12 th International Fall Workshop VISION, MODELING, AND VISUALIZATION 2007 November 7-9, 2007 Saarbrücken, Germany Estimating Natural Activity by Fitting.

Slides:



Advertisements
Similar presentations
Multiprocessor Scheduling
Advertisements

Institute for vision and graphics university of siegen, germany High-Level User Interfaces for Transfer Function Design with Semantics Christof Rezk Salama.
Technische Universität Ilmenau CCSW 2013 Sander Wozniak
Matthias Wimmer, Bernd Radig, Michael Beetz Chair for Image Understanding Computer Science TU München, Germany A Person and Context.
Active Appearance Models
Model-based Image Interpretation with Application to Facial Expression Recognition Matthias Wimmer
A Methodology for Simultaneous Retrieval of Ice and Liquid Water Cloud Properties O. Sourdeval 1, L. C.-Labonnote 2, A. J. Baran 3, G. Brogniez 2 1 – Institute.
Surface Simplification Using Quadric Error Metrics Speaker: Fengwei Zhang September
Technische Universität München Face Model Fitting based on Machine Learning from Multi-band Images of Facial Components Institute for Informatics Technische.
November 12, 2013Computer Vision Lecture 12: Texture 1Signature Another popular method of representing shape is called the signature. In order to compute.
Matthias Wimmer, Ursula Zucker and Bernd Radig Chair for Image Understanding Computer Science Technische Universität München { wimmerm, zucker, radig
Christoph F. Eick Questions and Topics Review Nov. 22, Assume you have to do feature selection for a classification task. What are the characteristics.
Simulation of Fibrous Scaffold Optimal Distribution by Genetic Algorithm Presentation : D. Semnani ICSIP 2009, Amsterdam Isfahan University of Technology.
THE AUSTRALIAN NATIONAL UNIVERSITY Infrasound Technology Workshop, November 2007, Tokyo, Japan OPTIMUM ARRAY DESIGN FOR THE DETECTION OF DISTANT.
Eyes for Relighting Extracting environment maps for use in integrating and relighting scenes (Noshino and Nayar)
The perception of Shading and Reflectance E.H. Adelson, A.P. Pentland Presenter: Stefan Zickler.
3D Shape Histograms for Similarity Search and Classification in Spatial Databases. Mihael Ankerst,Gabi Kastenmuller, Hans-Peter-Kriegel,Thomas Seidl Univ.
Multiple View Based 3D Object Classification Using Ensemble Learning of Local Subspaces ( ThBT4.3 ) Jianing Wu, Kazuhiro Fukui
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Presenter : Shih-Tung Huang Tsung-Cheng Lin Kuan-Fu Kuo 2015/6/15 EICE team Model-Level Debugging of Embedded Real-Time Systems Wolfgang Haberl, Markus.
3D Mapping Robots Intelligent Robotics School of Computer Science Jeremy Wyatt James Walker.
Parametric Inference.
Basic Concepts and Definitions Vector and Function Space. A finite or an infinite dimensional linear vector/function space described with set of non-unique.
Evaluating the Quality of Image Synthesis and Analysis Techniques Matthew O. Ward Computer Science Department Worcester Polytechnic Institute.
Force Directed Algorithm Adel Alshayji 4/28/2005.
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.
Mario Vodisek 1 HEINZ NIXDORF INSTITUTE University of Paderborn Algorithms and Complexity Erasure Codes for Reading and Writing Mario Vodisek ( joint work.
Motion from normal flow. Optical flow difficulties The aperture problemDepth discontinuities.
Chair for Computer Aided Medical Procedures & Augmented Reality Department of Computer Science | Technische Universität München Chair for Computer Aided.
Matthias Wimmer, Bernd Radig, Michael Beetz Chair for Image Understanding Computer Science Technische Universität München Adaptive.
Matthias Wimmer, Sylvia Pietzsch, Freek Stulp and Bernd Radig Chair for Image Understanding Institute for Computer Science Technische Universität München.
Optimization of Gamma Knife Radiosurgery Michael Ferris University of Wisconsin, Computer Sciences David Shepard University of Maryland School of Medicine.
Jinhui Tang †, Shuicheng Yan †, Richang Hong †, Guo-Jun Qi ‡, Tat-Seng Chua † † National University of Singapore ‡ University of Illinois at Urbana-Champaign.
HMM-BASED PSEUDO-CLEAN SPEECH SYNTHESIS FOR SPLICE ALGORITHM Jun Du, Yu Hu, Li-Rong Dai, Ren-Hua Wang Wen-Yi Chu Department of Computer Science & Information.
Summarized by Soo-Jin Kim
„Bandwidth Extension of Speech Signals“ 2nd Workshop on Wideband Speech Quality in Terminals and Networks: Assessment and Prediction 22nd and 23rd June.
Domain testing Tor Stålhane. Domain testing revisited We have earlier looked at domain testing as a simple strategy for selecting test cases. We will.
Multimodal Interaction Dr. Mike Spann
1/20 Obtaining Shape from Scanning Electron Microscope Using Hopfield Neural Network Yuji Iwahori 1, Haruki Kawanaka 1, Shinji Fukui 2 and Kenji Funahashi.
Face Model Fitting with Generic, Group-specific, and Person- specific Objective Functions Chair for Image Understanding and Knowledge-based Systems Institute.
October 14, 2014Computer Vision Lecture 11: Image Segmentation I 1Contours How should we represent contours? A good contour representation should meet.
Improved search for Socially Annotated Data Authors: Nikos Sarkas, Gautam Das, Nick Koudas Presented by: Amanda Cohen Mostafavi.
A Modified Meta-controlled Boltzmann Machine Tran Duc Minh, Le Hai Khoi (*), Junzo Watada (**), Teruyuki Watanabe (***) (*) Institute Of Information Technology-Viet.
Crowdsourcing with Multi- Dimensional Trust Xiangyang Liu 1, He He 2, and John S. Baras 1 1 Institute for Systems Research and Department of Electrical.
Automatic Image Annotation by Using Concept-Sensitive Salient Objects for Image Content Representation Jianping Fan, Yuli Gao, Hangzai Luo, Guangyou Xu.
A survey of different shape analysis techniques 1 A Survey of Different Shape Analysis Techniques -- Huang Nan.
A WEIGHTED CALIBRATION METHOD OF INTERFEROMETRIC SAR DATA Yongfei Mao Maosheng Xiang Lideng Wei Daojing Li Bingchen Zhang Institute of Electronics, Chinese.
Data Mining, ICDM '08. Eighth IEEE International Conference on Duy-Dinh Le National Institute of Informatics Hitotsubashi, Chiyoda-ku Tokyo,
Fast Learning in Networks of Locally-Tuned Processing Units John Moody and Christian J. Darken Yale Computer Science Neural Computation 1, (1989)
Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology 1 A self-organizing map for adaptive processing of structured.
Sylvia Pietzsch Chair for Image Understanding Computer Science Technische Universität München Learning Generic and Person Specific Objective.
Chapter 8. Learning of Gestures by Imitation in a Humanoid Robot in Imitation and Social Learning in Robots, Calinon and Billard. Course: Robots Learning.
Large-Scale Matrix Factorization with Missing Data under Additional Constraints Kaushik Mitra University of Maryland, College Park, MD Sameer Sheoreyy.
Week 21 Order Statistics The order statistics of a set of random variables X 1, X 2,…, X n are the same random variables arranged in increasing order.
Stephan Tschechne Chair for Image Understanding Computer Science Technische Universität München Designing vs. Learning the Objective.
Meta-controlled Boltzmann Machine toward Accelerating the Computation Tran Duc Minh (*), Junzo Watada (**) (*) Institute Of Information Technology-Viet.
Kevin Stevenson AST 4762/5765. What is MCMC?  Random sampling algorithm  Estimates model parameters and their uncertainty  Only samples regions of.
May 2003 SUT Color image segmentation – an innovative approach Amin Fazel May 2003 Sharif University of Technology Course Presentation base on a paper.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching.
CIVET seminar Presentation day: Presenter : Park, GilSoon.
Week 21 Statistical Model A statistical model for some data is a set of distributions, one of which corresponds to the true unknown distribution that produced.
Discrete ABC Based on Similarity for GCP
Multidisciplinary Engineering Senior Design Project P06441 See Through Fog Imaging Preliminary Design Review 05/19/06 Project Sponsor: Dr. Rao Team Members:
Optimization of Gamma Knife Radiosurgery
Dynamical Statistical Shape Priors for Level Set Based Tracking
Morgan Bruns1, Chris Paredis1, and Scott Ferson2
Fitting Curve Models to Edges
Flower Pollination Algorithm
Outline H. Murase, and S. K. Nayar, “Visual learning and recognition of 3-D objects from appearance,” International Journal of Computer Vision, vol. 14,
Visual Recognition of American Sign Language Using Hidden Markov Models 문현구 문현구.
Presentation transcript:

12 th International Fall Workshop VISION, MODELING, AND VISUALIZATION 2007 November 7-9, 2007 Saarbrücken, Germany Estimating Natural Activity by Fitting 3D Models via Learned Objective Functions 1 Faculty of Science and Engineering, Waseda University, Tokyo , Japan 2 Institut für Informatik, Technische Universität München, Garching, Germany 3 Kognitive Neuroinformatik, Universität Bremen, Bremen, Germany Matthias Wimmer 1, Christoph Mayer 2, Freek Stulp 3 and Bernd Radig 2

Natural Activity tactile channel visual channel auditory channel olfactory channel auditory channel visual channel tactile channel olfactory channel

Model-based Image Interpretation Model Describes the image content with the help of a parameter vector p. Objective Function Calculates how well a parameterized model p fits to an image I. Fitting Algorithm Optimizes the objective function and therefore estimates the model that fits the image best.

Objective Functions f(I,p) Splitting the Objective Function to Local Objective Functions Evaluate one objective function per model point. Approximate the model parameters. Evaluation of the Objective Function Along characteristic direction. Often perpendicular to the model.

Traditional Approach Shortcomings:  Requires domain knowledge.  Based on designer’s intuition.  Time-consuming. Manually design the objective function Manually evaluate on test images designed objective function good not good

Ideal Objective Functions P1:Correctness Property: The global minimum corresponds to the best model fit. P2:Uni-modality Property: The objective function has no local extrema. ¬ P1 P1 ¬P2 P2

Learning the Objective Function (1)

Learning the Objective Function (2) Generate further Annotations Annotations in three-dimensional space along characteristic direction One characteristic direction is not sufficient.

Learning the Objective Function (3)

Learning the Objective Function (4) Three characteristic directions in three-dimensional space. Model point is moved along the most important characteristic direction. Characteristic direction with largest angle to the image normal is considered most important.

Learning the Objective Function (5)

Learning the Objective Function (6) Advantages  The loop is removed.  The objective function approximates the ideal objective function.  No domain-dependent knowledge is needed.

Evaluation General approach Uniformly distributed error is applied to models and fitting is performed afterwards. Distances are measured in centimeters. Fraction of models located at a certain distance or better is evaluated. Two objective functions f A and f B with learning radii ∆ A = 3 × ∆ B.

Evaluation (2) f B handles small displacements better. f A handles large displacements better. Subsequent execution shows both advantages.

Evaluation (3) Results are improved with every iteration. Lower bound of quality is reached after several iterations.

Thank you !