Automatic Identification of Ice Layers in Radar Echograms David Crandall, Jerome Mitchell, Geoffrey C. Fox School of Informatics and Computing Indiana.

Slides:



Advertisements
Similar presentations
Bayesian Belief Propagation
Advertisements

Various Regularization Methods in Computer Vision Min-Gyu Park Computer Vision Lab. School of Information and Communications GIST.
The Shape Boltzmann Machine S. M. Ali Eslami Nicolas Heess John Winn CVPR 2012 Providence, Rhode Island A Strong Model of Object Shape.
Lecture 07 Segmentation Lecture 07 Segmentation Mata kuliah: T Computer Vision Tahun: 2010.
Real-Time Human Pose Recognition in Parts from Single Depth Images Presented by: Mohammad A. Gowayyed.
Proportion Priors for Image Sequence Segmentation Claudia Nieuwenhuis, etc. ICCV 2013 Oral.
Introduction to Belief Propagation and its Generalizations. Max Welling Donald Bren School of Information and Computer and Science University of California.
Qualifying Exam: Contour Grouping Vida Movahedi Supervisor: James Elder Supervisory Committee: Minas Spetsakis, Jeff Edmonds York University Summer 2009.
EE462 MLCV Lecture Introduction of Graphical Models Markov Random Fields Segmentation Tae-Kyun Kim 1.
Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.
Uncertainty Representation. Gaussian Distribution variance Standard deviation.
Active Contour Models (Snakes)
A Survey of Techniques for Detecting Layers in Polar Radar Imagery Jerome E. Mitchell, David J. Crandall, Geoffrey C. Fox, and John D. Paden.
Yung-Lin Huang, Yi-Nung Liu, and Shao-Yi Chien Media IC and System Lab Graduate Institute of Networking and Multimedia National Taiwan University Signal.
1 Graphical Models in Data Assimilation Problems Alexander Ihler UC Irvine Collaborators: Sergey Kirshner Andrew Robertson Padhraic Smyth.
Region Segmentation. Find sets of pixels, such that All pixels in region i satisfy some constraint of similarity.
Abstract We present a model of curvilinear grouping using piecewise linear representations of contours and a conditional random field to capture continuity.
Particle filters (continued…). Recall Particle filters –Track state sequence x i given the measurements ( y 0, y 1, …., y i ) –Non-linear dynamics –Non-linear.
Abstract Extracting a matte by previous approaches require the input image to be pre-segmented into three regions (trimap). This pre-segmentation based.
Lecture 17: Parts-based models and context CS6670: Computer Vision Noah Snavely.
Understanding Belief Propagation and its Applications Dan Yuan June 2004.
An Iterative Optimization Approach for Unified Image Segmentation and Matting Hello everyone, my name is Jue Wang, I’m glad to be here to present our paper.
CS292 Computational Vision and Language Segmentation and Region Detection.
Performance Evaluation of Grouping Algorithms Vida Movahedi Elder Lab - Centre for Vision Research York University Spring 2009.
Reconstructing Relief Surfaces George Vogiatzis, Philip Torr, Steven Seitz and Roberto Cipolla BMVC 2004.
Layer-finding in Radar Echograms using Probabilistic Graphical Models David Crandall Geoffrey C. Fox School of Informatics and Computing Indiana University,
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields Yong-Joong Kim Dept. of Computer Science Yonsei.
Techniques for Estimating Layers from Polar Radar Imagery Jerome E. Mitchell, Geoffrey C. Fox, and David J. Crandall :: CReSIS NSF Site Visit :: School.
October 14, 2014Computer Vision Lecture 11: Image Segmentation I 1Contours How should we represent contours? A good contour representation should meet.
SVCL Automatic detection of object based Region-of-Interest for image compression Sunhyoung Han.
Perception Introduction Pattern Recognition Image Formation
MRFs and Segmentation with Graph Cuts Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 02/24/10.
City University of Hong Kong 18 th Intl. Conf. Pattern Recognition Self-Validated and Spatially Coherent Clustering with NS-MRF and Graph Cuts Wei Feng.
Interactive Shortest Path Part 3 An Image Segmentation Technique Jonathan-Lee Jones.
Automated Detection and Classification Models SAR Automatic Target Recognition Proposal J.Bell, Y. Petillot.
Experiments Test different parking lot images captured in different luminance conditions The test samples include 1300 available parking spaces and 1500.
Supervised Learning of Edges and Object Boundaries Piotr Dollár Zhuowen Tu Serge Belongie.
G52IVG, School of Computer Science, University of Nottingham 1 Edge Detection and Image Segmentation.
28 February, 2003University of Glasgow1 Cluster Variation Method and Probabilistic Image Processing -- Loopy Belief Propagation -- Kazuyuki Tanaka Graduate.
Copyright © 2010 Siemens Medical Solutions USA, Inc. All rights reserved. Hierarchical Segmentation and Identification of Thoracic Vertebra Using Learning-based.
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
Image Segmentation and Edge Detection Digital Image Processing Instructor: Dr. Cheng-Chien LiuCheng-Chien Liu Department of Earth Sciences National Cheng.
Fields of Experts: A Framework for Learning Image Priors (Mon) Young Ki Baik, Computer Vision Lab.
Automatic Locating of Anthropometric Landmarks on 3D Human Models
Tell Me What You See and I will Show You Where It Is Jia Xu 1 Alexander G. Schwing 2 Raquel Urtasun 2,3 1 University of Wisconsin-Madison 2 University.
Exploring Learning Algorithms for Layer Identification from Polar Radar Imagery Tori Wilborn (Elizabeth City State University), Omar Owens (Winston Salam.
Approximate Inference: Decomposition Methods with Applications to Computer Vision Kyomin Jung ( KAIST ) Joint work with Pushmeet Kohli (Microsoft Research)
Markov Random Fields & Conditional Random Fields
The rise of the planet’s temperature has a very negative impact on the subsurface dynamics of Earth’s Polar Regions. Analyzing the polar subsurface is.
Efficient Belief Propagation for Image Restoration Qi Zhao Mar.22,2006.
Layer-finding in Radar Echograms using Probabilistic Graphical Models David Crandall Geoffrey C. Fox School of Informatics and Computing Indiana University,
Lecture 04 Edge Detection Lecture 04 Edge Detection Mata kuliah: T Computer Vision Tahun: 2010.
Markov Networks: Theory and Applications Ying Wu Electrical Engineering and Computer Science Northwestern University Evanston, IL 60208
Jianchao Yang, John Wright, Thomas Huang, Yi Ma CVPR 2008 Image Super-Resolution as Sparse Representation of Raw Image Patches.
Gaussian Conditional Random Field Network for Semantic Segmentation
ICPR2004 (24 July, 2004, Cambridge) 1 Probabilistic image processing based on the Q-Ising model by means of the mean- field method and loopy belief propagation.
Course : T Computer Vision
Statistical-Mechanical Approach to Probabilistic Image Processing -- Loopy Belief Propagation and Advanced Mean-Field Method -- Kazuyuki Tanaka and Noriko.
Sublinear Computational Time Modeling in Statistical Machine Learning Theory for Markov Random Fields Kazuyuki Tanaka GSIS, Tohoku University, Sendai,
An Improved Probabilistic Graphical Model for the Detection of Internal Layers from Polar Radar Imagery Jerome E. Mitchell 2013 NASA Earth and Space Science.
LOCUS: Learning Object Classes with Unsupervised Segmentation
Nonparametric Semantic Segmentation
Mean Shift Segmentation
Dynamical Statistical Shape Priors for Level Set Based Tracking
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Where did we stop? The Bayes decision rule guarantees an optimal classification… … But it requires the knowledge of P(ci|x) (or p(x|ci) and P(ci)) We.
“Traditional” image segmentation
Jerome E. Mitchell 2013 NASA Earth and Space Science Fellow
Subglacial bed topography using machine learning and geostatistical analysis applied to 2D and 3D radar sounding John Paden1, Victor Berger1, Mohanad Al-Ibadi1,
Presentation transcript:

Automatic Identification of Ice Layers in Radar Echograms David Crandall, Jerome Mitchell, Geoffrey C. Fox School of Informatics and Computing Indiana University, USA John D. Paden Center for Remote Sensing of Ice Sheets University of Kansas, USA

Ice sheet radar echograms Distance along flight line Distance below aircraft

Ice sheet radar echograms Bedrock Ice Distance along flight line Distance below aircraft Air

Related work Subsurface imaging – [Turk2011], [Allen2012], … Buried object detection – [Trucco1999], [Gader2001], [Frigui2005], … Layer finding in ground-penetrating echograms – [Freeman2010], [Ferro2011], [Sime2012], [Panton2013], … General-purpose image segmentation – [Haralick1985], [Kass1998], [Shi2000], [Felzenszwalb2004], …

Lessons from Computer Vision: Pipelined approaches Edge detection Group edge pixels into lines and circles Assemble lines & circles into objects

Lessons from Computer Vision: Pipelined approaches Edge detection Group edge pixels into line and curve fragments Grow line and curve fragments Group nearby line and curve fragments together Break apart complex fragments Group into circles and curves Filter out small isolated shapes Assemble lines & circles into objects

Lessons from Computer Vision: “Unified” approaches Use features derived from raw image data Consider all evidence together, at the same time – Probabilistic frameworks can naturally model uncertainty and combine weak evidence – Probabilistic graphical models provide framework for making inference tractable (see e.g. Koller 2009) Set parameters and thresholds automatically, by learning from training data

Unified inference example Left eyeRight eyeNose ChinRight mouthLeft mouth Graphical model inference Graphical model inference Marginal on Nose From: Crandall, Felszenswalb, Huttenlocher, CVPR 2005.

Sample “bicycle” localizations Correct detections: False positives:

Correct detections: False positives: Sample “TV/monitor” detections

Tiered segmentation Layer-finding is a tiered segmentation problem [Felzenszwalb2010] – Label each pixel with one of [1, K+1], under the constraint that if y < y ’, label of (x, y) ≤ label of (x, y’) Equivalently, find K boundaries in each column – Let denote the row indices of the K region boundaries in column i – Goal is to find labeling of whole image, LiLi li1li1 li2li2 li3li3li3li Crandall, Fox, Paden, International Conference on Pattern Recognition (ICPR), 2012.

Probabilistic formulation Goal is to find most-likely labeling given image I, Likelihood term models how well labeling agrees with image Prior term models how well labeling agrees with typical ice layer properties

Prior term Prior encourages smooth, non-crossing boundaries Zero-mean Gaussian penalizes discontinuities in layer boundaries across columns Repulsive term prevents boundary crossings; is 0 if and uniform otherwise li1li1 li2li2 li3li3li3li3 l i

Likelihood term Likelihood term encourages labels to coincide with layer boundary features (e.g. edges) – Learn a single-column appearance template T k consisting of Gaussians at each position p, with – Also learn a simple background model, with – Then likelihood for each column is,

Efficient inference Finding L that maximizes P(L | I) involves inference on a Markov Random Field – Simplify problem by solving each row of MRF in succession, using the Viterbi algorithm – Naïve Viterbi requires O(Kmn 2 ) time, for m x n echogram with K layer boundaries – Can use min-convolutions to speed up Viterbi (because of the Gaussian prior), reducing time to O(Kmn) [Crandall2008] – Very fast: ~100ms per image

Experimental results Tested finding surface and bedrock layer boundaries, with 827 echograms from Antarctica – From Multichannel Coherent Radar Depth Sounder system in 2009 NASA Operation Ice Bridge [Allen12] – About 24,810 km of flight data – Split into equal-size training and test datasets

Original echogram Automatic labelingGround truth

Original echogram Automatic labelingGround truth

Original echogram Automatic labelingGround truth

Original echogram Automatic labelingGround truth

User interaction

* *

* * Modify P(L) such that this label has probability 1

User interaction * * Modify P(L) such that this label has probability 1

Sampling from the posterior Instead of maximizing P(L|I), sample from it

Quantitative results Comparison against simple baselines: – Fixed simply draws a straight line at mean layer depth – AppearOnly maximizes likelihood term only

Quantitative results Comparison against simple baselines: – Fixed simply draws a straight line at mean layer depth – AppearOnly maximizes likelihood term only – Further improvement with human interaction:

Internal layer-finding The above framework applies naturally to internal layer-finding, with one crucial problem – Inference on the statistical model is NP-hard! Two potential solutions – Break the problem into a sequence of smaller problems – Use an approximation algorithm to do the optimization; we use loopy belief propagation

Internal layer-finding Sequential approach: [Mitchell13] Approximate inference: What’s the right evaluation metric?

Summary and Future work We present a probabilistic technique for ice sheet layer-finding from radar echograms – Inference is robust to noise and very fast – Parameters can be learned from training data – Easily include evidence from external sources Ongoing and future work – How to evaluate quality of labeling? – Explicitly modeling sources of noise in radar images – Full 3d inference: Solving for all layers in 3d, using data from all flight tracks as well as cores, etc.

More information available at: This work was supported in part by: Thanks!