Last Week Recognized the fact that the 2D image is a representation of a 3D scene thus contains a consistent interpretation –Labeled edges –Labeled vertices.

Slides:



Advertisements
Similar presentations
By: Mani Baghaei Fard.  During recent years number of moving vehicles in roads and highways has been considerably increased.
Advertisements

1Ellen L. Walker Stereo Vision Why? Two images provide information to extract (some) 3D information We have good biological models (our own vision system)
CSE473/573 – Stereo and Multiple View Geometry
For Internal Use Only. © CT T IN EM. All rights reserved. 3D Reconstruction Using Aerial Images A Dense Structure from Motion pipeline Ramakrishna Vedantam.
November 12, 2013Computer Vision Lecture 12: Texture 1Signature Another popular method of representing shape is called the signature. In order to compute.
CS 376b Introduction to Computer Vision 04 / 21 / 2008 Instructor: Michael Eckmann.
MASKS © 2004 Invitation to 3D vision Lecture 7 Step-by-Step Model Buidling.
December 5, 2013Computer Vision Lecture 20: Hidden Markov Models/Depth 1 Stereo Vision Due to the limited resolution of images, increasing the baseline.
Contents Description of the big picture Theoretical background on this work The Algorithm Examples.
1 Introduction to 3D Imaging: Perceiving 3D from 2D Images How can we derive 3D information from one or more 2D images? There have been 2 approaches: 1.
Introduction to Computer Vision 3D Vision Topic 9 Stereo Vision (I) CMPSCI 591A/691A CMPSCI 570/670.
Stereopsis Mark Twain at Pool Table", no date, UCR Museum of Photography.
CSSE463: Image Recognition Day 30 Due Friday – Project plan Due Friday – Project plan Evidence that you’ve tried something and what specifically you hope.
Stereo and Multiview Sequence Processing. Outline Stereopsis Stereo Imaging Principle Disparity Estimation Intermediate View Synthesis Stereo Sequence.
Stockman MSU Fall Computing Motion from Images Chapter 9 of S&S plus otherwork.
3D Computer Vision and Video Computing 3D Vision Lecture 14 Stereo Vision (I) CSC 59866CD Fall 2004 Zhigang Zhu, NAC 8/203A
COMP 290 Computer Vision - Spring Motion II - Estimation of Motion field / 3-D construction from motion Yongjik Kim.
May 2004Stereo1 Introduction to Computer Vision CS / ECE 181B Tuesday, May 11, 2004  Multiple view geometry and stereo  Handout #6 available (check with.
1 Chapter 21 Machine Vision. 2 Chapter 21 Contents (1) l Human Vision l Image Processing l Edge Detection l Convolution and the Canny Edge Detector l.
CSE473/573 – Stereo Correspondence
December 2, 2014Computer Vision Lecture 21: Image Understanding 1 Today’s topic is.. Image Understanding.
Announcements PS3 Due Thursday PS4 Available today, due 4/17. Quiz 2 4/24.
David Luebke Modeling and Rendering Architecture from Photographs A hybrid geometry- and image-based approach Debevec, Taylor, and Malik SIGGRAPH.
Stereo vision A brief introduction Máté István MSc Informatics.
1 Perceiving 3D from 2D Images How can we derive 3D information from one or more 2D images? There have been 2 approaches: 1. intrinsic images: a 2D representation.
3-D Scene u u’u’ Study the mathematical relations between corresponding image points. “Corresponding” means originated from the same 3D point. Objective.
Recap Low Level Vision –Input: pixel values from the imaging device –Data structure: 2D array, homogeneous –Processing: 2D neighborhood operations Histogram.
Lecture 11 Stereo Reconstruction I Lecture 11 Stereo Reconstruction I Mata kuliah: T Computer Vision Tahun: 2010.
TP15 - Tracking Computer Vision, FCUP, 2013 Miguel Coimbra Slides by Prof. Kristen Grauman.
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
1. Introduction Motion Segmentation The Affine Motion Model Contour Extraction & Shape Estimation Recursive Shape Estimation & Motion Estimation Occlusion.
Integral University EC-024 Digital Image Processing.
High-Resolution Interactive Panoramas with MPEG-4 발표자 : 김영백 임베디드시스템연구실.
Shape from Stereo  Disparity between two images  Photogrammetry  Finding Corresponding Points Correlation based methods Feature based methods.
3D Sensing and Reconstruction Readings: Ch 12: , Ch 13: , Perspective Geometry Camera Model Stereo Triangulation 3D Reconstruction by.
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.
Computer Vision Why study Computer Vision? Images and movies are everywhere Fast-growing collection of useful applications –building representations.
Course 9 Texture. Definition: Texture is repeating patterns of local variations in image intensity, which is too fine to be distinguished. Texture evokes.
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
Lec 22: Stereo CS4670 / 5670: Computer Vision Kavita Bala.
Computer Vision Stereo Vision. Bahadir K. Gunturk2 Pinhole Camera.
1 Artificial Intelligence: Vision Stages of analysis Low level vision Surfaces and distance Object Matching.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
CSE 185 Introduction to Computer Vision Stereo. Taken at the same time or sequential in time stereo vision structure from motion optical flow Multiple.
3D Sensing Camera Model Camera Calibration
Bahadir K. Gunturk1 Phase Correlation Bahadir K. Gunturk2 Phase Correlation Take cross correlation Take inverse Fourier transform  Location of the impulse.
(c) 2000, 2001 SNU CSE Biointelligence Lab Finding Region Another method for processing image  to find “regions” Finding regions  Finding outlines.
Colour and Texture. Extract 3-D information Using Vision Extract 3-D information for performing certain tasks such as manipulation, navigation, and recognition.
Course14 Dynamic Vision. Biological vision can cope with changing world Moving and changing objects Change illumination Change View-point.
55:148 Digital Image Processing Chapter 11 3D Vision, Geometry Topics: Basics of projective geometry Points and hyperplanes in projective space Homography.
Computer vision: models, learning and inference M Ahad Multiple Cameras
Lecture 9 Feature Extraction and Motion Estimation Slides by: Michael Black Clark F. Olson Jean Ponce.
1Ellen L. Walker 3D Vision Why? The world is 3D Not all useful information is readily available in 2D Why so hard? “Inverse problem”: one image = many.
Perception and VR MONT 104S, Fall 2008 Lecture 8 Seeing Depth
CS 376b Introduction to Computer Vision 03 / 31 / 2008 Instructor: Michael Eckmann.
Correspondence and Stereopsis Original notes by W. Correa. Figures from [Forsyth & Ponce] and [Trucco & Verri]
John Morris Stereo Vision (continued) Iolanthe returns to the Waitemata Harbour.
Image-Based Rendering Geometry and light interaction may be difficult and expensive to model –Think of how hard radiosity is –Imagine the complexity of.
Correspondence and Stereopsis. Introduction Disparity – Informally: difference between two pictures – Allows us to gain a strong sense of depth Stereopsis.
A Plane-Based Approach to Mondrian Stereo Matching
Processing visual information for Computer Vision
CS4670 / 5670: Computer Vision Kavita Bala Lec 27: Stereo.
Common Classification Tasks
Range Imaging Through Triangulation
Multiple View Geometry for Robotics
Computer Vision Stereo Vision.
CSSE463: Image Recognition Day 30
Course 6 Stereo.
CSSE463: Image Recognition Day 30
Presentation transcript:

Last Week Recognized the fact that the 2D image is a representation of a 3D scene thus contains a consistent interpretation –Labeled edges –Labeled vertices Matching techniques for object recognition –Graph theoretic –Relaxation –Perceptual organization (neural networks)

This Week Look at direct measurement of 3D attributes via stereo cameras Look at other uses of matching –Stereo correspondence –Motion correspondence

Stereo Vision Goal is to extract scene depth via multiple monocular images with a passive sensor –Note that this can be done by other “active” means such as LIDAR (LIght Detection And Ranging)

Stereo Vision Humans do it well from a single image and very, very well through stereo images Not well understood what the mechanism is –We understand the biological design, but not the exact algorithm Goal of computer vision is not to mimic the mechanics of the biological system, but to mimic the functionality of the system

Stereo Vision Depth information will be used to… –Differentiate objects from background –Differentiate objects from one another –Expose camouflaged objects Basic method is to take advantage of the lateral displacement of the image of a 3D object in two cameras with different, but overlapping views –Lateral displacement is also known as disparity

Stereo Vision Two sub-problems –Correspondence problem The problem of measuring the disparity of each point in the two eye (camera) projections –Interpretation problem The use of disparity information to recover the orientation and distance of surfaces in the scene

Stereo Algorithmic Steps Basic steps to be performed in any stereo imaging system –Image Acquisition –Camera Modeling –Feature Extraction –Image Matching –Depth Determination –Depth Interpolation

Image Acquisition Just as the name implies Capturing two images with a very specific camera geometry

Camera Modeling Related to Image Acquisition For accurate depth results the camera parameters must be known Also, the relationship between the two cameras must be known

Stereo Imaging Geometry f (focal length) Right Camera Axis Left Camera Axis Stereo Baseline B Right Image Left Image Scene The result is two images that are slightly different

Feature Acquisition These are the image objects that will be matched between the left and right images –Gray level pixel based –Edge based –Line based –Region based –Hybrid approaches All techniques have been tried –All provide some degree of success –All have drawbacks

Image Matching By far the most difficult part of the stereo problem Also called the “stereo correspondence problem” When people “study” stereo imaging, this is generally what they are looking at The question is: Which parts (pixels, edges, lines, etc.) of the left image correspond to which parts of the right image?

Image Matching Gray level based –Take a section of one image and use it as a convolution mask over the other Edge based –Extract edges then take a section of one edge image and used it as a convolution mask over the other Line based –Extract edges, form line segments, then match using a relaxation technique Region based –Extract regions then match using a relaxation technique Hybrid approach –Use matched regions (or lines) as guides to further pixel level matches

Image Matching Issues Density of depth map –Would like to have a depth measurement at every image pixel This means a correspondence between every pixel in each image must be made –Clearly difficult (if not impossible) to do Gray level matching is the only real hope All other approaches will not provide a dense map, especially the region based approach Thus the study of hybrid algorithms

Depth Map CSC508 15

Image Matching Issues Photometric variation –The two cameras image the scene from two different viewpoints, by definition –Thus the lighting on the scene differs for the two cameras Shadows, reflectance, etc. –Affects all matching and feature extraction techniques

Image Matching Issues Occlusion –When the image of one object is blocked by another in one of the two cameras It’s a 3D scene so this will happen! –Some features will show up in one image and not the other thus making matching impossible –Affects all matching and feature extraction techniques

Image Matching Issues Repetitive texture –i.e. A brick wall (or any other regular, repeated pattern texture) –Makes the matching process very difficult although some sort of a relaxation algorithm may address the issue –Region based matching may be used to address this issue

Image Matching Issues Lack of texture –i.e. Smooth, feature-less objects –If there are no features, there is no way to match –Region based matching may be used to address this issue

Depth Determination It’s all math! –And relatively simple math at that.

CSC Depth Determination P l (X l,Y l ) P r (X r,Y r ) (X w,0,Z w ) P w (X w,Y w,Z w ) XwXw YwYw ZwZw (X w,0,0) XlXl YlYl YrYr XrXr f (focal length) Right Camera Axis Left Camera Axis Stereo Baseline B Right Image Left Image

Depth Determination Depth (distance of a pixel location to the baseline) can be determined through simple algebraic and geometric relationships is referred to as the stereo disparity –i.e. the difference in how the two cameras saw an object

Depth Interpolation We want to describe surfaces, not individual points In the event that we don’t get a dense depth map (and we rarely do) we must interpolate the missing points –What we get is called a sparse depth map

Depth Interpolation Three basic methods –Relaxation – surface fitting with constraints Similar in nature to the relaxation labeling –Analytic – surface fitting to a specified model (equation) –Heuristic – use of local neighborhoods and predetermined rules Use of “educated guesses” and “higher level scene knowledge” – AI technique

Assumptions To Make Life Easier From psychological studies… –In light of ambiguities in the matching problem, matches which preserve “figural continuity” are to be preferred –That is, we prefer smooth surfaces over sharp changes –This isn’t really a problem since the sharp changes [in all likelihood] won’t result in ambiguities

Assumptions To Make Life Easier Epipolarity (epipolar lines) –The camera geometry can be defined such that a point feature in one image must lie on a specific line in the other image –This constrains the search to multiple 1D problems

Epipolar Lines P l (X l,Y l ) P r (X r,Y r ) (X w,0,Z w ) P w (X w,Y w,Z w ) XwXw YwYw ZwZw (X w,0,0) XlXl YlYl YrYr XrXr f (focal length) Right Camera Axis Left Camera Axis Stereo Baseline B Right Image Left Image

Stereo Pair Images Left Camera Right Camera

Depth Map Rendering

Gray Level Rendering

Final Thoughts Yes, it can be done with more than two cameras –This improves the accuracy of (removes ambiguity from) the match Yes, it can be done with one camera –Simply move the camera along the baseline snapping pictures as it goes

Motion Processing Whereas stereo processing worked on two (or more) frames taken at the same time, motion processing works on two (or more) frames taken at different times

Motion Processing Uses for motion processing –Scene segmentation –Motion detection (is something moving?) Security applications –Motion estimation (how is the object moving?) MPEG uses this to predict future frames –3D structure determination Multiple views of an object as it moves –Object tracking Defense industry makes great use of this –Separate camera motion from object motion Camera stablization

Motion Processing Approaches range from simple… –Frame-to-frame subtraction to intermediate… –Frame-to-frame correspondence to difficult… –Statistical based processing for tracking

Correspondence The frame-to-frame correspondence problem is essentially the same as that for stereo processing –But, it may be more difficult since… objects may be moving towards the camera (they get larger) objects may be moving away from the camera (they get smaller) objects may be rotating (they change shape)

Frame Subtraction Avoids the correspondence operation all together Problems arise in that objects lacking texture do not get detected We also must address the threshold selection problem Assumes that the scene changes will be small due to the short time duration between frames Variations include learning the background (static scene) and subtracting it from the live (dynamic scene)

Frame Subtraction Frame(n)Frame(n + 1) Frame(n) - Frame(n + 1) enhanced

Optical Flow Apparent motion of the brightness patterns within an image You end up with pictures as shown –In this case the camera was moving towards the object

Another Example

Optical Flow Its basically frame-to-frame subtraction with a lot more information From the optical flow field various parameters can be measured –Object shape –Object segmentation –Camera motion –Multiple object motions

Motion Estimation in MPEG Select an image block from frame f n Select a larger image block from frame f n+1 Center the f n block on the f n+1 block Compute correlation between the two blocks Spiral the f n block outward on the f n+1 block until the correlation yields a suitable response Image block from frame f n Image block from frame f n+1

Motion Estimation in MPEG The basic scheme using gray level correlation (matching) works because the premise is that there will be very small motions between frames In the event of large motions or illumination changes (or any other “drastic” changes) the systems reinitializes and doesn’t try to use any motion information

Object Tracking This is essentially motion prediction After observing a moving object can we predict where it will appear in the next frame?

Object Tracking Can be as simple as a low pass filter –A weighted average of the object’s position in previous frames –Heavily weight the newest frames Can be a complex statistical model taking into account noisy measurements –Kalman Filter As your confidence in the prediction increases the window in which you must perform the correspondence decreases in size –Basically, you’re trying to reduce the time to search

Summary We have merely touched on the basics of Computer Vision There is much, much more Hopefully, with this introduction you will be able to pursue other topic areas on your own

CSC Things To Do Final Exam due next week Course evaluation this week (online)