Chromatic Framework for Vision in Bad Weather Srinivasa G. Narasimhan and Shree K. Nayar Computer Science Department Columbia University IEEE CVPR Conference.

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

Film and Sensitometry The science of measuring an emulsions reaction (sensitivity) to light is called sensitometry The Characteristic Curve The graph that.
Visibility in Bad Weather from a Single Image
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm Lecture #12.
Micro Phase Shifting Mohit Gupta and Shree K. Nayar Computer Science Columbia University Supported by: NSF and ONR.
16421: Vision Sensors Lecture 6: Radiometry and Radiometric Calibration Instructor: S. Narasimhan Wean 5312, T-R 1:30pm – 2:50pm.
Two-View Geometry CS Sastry and Yang
Rob Fergus Courant Institute of Mathematical Sciences New York University A Variational Approach to Blind Image Deconvolution.
Physics-based Illuminant Color Estimation as an Image Semantics Clue Christian Riess Elli Angelopoulou Pattern Recognition Lab (Computer Science 5) University.
ICCV 2003 Colour Workshop 1 Recovery of Chromaticity Image Free from Shadows via Illumination Invariance Mark S. Drew 1, Graham D. Finlayson 2, & Steven.
Multimodal Templates for Real-Time Detection of Texture-less Objects in Heavily Cluttered Scenes Stefan Hinterstoisser, Stefan Holzer, Cedric Cagniart,
Shree Nayar and Srinivasa Narasimhan Computer Science Columbia University ICCV Conference Korfu, Greece, September 1999 Sponsors: NSF Vision in Bad Weather.
Radiometric Self Calibration
When Does a Camera See Rain? Department of Computer Science Columbia University Kshitiz Garg Shree K. Nayar ICCV Conference October 2005, Beijing, China.
Free Space Detection for autonomous navigation in daytime foggy weather Nicolas Hautière, Jean-Philippe Tarel, Didier Aubert.
Detection and Removal of Rain from Videos Department of Computer Science Columbia University Kshitiz Garg and Shree K. Nayar IEEE CVPR Conference June.
Uncalibrated Geometry & Stratification Sastry and Yang
360 x 360 Mosaics Shree K. Nayar and Amruta Karmarkar Computer Science Department Columbia University IEEE CVPR Conference June 2000, Hilton Head Island,
Photorealistic Rendering of Rain Streaks Department of Computer Science Columbia University Kshitiz Garg Shree K. Nayar SIGGRAPH Conference July 2006,
Image-based Rendering of Real Objects with Complex BRDFs.
Structured Light in Scattering Media Srinivasa Narasimhan Sanjeev Koppal Robotics Institute Carnegie Mellon University Sponsor: ONR Shree Nayar Bo Sun.
Single Image Haze Removal Using Dark Channel Prior Professor : 王聖智 教授 Student : 戴玉書 CVPR Best Paper AwardBest Paper Award Kaiming HeKaiming He, Dept.
Lensless Imaging with A Controllable Aperture Assaf Zomet and Shree K. Nayar Columbia University IEEE CVPR Conference June 2006, New York, USA.
Object recognition under varying illumination. Lighting changes objects appearance.
A Novel 2D To 3D Image Technique Based On Object- Oriented Conversion.
Removing Weather Effects from Monochrome Images Srinivasa Narasimhan and Shree Nayar Computer Science Department Columbia University IEEE CVPR Conference.
Noise Estimation from a Single Image Ce Liu William T. FreemanRichard Szeliski Sing Bing Kang.
Computer Vision Spring ,-685 Instructor: S. Narasimhan WH 5409 T-R 10:30am – 11:50am Lecture #15.
Computer Vision Spring ,-685 Instructor: S. Narasimhan PH A18B T-R 10:30am – 11:50am Lecture #13.
CSC 589 Lecture 22 Image Alignment and least square methods Bei Xiao American University April 13.
Simple Calibration of Non-overlapping Cameras with a Mirror
Jitter Camera: High Resolution Video from a Low Resolution Detector Moshe Ben-Ezra, Assaf Zomet and Shree K. Nayar IEEE CVPR Conference June 2004, Washington.
Camera Geometry and Calibration Thanks to Martial Hebert.
Shedding Light on the Weather
Multiple Scattering in Vision and Graphics Lecture #21 Thanks to Henrik Wann Jensen.
Overview of Haze Removal Methods Matteo Pedone Machine Vision Group, University of Oulu, Finland.
Sebastian Enrique Columbia University Relighting Framework COMS 6160 – Real-Time High Quality Rendering Nov 3 rd, 2004.
16421: Vision Sensors Lecture 7: High Dynamic Range Imaging Instructor: S. Narasimhan Wean 5312, T-R 1:30pm – 3:00pm.
Colour changes in a natural scene due to the interaction between the light and the atmosphere Raúl Luzón González Colour Imaging Laboratory.
Metrology 1.Perspective distortion. 2.Depth is lost.
Blind Contrast Restoration Assessment by Gradient Ratioing at Visible Edges Nicolas Hautière 1, Jean-Philippe Tarel 1, Didier Aubert 1-2, Eric Dumont 1.
Motion Deblurring Using Hybrid Imaging Moshe Ben-Ezra and Shree K. Nayar Columbia University IEEE CVPR Conference June 2003, Madison, USA.
Surface reconstruction of sea-ice through stereo - initial steps Rohith MV Gowri Somanath VIMS Lab.
Aircraft Navigation State-of-the-Art in Vision Technologies Rangachar Kasturi, PhD Computer Science & Engineering University of South Florida.
Raquel A. Romano 1 Scientific Computing Seminar May 12, 2004 Projective Geometry for Computer Vision Projective Geometry for Computer Vision Raquel A.
Vision Review: Miscellaneous Course web page: October 8, 2002.
Determining the location and orientation of webcams using natural scene variations Nathan Jacobs.
CS332 Visual Processing Department of Computer Science Wellesley College Analysis of Motion Recovering 3-D structure from motion.
Color and Brightness Constancy Jim Rehg CS 4495/7495 Computer Vision Lecture 25 & 26 Wed Oct 18, 2002.
Inferring Reflectance Functions from Wavelet Noise Pieter Peers Philip Dutré Pieter Peers Philip Dutré June 30 th 2005 Department of Computer Science.
Zhang & Liang, Computer Graphics Using Java 2D and 3D (c) 2007 Pearson Education, Inc. All rights reserved. 1 Chapter 9 Lighting and Texturing.
True FOE Computed FOE Recovering the observer’s rotation Velocity component due to observer’s translation Velocity component due to observer’s rotation.
IEEE International Conference on Multimedia and Expo.
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.
Polarization-based dehazing using two reference objects
Reconstruction from Two Calibrated Views Two-View Geometry
Tal Amir Advanced Topics in Computer Vision May 29 th, 2015 COUPLED MOTION- LIGHTING ANALYSIS.
May 16-18, Tsukuba Science City, Japan Machine Vision Applications 2005 Estimation of the Visibility Distance by Stereovision: a Generic Approach.
1 What do color changes reveal about an outdoor scene? KalyanFabianoWojciechToddHanspeter SunkavalliRomeiroMatusikZicklerPfister Harvard University Adobe.
Using Clouds Shadows to Infer Scene Structure and Camera Calibration
By: Rachel Yuen, Chad Van De Hey, and Jake Trotman
Phil Morley Haze Removal.
Instant Dehazing of Images using Polarization
A Practical Analytic Single Scattering Model for Real Time Rendering
Multiplexed Illumination
Image Restoration using Model-based Tracking
Markov Random Fields with Efficient Approximations
© 2003 University of Wisconsin
Abstract In this paper, an improved defogging algorithm for intelligent transportation system based on image processing is proposed. According to the.
Single Image Haze Removal Using Dark Channel Prior
Presentation transcript:

Chromatic Framework for Vision in Bad Weather Srinivasa G. Narasimhan and Shree K. Nayar Computer Science Department Columbia University IEEE CVPR Conference June 2000, Hilton Head Island, USA Sponsors: ONR MURI, NSF

The Colors of Bad Weather Clear Day B R G Dense Fog B R G Noon Haze B R G

Prior Work Overviews : Middleton 1952, McCartney 1976 Haze : Hulburt 1946, Hidy 1972 Fog : Koshmeider 1924, George 1951, Myers 1968 Vision : Cozman & Krotkov Depth Cues from Iso-Intensities Nayar & Narasimhan Complete Structure ; Restricted weather conditions General Color Framework for Analysis of Bad Weather Images OUR GOAL :

Direct Transmission and Airlight Models Object Observer d ( Allard, 1876 ) Direct Transmission E Sunlight Diffuse Skylight Diffuse Ground Light ( Koschmieder, 1924 ) Airlight E

Dichromatic Atmospheric Scattering Model B G R Model : ( Nayar & Narasimhan, 1999 ) E Direct Transmission (True Color ) Airlight (Fog / Haze Color)

Dichromatic Planes Direct Transmission Color Airlight Color Dichromatic Plane Scene (800 x 600 pixels) Avg. Error (degrees) Foggy Hazy 0.25 º 0.31 º Verification :

Direction of Airlight ( Fog or Haze ) Color Plane 1 (Scene Point X) Plane 2 (Scene Point O) Weather Condition 1 Weather Condition 2 Airlight Color from Planes :

Depth from Unknown Weather Conditions Ratio of Direct Transmissions : Scattering Coefficients :, ( Unknown ) Sky Brightnesses :, ( Unknown ) Depth of a Scene Point : Direct Transmission Ratio Scaled Depth Sky Brightness Ratio

Direct Transmission Ratio Dichromatic Plane Direct Transmission Color Airlight Color Direct Transmission Ratio :

Sky Brightnesses Relation Between Sky Brightnesses Dichromatic Plane Direct Transmission Color Airlight Color Relative Airlight Depth of a Scene Point

Results with a Synthetic Scene Color Patches Recovered Structure Fog 1 + Noise Fog 2 + Noise Rotated Structure

Simulation Results Noise Estimated Depth Error (%) Actual Values = Actual Values = Noise Estimated Depth Error (%)

Scene under two different Hazy Conditions Computed Depth Map Structure from Two Weather Conditions

Scene under two different Foggy Conditions Computed Depth Map

True Color Recovery - Color Cube Boundary Algorithm R G B O Min Minimum Time to Collision First Collision with Color Boundary

True Color Recovery Scene under two different Foggy Conditions Computed True Color ( Brightened )

Summary Scene Depth from Dichromatic Constraints Airlight Color from Dichromatic Planes True Color from Color Boundary Constraint Color Framework for Vision in Bad Weather