Derek Hoiem.
Digital Image Processing
Human pose recognition from depth image MS Research Cambridge.
Face Detection Using Large Margin Classifiers Ming-Hsuan Yang Dan Roth Narendra Ahuja Presented by Kiang “Sean” Zhou Beckman Institute University of Illinois.
Competence Centre on Information Extraction and Image Understanding for Earth Observation 29th March 2007 Category - based Semantic Search Engine 1 Mihai.
1Ellen L. Walker Category Recognition Associating information extracted from images with categories (classes) of objects Requires prior knowledge about.
Radiometric Normalization Spring 2009 Ben-Gurion University of the Negev.
Ivica Dimitrovski 1, Dragi Kocev 2, Suzana Loskovska 1, Sašo Džeroski 2 1 Faculty of Electrical Engineering and Information Technologies, Department of.
Inference in generative models of images and video John Winn MSR Cambridge May 2004.
Supervisor: Nakhmani Arie Semester: Winter 2007 Target Recognition Harmatz Isca.
GENDER AND AGE RECOGNITION FOR VIDEO ANALYTICS SOLUTION PRESENTED BY: SUBHASH REDDY JOLAPURAM.
Introduction to Related Papers of Vessel Segmentation Methods Advisor : Ku-Yaw Chang Student : Wei-Lu Lin 2015/1/7.
Automated Detection and Classification Models SAR Automatic Target Recognition Proposal J.Bell, Y. Petillot.
Identifying “Best Bet” Web Search Results by Mining Past User Behavior Author: Eugene Agichtein, Zijian Zheng (Microsoft Research) Source: KDD2006 Reporter:
Cell Segmentation in Microscopy Imagery Using a Bag of Local Bayesian Classifiers Zhaozheng Yin RI/CMU, Fall 2009.
What Is Cluster Analysis?
Classification techniques
Fast Preprocessing for Robust Face Sketch Synthesis
A weight-incorporated similarity-based clustering ensemble method based on swarm intelligence Yue Ming NJIT#:
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Presentation transcript:

Automated Detection and Classification Models SAR Automatic Target Recognition Proposal J.Bell, Y. Petillot

Automated Detection and Classification Models Contents Background ATR on SAR ATR on Sonar Supporting Technologies Initial results on SAR Way forward

Automated Detection and Classification Models ATR approaches

Automated Detection and Classification Models Unsupervised Techniques Future automated systems will require all available information (navigation data, image processing models.etc.) to be fused.

Automated Detection and Classification Models CAD/CAC Proposal Detect MLO’s (MRF-based Model) Fuse Other Views Extract Highlight/Shadow (CSS Model) Classify Object (Dempster-Shafer) False Alarm? Positive Classification? 12YES NO MINE REMOVE FALSE ALARM

Automated Detection and Classification Models The Sonar Process Sonar images represent the time of flight of the sound rather than distance. Objects appear as a highlight/shadow pair in the sonar image.

Automated Detection and Classification Models The Detection Model A Markov Random Field(MRF) model framework is used. MRF models operate well on noisy images. A priori information can be easily incorporated. They are used to retrieve the underlying label field (e.g shadow/non-shadow)

Automated Detection and Classification Models Basic MRF Theory A pixel’s class is determined by 2 terms: –The probability of being drawn from each classes distribution. –The classes of its neighbouring pixels.

Automated Detection and Classification Models Incorporating A Priori Info Object-highlight regions appear as small, dense clusters. Most highlight regions have an accompanying shadow region. Segment by minimising:

Automated Detection and Classification Models Initial Detection Results Initial Results Good. Model sometimes detects false alarms due to clutter such as the surface return – requires more analysis! DETECTED OBJECT

Automated Detection and Classification Models Object Feature Extraction The object’s shadow is often extracted for classification. The shadow region is generally more reliable than the object’s highlight region for classification. Most shadow extraction models operate well on flat seafloors but give poor results on complex seafloors.

Automated Detection and Classification Models The CSS Model 2 Statistical Snakes segment the mugshot image into 3 regions : object-highlight, object-shadow and background. A priori information is modelled: The highlight is brighter than the shadow An object’s shadow region can only be as wide as its highlight region.

Automated Detection and Classification Models CSS Results CSS Model Standard Model

Automated Detection and Classification Models The Combined Model Objects detected by MRF model are put through the CSS model. The CSS snakes are initialised using the label field from the detection result. This ensures a confident initialisation each time. The CSS can detect MANY of the false alarms. False alarms without 3 distinct regions ensure the snakes rapidly expand, identifying the detection as a false alarm. Navigation info is also used to produce height information which can also remove false alarms.

Automated Detection and Classification Models Results

Results 2

Automated Detection and Classification Models Results 3

Automated Detection and Classification Models Result 4

Automated Detection and Classification Models BP ’02 Results The combined detection/CSS model was run on 200 BP’02 data files containing 70 objects. 80% of the objects where detected and features extracted(for classification) false alarms per image. The surface return resulted in some of the objects not being detected. Dealing with this would produce a detection rate of ~ 91%.

Automated Detection and Classification Models Object Classification The extracted object’s shadow can be used for classification. We extend the classic mine/not-mine classification to provide shape and dimension information. The non-linear nature of the shadow-forming process ensures finding relevant invariant features is difficult. Shadows from the same object

Automated Detection and Classification Models Modelling the Sonar Process Mines can be approximated as simple shapes – cylinders, spheres and truncated cones. Using Nav data to slant-range correct, we can generate synthetic shadows under the same sonar conditions as the object was detected. Simple line-of-sight sonar simulator. Very fast.

Automated Detection and Classification Models Comparing the Shadows Iterative Technique is required to find best fit. Parameter space limited by considering highlight and shadow length. Synthetic and real shadow compared using the Hausdorff Distance. It measures the mismatch of the 2 shapes. HAUSDORFF DISTANCE

Automated Detection and Classification Models Incorporating Knowledge As the technique is model-based, information on likely mine dimensions can be incorporated. Limited information from the highlight region can also be used to distinguish between the tested classes. We obtain an overall membership function for each class.

Automated Detection and Classification Models The Classification Decision A decision could be made by simply defining a ‘Positive Classification Threshold’. This is a ‘hard’ decision and non-changeable. The ‘lawnmower’ nature of Sidescan surveys ensures the same object is often viewed multiple times. The model should ideally be capable of multi-view classification. We use DEMPSTER-SHAFER theory.

Automated Detection and Classification Models Mono-view Results Dempster-Shafer allocates a BELIEF to each class. Unlike Bayesian or Fuzzy methods, D-S theory can also consider union of classes. Bel(cyl)=0.83 Bel(sph)=0.0 Bel(cone)=0.0 Bel(clutter)=0.08 Bel(cyl)=0.0 Bel(sph)=0.303 Bel(cone)=0.45 Bel(clutter)=0.045 Bel(cyl)=0.42 Bel(sph)=0.0 Bel(cone)=0.0 Bel(clutter)=0.46

Automated Detection and Classification Models Mono-view Results Model was tested on 66 mugshots containing cylinders, Spheres, Truncated cones and clutter objects.

Automated Detection and Classification Models Multi-view Analysis Dempster-Shafer allows results from multiple views to be fused. Mono-Image BeliefFused Belief ObjCylSphConeCluttObjs Fused CylSphConeClutt , ,2, ,2,3,

Automated Detection and Classification Models Multi-Image Analysis Mono-Image BeliefFused Belief ObjCylSphConeCluttObjs Fused CylSphConeClutt , ,6, ,6,7,

Automated Detection and Classification Models Future Research The current detection model considers objects as a Highlight/Shadow pair. An object can also be considered as a discrepancy in the surrounding texture field.

Automated Detection and Classification Models Conclusions Automated Detection/Feature Extraction model has been developed and tested on a large amount of data. Good Results obtained, improvements expected when surface returns removed. Classification model uses a simple sonar simulator and Dempster-Shafer theory to classify the objects. Extends mine/not-mine classification to provide shape and size information. Future research is focusing on texture segmentation to complement the current work.

Automated Detection and Classification Models Acknowledgements We would like to thank the following institutions for their support and for providing data: DRDC–Atlantic, Canada Saclant Centre, Italy GESMA, France