1 Computational Vision CSCI 363, Fall 2012 Lecture 28 Structure from motion.

Slides:



Advertisements
Similar presentations
Bayesian Belief Propagation
Advertisements

Motion Illusions As Optimal Percepts. What’s Special About Perception? Arguably, visual perception is better optimized by evolution than other cognitive.
Dynamic Occlusion Analysis in Optical Flow Fields
CS 376b Introduction to Computer Vision 04 / 21 / 2008 Instructor: Michael Eckmann.
Chapter 6 Feature-based alignment Advanced Computer Vision.
December 5, 2013Computer Vision Lecture 20: Hidden Markov Models/Depth 1 Stereo Vision Due to the limited resolution of images, increasing the baseline.
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
Probabilistic video stabilization using Kalman filtering and mosaicking.
Motion and Ambiguity Russ DuBois. Ambiguity = the possibility to interpret a stimulus in two or more ways Q: Can motion play a part in our interpretation.
Detecting and Tracking Moving Objects for Video Surveillance Isaac Cohen and Gerard Medioni University of Southern California.
Uncalibrated Geometry & Stratification Sastry and Yang
CSc83029 – 3-D Computer Vision/ Ioannis Stamos 3-D Computational Vision CSc Optical Flow & Motion The Factorization Method.
CSSE463: Image Recognition Day 30 Due Friday – Project plan Due Friday – Project plan Evidence that you’ve tried something and what specifically you hope.
Previously Two view geometry: epipolar geometry Stereo vision: 3D reconstruction epipolar lines Baseline O O’ epipolar plane.
COMP 290 Computer Vision - Spring Motion II - Estimation of Motion field / 3-D construction from motion Yongjik Kim.
1B50 – Percepts and Concepts Daniel J Hulme. Outline Cognitive Vision –Why do we want computers to see? –Why can’t computers see? –Introducing percepts.
1/20 Obtaining Shape from Scanning Electron Microscope Using Hopfield Neural Network Yuji Iwahori 1, Haruki Kawanaka 1, Shinji Fukui 2 and Kenji Funahashi.
Colorado Center for Astrodynamics Research The University of Colorado 1 STATISTICAL ORBIT DETERMINATION Satellite Tracking Example of SNC and DMC ASEN.
CSSE463: Image Recognition Day 30 This week This week Today: motion vectors and tracking Today: motion vectors and tracking Friday: Project workday. First.
Brief Introduction to Geometry and Vision
Y. Moses 11 Combining Photometric and Geometric Constraints Yael Moses IDC, Herzliya Joint work with Ilan Shimshoni and Michael Lindenbaum, the Technion.
Time Series Data Analysis - I Yaji Sripada. Dept. of Computing Science, University of Aberdeen2 In this lecture you learn What are Time Series? How to.
1-1 Measuring image motion velocity field “local” motion detectors only measure component of motion perpendicular to moving edge “aperture problem” 2D.
1 Computational Vision CSCI 363, Fall 2012 Lecture 31 Heading Models.
Computer Vision, Robert Pless Lecture 11 our goal is to understand the process of multi-camera vision. Last time, we studies the “Essential” and “Fundamental”
CSCI 256 Data Structures and Algorithm Analysis Lecture 14 Some slides by Kevin Wayne copyright 2005, Pearson Addison Wesley all rights reserved, and some.
December 4, 2014Computer Vision Lecture 22: Depth 1 Stereo Vision Comparing the similar triangles PMC l and p l LC l, we get: Similarly, for PNC r and.
1 Computational Vision CSCI 363, Fall 2012 Lecture 20 Stereo, Motion.
Metrology 1.Perspective distortion. 2.Depth is lost.
1 Perception, Illusion and VR HNRS 299, Spring 2008 Lecture 8 Seeing Depth.
CSC321: 2011 Introduction to Neural Networks and Machine Learning Lecture 9: Ways of speeding up the learning and preventing overfitting Geoffrey Hinton.
1 Perception, Illusion and VR HNRS 299, Spring 2008 Lecture 2 Introduction, Light Course webpage:
Uses of Motion 3D shape reconstruction Segment objects based on motion cues Recognize events and activities Improve video quality Track objects Correct.
University of Colorado Boulder ASEN 5070: Statistical Orbit Determination I Fall 2014 Professor Brandon A. Jones Lecture 26: Singular Value Decomposition.
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
1 Computational Vision CSCI 363, Fall 2012 Lecture 21 Motion II.
1 Computational Vision CSCI 363, Fall 2012 Lecture 5 The Retina.
3D Imaging Motion.
Raquel A. Romano 1 Scientific Computing Seminar May 12, 2004 Projective Geometry for Computer Vision Projective Geometry for Computer Vision Raquel A.
Optical Flow. Distribution of apparent velocities of movement of brightness pattern in an image.
1 Computational Vision CSCI 363, Fall 2012 Lecture 24 Computing Motion.
CS332 Visual Processing Department of Computer Science Wellesley College Analysis of Motion Recovering 3-D structure from motion.
Motion Illusions As Optimal Percepts. What’s Special About Perception? Visual perception important for survival  Likely optimized by evolution  at least.
1 Perception and VR MONT 104S, Fall 2008 Lecture 6 Seeing Motion.
Course14 Dynamic Vision. Biological vision can cope with changing world Moving and changing objects Change illumination Change View-point.
Ch.9 Bayesian Models of Sensory Cue Integration (Mon) Summarized and Presented by J.W. Ha 1.
Tracking with dynamics
IEEE International Conference on Multimedia and Expo.
Lecture 9 Feature Extraction and Motion Estimation Slides by: Michael Black Clark F. Olson Jean Ponce.
6. Population Codes Presented by Rhee, Je-Keun © 2008, SNU Biointelligence Lab,
Perception and VR MONT 104S, Fall 2008 Lecture 8 Seeing Depth
By James J. Todd and Victor J. Perotti Presented by Samuel Crisanto THE VISUAL PERCEPTION OF SURFACE ORIENTATION FROM OPTICAL MOTION.
1 Computational Vision CSCI 363, Fall 2012 Lecture 16 Stereopsis.
Structure from Motion Paul Heckbert, Nov , Image-Based Modeling and Rendering.
1 Computational Vision CSCI 363, Fall 2012 Lecture 29 Structure from motion, Heading.
1 Computational Vision CSCI 363, Fall 2012 Lecture 18 Stereopsis III.
1 Computational Vision CSCI 363, Fall 2012 Lecture 2 Introduction to Vision Science.
1 Computational Vision CSCI 363, Fall 2012 Lecture 32 Biological Heading, Color.
11/25/03 3D Model Acquisition by Tracking 2D Wireframes Presenter: Jing Han Shiau M. Brown, T. Drummond and R. Cipolla Department of Engineering University.
Reconstruction of a Scene with Multiple Linearly Moving Objects Mei Han and Takeo Kanade CISC 849.
From local motion estimates to global ones - physiology:
Instructor: S. Narasimhan
Computational Vision CSCI 363, Fall 2016 Lecture 15 Stereopsis
2D Motion is just the Beginning
Measuring motion in biological vision systems
Measuring motion in biological vision systems
CSSE463: Image Recognition Day 30
Measuring image motion
CSSE463: Image Recognition Day 30
Optical flow and keypoint tracking
Presentation transcript:

1 Computational Vision CSCI 363, Fall 2012 Lecture 28 Structure from motion

2 2D Motion is just the Beginning 2D image motion contains information about: Relative depth of surfaces 3D motion of objects 3D structure of objects Direction of observer motion Among other things.

3 Structure From Motion Structure from motion originally studied rigorously by Wallach and O'Connell (1953). They studied wire-frame objects and examined peoples ability to judge the structure of the objects when moving. The ability to see a 3D structure from a moving 2D image is known as the Kinetic Depth Effect. Demo:

4 Inherent Ambiguity How do we compute a 3D motion from a 2D image motion? Given the 2D image motion, there are multiple possible 3D motions that could have generated it: v Image plane ? To solve for 3D motion from 2D image information, we must use a constraint. The Rigidity constraint assumes that the object is rigid. Next time: Incremental rigidity scheme.

5 The Rigidity Constraint To solve for 3D motion from 2D image information, we must use a constraint. The Rigidity constraint assumes that the object is rigid. Ullman showed that, for an orthographic projection system, one can compute the 3D structure of an object given: 3 distinct views of 4 non-coplanar points in motion. If there exists a rigid 3D structure consistent with these views, then it is unique. The 2D positions of the points generate a set of equations that can be solved for the 3D structure.

6 The problem with noise For perspective projection, one needs 2 views and 7 points. If working with velocity fields, you need 5 points and 1 view (for perspective projection). Problem: This approach is very sensitive to noise in the velocity estimates. This approach does not allow interpretation of non-rigid motions.

7 Information about Human ability The human visual system takes some time to recover the 3D structure: It is not instantaneous. Humans can cope with significant deviations from rigidity. The visual system integrates multiple sources of information (e.g. static depth cues) to determine 3D structure.

8 Incremental Rigidity Scheme The basic idea: 1)At each instant, generate an estimate of the 3D structure. 2)The recovery process prefers rigid transformations, but rigidity is not required. 3)The scheme can tolerate deviations from rigidity. 4)It should be able to integrate information over an extended viewing period. 5)It should eventually recover the correct 3D structure (or a close approximation). y x (x 1, y 1, z 1 ) -> (x 1 ', y 1 ', ?) (x 2, y 2, z 2 ) -> (x 2 ', y 2 ', ?) (x 3, y 3, z 3 ) -> (x 3 ', y 3 ', ?) Initially set z to zero.

9 Maximizing Rigidity We want to find the 3D model, S'(t), that maximizes the rigidity. Therefore, we want to find new Z values that minimize the change in structure L ij l ij Current model Model update Image Find z i to minimize: The denominator makes sure that distant points count less, as they are less likely to be rigidly connected to each other.

10 Performance The incremental rigidity scheme works fairly well for rigid motions. For a rotating object, it can find the 3D shape within about 2-5% error after a few rotations. Mirror reversals may occur sometimes during the computations. (This may arise from orthographic projection). The performance is similar to human structure from motion. x z 0o0o 90 o 180 o 360 o 720 o 1440 o Results of scheme after various rotations of object.

11 Properties of Incremental Rigidity Scheme 1.Veridicality--Usually get a reasonable approximation of the true structure. 2.Temporal extension--The time required is longer than for the 4 points, 3 views method. 3.There is some residual non-rigidity in computed 3D structure. 4.The improvement over time is non-monotonic. There may be some increase in error at times, before it decreases again. 5.Depth reversals--Sometimes this method exhibits spontaneous depth reversals in the estimated 3D structure. 6.May converge to a local minimum that's not the most rigid interpretation. 7.It can be influenced by static depth cues. 8.It can track moderate amounts of non-rigid motion over time. In many ways, this scheme behaves similarly to the human system.

12 Psychophysics of Structure from Motion Psychophysical results show that people can judge structure-from- motion from motion of points with limited lifetimes. Demo of cylinder: Cylinder DemoCylinder Demo Stimulus: Rotating cylinder composed of dots. Dots have limited lifetimes (e.g. 50, 100, 150 msec) People can see 3D structure of cylinder for point lifetimes as low as 125 msec. This is faster than the incremental rigidity scheme can handle.

13 Hildreth extension of Incremental Rigidity Hildreth and colleagues developed an extension of Ullman's incremental rigidity scheme, that uses velocity estimates instead of measure point positions.

14 Depth Estimate from 2D velocities We can compare the 2D velocities that would be generated by the estimated depths of each point with the measured 2D velocities. => Estimate depths, Z i, and velocities: Minimize:

15 Combine with Incremental rigidity The full model uses the 2D velocity estimates and the rigidity constraint: Minimize: E D + E R Where E D is from previous slide. E R is rigidity error: Temporal integration: Information from multiple frames is combined using Kalman filters. Velocity computed at one instant is used to predict depths at the next instant. This tends to smooth out errors.

16 Results Estimated dot positions Surface reconstruction. Surface reconstruction uses smoothness and position of image points to interpolate a surface between point positions.

17 Cylinder Perceptions Ramachandran showed that people do not see cylinder structure accurately in some conditions: Cylinders with different speeds. Cylinders with different radii. Perception

18 Model results for illusions Illusion 1: Different speeds Illusion 2: Different radii The model generates structures similar to those perceived by people.