1 A Markov Random Field Framework for Finding Shadows in a Single Colour Image Cheng Lu and Mark S. Drew School of Computing Science, Simon Fraser University,

Slides:



Advertisements
Similar presentations
A Common Framework for Ambient Illumination in the Dichromatic Reflectance Model Color and Reflectance in Imaging and Computer Vision Workshop 2009 October.
Advertisements

Intrinsic Images by Entropy Minimization (Midway Presentation, by Yingda Chen) Graham D. Finlayson, Mark S. Drew and Cheng Lu, ECCV, Prague, 2004.
Computer Vision Radiometry. Bahadir K. Gunturk2 Radiometry Radiometry is the part of image formation concerned with the relation among the amounts of.
3-D Computer Vision CSc83020 / Ioannis Stamos  Revisit filtering (Gaussian and Median)  Introduction to edge detection 3-D Computater Vision CSc
A Standardized Workflow for Illumination-Invariant Image Extraction Mark S. Drew Muntaseer Salahuddin Alireza Fathi Simon Fraser University, Vancouver,
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm Lecture #12.
Lilong Shi and Brian Funt School of Computing Science, Simon Fraser University, Canada.
Outdoor Image Processing 1. Photometric stereo for outdoor webcams  "Photometric stereo for outdoor webcams" Ackermann, J.; Langguth, F.; Fuhrmann, S.;
16421: Vision Sensors Lecture 6: Radiometry and Radiometric Calibration Instructor: S. Narasimhan Wean 5312, T-R 1:30pm – 2:50pm.
Basic Principles of Surface Reflectance
December 5, 2013Computer Vision Lecture 20: Hidden Markov Models/Depth 1 Stereo Vision Due to the limited resolution of images, increasing the baseline.
1 Practical Scene Illuminant Estimation via Flash/No-Flash Pairs Cheng Lu and Mark S. Drew Simon Fraser University {clu,
BMVC 2009 Specularity and Shadow Interpolation via Robust Polynomial Texture Maps Mark S. Drew 1, Nasim Hajari 1, Yacov Hel-Or 2 & Tom Malzbender 3 1 School.
ECCV 2002 Removing Shadows From Images G. D. Finlayson 1, S.D. Hordley 1 & M.S. Drew 2 1 School of Information Systems, University of East Anglia, UK 2.
ICCV 2003 Colour Workshop 1 Recovery of Chromaticity Image Free from Shadows via Illumination Invariance Mark S. Drew 1, Graham D. Finlayson 2, & Steven.
1 Invariant Image Improvement by sRGB Colour Space Sharpening 1 Graham D. Finlayson, 2 Mark S. Drew, and 2 Cheng Lu 1 School of Information Systems, University.
1 Automatic Compensation for Camera Settings for Images Taken under Different Illuminants Cheng Lu and Mark S. Drew Simon Fraser University {clu,
School of Computer Science Simon Fraser University November 2009 Sharpening from Shadows: Sensor Transforms for Removing Shadows using a Single Image Mark.
Image Quilting for Texture Synthesis and Transfer Alexei A. Efros1,2 William T. Freeman2.
Color Image Understanding Sharon Alpert & Denis Simakov.
Mark S. Drew and Amin Yazdani Salekdeh School of Computing Science,
6/23/2015CIC 10, Color constancy at a pixel [Finlayson et al. CIC8, 2000] Idea: plot log(R/G) vs. log(B/G): 14 daylights 24 patches.
7M836 Animation & Rendering
Basic Principles of Surface Reflectance
Stereo Computation using Iterative Graph-Cuts
Shadow Removal Using Illumination Invariant Image Graham D. Finlayson, Steven D. Hordley, Mark S. Drew Presented by: Eli Arbel.
CS292 Computational Vision and Language Visual Features - Colour and Texture.
Basic Principles of Surface Reflectance Lecture #3 Thanks to Shree Nayar, Ravi Ramamoorthi, Pat Hanrahan.
Object recognition under varying illumination. Lighting changes objects appearance.
Information that lets you recognise a region.
Introduction of the intrinsic image. Intrinsic Images The method of Finlayson & Hordley ( 2001 ) Two assumptions 1. the camera ’ s sensors are sufficiently.
Stereo Matching & Energy Minimization Vision for Graphics CSE 590SS, Winter 2001 Richard Szeliski.
Basic Ray Tracing CMSC 435/634. Visibility Problem Rendering: converting a model to an image Visibility: deciding which objects (or parts) will appear.
Basic Principles of Imaging and Photometry Lecture #2 Thanks to Shree Nayar, Ravi Ramamoorthi, Pat Hanrahan.
Computer Vision Spring ,-685 Instructor: S. Narasimhan PH A18B T-R 10:30am – 11:50am Lecture #13.
My Research Experience Cheng Qian. Outline 3D Reconstruction Based on Range Images Color Engineering Thermal Image Restoration.
1 Intelligent Robotics Research Centre (IRRC) Department of Electrical and Computer Systems Engineering Monash University, Australia Visual Perception.
Tricolor Attenuation Model for Shadow Detection. INTRODUCTION Shadows may cause some undesirable problems in many computer vision and image analysis tasks,
Lecture 12 Modules Employing Gradient Descent Computing Optical Flow Shape from Shading.
November 2012 The Role of Bright Pixels in Illumination Estimation Hamid Reza Vaezi Joze Mark S. Drew Graham D. Finlayson Petra Aurora Troncoso Rey School.
Y. Moses 11 Combining Photometric and Geometric Constraints Yael Moses IDC, Herzliya Joint work with Ilan Shimshoni and Michael Lindenbaum, the Technion.
Shape from Shading and Texture. Lambertian Reflectance Model Diffuse surfaces appear equally bright from all directionsDiffuse surfaces appear equally.
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 Formation et Analyse d’Images Session 2 Daniela Hall 7 October 2004.
Phase Congruency Detects Corners and Edges Peter Kovesi School of Computer Science & Software Engineering The University of Western Australia.
Course 9 Texture. Definition: Texture is repeating patterns of local variations in image intensity, which is too fine to be distinguished. Texture evokes.
Xu Huaping, Wang Wei, Liu Xianghua Beihang University, China.
Image Segmentation and Edge Detection Digital Image Processing Instructor: Dr. Cheng-Chien LiuCheng-Chien Liu Department of Earth Sciences National Cheng.
Course 10 Shading. 1. Basic Concepts: Light Source: Radiance: the light energy radiated from a unit area of light source (or surface) in a unit solid.
1 Markov random field: A brief introduction (2) Tzu-Cheng Jen Institute of Electronics, NCTU
November 4, THE REFLECTANCE MAP AND SHAPE-FROM-SHADING.
Multiple Light Source Optical Flow Multiple Light Source Optical Flow Robert J. Woodham ICCV’90.
Course14 Dynamic Vision. Biological vision can cope with changing world Moving and changing objects Change illumination Change View-point.
Local Illumination and Shading
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.
Lecture 04 Edge Detection Lecture 04 Edge Detection Mata kuliah: T Computer Vision Tahun: 2010.
Radiometry of Image Formation Jitendra Malik. A camera creates an image … The image I(x,y) measures how much light is captured at pixel (x,y) We want.
Schedule Update GP 4 – Tesselation/Cg GDS 4 – Subdiv Surf. GP 5 – Object Modeling Lab: Mini-proj Setup GDS 5 – Maya Modeling MCG 6 – Intersections GP 6.
Radiometry of Image Formation Jitendra Malik. What is in an image? The image is an array of brightness values (three arrays for RGB images)
Announcements Project 3a due today Project 3b due next Friday.
MAN-522 Computer Vision Spring
The Colour of Light: Additive colour theory.
Announcements Final is Thursday, March 20, 10:30-12:20pm
3D Graphics Rendering PPT By Ricardo Veguilla.
Image gradients and edges
Range Imaging Through Triangulation
Object tracking in video scenes Object tracking in video scenes
Mingjing Zhang and Mark S. Drew
Specularity, the Zeta-image, and Information-Theoretic Illuminant
Shape from Shading and Texture
Presentation transcript:

1 A Markov Random Field Framework for Finding Shadows in a Single Colour Image Cheng Lu and Mark S. Drew School of Computing Science, Simon Fraser University, Vancouver (CANADA)

2 Objective – finding shadows Many computer vision algorithms, such as segmentation, tracking, and stereo registration, are confounded by shadows. Finding shadows

3 Shadows stem from what illumination effects? Changes of illuminant in both intensity and colour Region Lit by Sky-light only Region Lit by Sunlight and Sky-light Intensity — sharp intensity changes Colour — shadows exist in the chromaticity image

4 Colour of illuminants Wien’s approximation of Planckian illuminants: How good is this approximation? 2500 Kelvin Kelvin 5500 Kelvin

5 Invariant Image Concept For narrow-band Sensors: n aiai Lambertian Surface The responses: Planckian Lighting x Finlayson et al.,ECCV2002 k = R, G, B Shading and intensity term

6 Band-ratio chromaticity G R B Plane G=1 Perspective projection onto G=1 Let us define a set of 2D band-ratio chromaticities: p is one of the channels, (Green, say) [or could use Geometric Mean]

7 Let’s take log’s: Band-ratios remove shading and intensity with Gives a straight line: Shading and intensity are gone.

8 Calibration: find illuminant direction Log-ratio chromaticities for 6 surfaces under 14 different Planckian illuminants, HP912 camera Macbeth ColorChecker: 24 patches Illuminant direction Invariant direction

9 A real image containing shadows The red line refers to the changes of illuminants: same surface lit by two different lights Two lights: Shadows : lit by sunlight and sky-light Non-shadows : lit by sky-light

10 Illuminant discontinuity Illuminant discontinuity pair Illuminant discontinuity pair: Two neighbouring pixels of a single surface, under two different lights

11 Illuminant discontinuity measure Using the means of two neighboring blocks of pixels better than using two neighbouring pixels because of noise and diffuse shadow edges. Illuminant discontinuity angle: Cos of the two vectors

12 Finding Shadows First order neighbors Label image pixels with label l ={shadow, nonshadow} Model this labelling problem using Markov Random Field The label of a pixel depends only on its neighbours

13 Markov Random Field l is a Markov Random Field: l follows a Gibbs distribution: Z=normalizing constant, and U( l ) is an energy function defined with respect to neighbours labelling minimizing energy U( l )

14 Energy function D ij =wQ ij +(1-w)R ij Combining intensity difference Q ij and illuminant discontinuity angle R ij (weight=w) if (l i = l j ) if Roughly, In full,

15 Implementation Gibbs Sampler can be used to minimize the energy: optimization technique. Texture and noise may confuse the discontinuity measure, so the Mean Shift method is used to filter (segment) the image first.

16 Experiments