Optical Flow CS 637. Fuxin Li. With materials from Kristen Grauman, Richard Szeliski, S. Narasimhan, Deqing Sun

Similar documents
CS 4495 Computer Vision Motion and Optic Flow

Peripheral drift illusion

CS6670: Computer Vision

EE795: Computer Vision and Intelligent Systems

Lucas-Kanade Motion Estimation. Thanks to Steve Seitz, Simon Baker, Takeo Kanade, and anyone else who helped develop these slides.

Finally: Motion and tracking. Motion 4/20/2011. CS 376 Lecture 24 Motion 1. Video. Uses of motion. Motion parallax. Motion field

Multi-stable Perception. Necker Cube

EE795: Computer Vision and Intelligent Systems

Fundamental matrix. Let p be a point in left image, p in right image. Epipolar relation. Epipolar mapping described by a 3x3 matrix F

Motion and Optical Flow. Slides from Ce Liu, Steve Seitz, Larry Zitnick, Ali Farhadi

Computer Vision Lecture 20

Computer Vision Lecture 20

Visual motion. Many slides adapted from S. Seitz, R. Szeliski, M. Pollefeys

VC 11/12 T11 Optical Flow

Computer Vision Lecture 20

Automatic Image Alignment (direct) with a lot of slides stolen from Steve Seitz and Rick Szeliski

Dense Image-based Motion Estimation Algorithms & Optical Flow

Notes 9: Optical Flow

Ninio, J. and Stevens, K. A. (2000) Variations on the Hermann grid: an extinction illusion. Perception, 29,

Motion and Tracking. Andrea Torsello DAIS Università Ca Foscari via Torino 155, Mestre (VE)

Feature Tracking and Optical Flow

Matching. Compare region of image to region of image. Today, simplest kind of matching. Intensities similar.

Feature Tracking and Optical Flow

Lecture 16: Computer Vision

Motion Estimation (II) Ce Liu Microsoft Research New England

ECE Digital Image Processing and Introduction to Computer Vision

Optical Flow-Based Motion Estimation. Thanks to Steve Seitz, Simon Baker, Takeo Kanade, and anyone else who helped develop these slides.

Optic Flow and Basics Towards Horn-Schunck 1

EECS 556 Image Processing W 09

Overview. Video. Overview 4/7/2008. Optical flow. Why estimate motion? Motion estimation: Optical flow. Motion Magnification Colorization.

Displacement estimation

Visual Tracking (1) Tracking of Feature Points and Planar Rigid Objects

Lecture 16: Computer Vision

Optical flow and tracking

CS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching

Motion Estimation. There are three main types (or applications) of motion estimation:

Lecture 19: Motion. Effect of window size 11/20/2007. Sources of error in correspondences. Review Problem set 3. Tuesday, Nov 20

Visual Tracking (1) Feature Point Tracking and Block Matching

CS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching

CPSC 425: Computer Vision

Comparison between Motion Analysis and Stereo

COMPUTER VISION > OPTICAL FLOW UTRECHT UNIVERSITY RONALD POPPE

Visual Tracking (1) Pixel-intensity-based methods

Representing Moving Images with Layers. J. Y. Wang and E. H. Adelson MIT Media Lab

Computer Vision Lecture 18

Spatial track: motion modeling

SURVEY OF LOCAL AND GLOBAL OPTICAL FLOW WITH COARSE TO FINE METHOD

Comparison of stereo inspired optical flow estimation techniques

Particle Tracking. For Bulk Material Handling Systems Using DEM Models. By: Jordan Pease

Convolutional Neural Network Implementation of Superresolution Video

Visual Tracking. Image Processing Laboratory Dipartimento di Matematica e Informatica Università degli studi di Catania.

Visual Tracking. Antonino Furnari. Image Processing Lab Dipartimento di Matematica e Informatica Università degli Studi di Catania

Spatial track: motion modeling

Part II: Modeling Aspects

Ruch (Motion) Rozpoznawanie Obrazów Krzysztof Krawiec Instytut Informatyki, Politechnika Poznańska. Krzysztof Krawiec IDSS

CSCI 1290: Comp Photo

CS664 Lecture #18: Motion

EE 264: Image Processing and Reconstruction. Image Motion Estimation I. EE 264: Image Processing and Reconstruction. Outline

CS-465 Computer Vision

Augmented Reality VU. Computer Vision 3D Registration (2) Prof. Vincent Lepetit

Introduction to Computer Vision

Lecture 20: Tracking. Tuesday, Nov 27

SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014

Optical flow. Cordelia Schmid

Capturing, Modeling, Rendering 3D Structures

Edge and corner detection

Adaptive Multi-Stage 2D Image Motion Field Estimation

EE795: Computer Vision and Intelligent Systems

Mosaics. Today s Readings

The SIFT (Scale Invariant Feature

Computer Vision for HCI. Motion. Motion

Optical flow. Cordelia Schmid

Local Grouping for Optical Flow

Mariya Zhariy. Uttendorf Introduction to Optical Flow. Mariya Zhariy. Introduction. Determining. Optical Flow. Results. Motivation Definition

What have we leaned so far?

Learning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009

Solution: filter the image, then subsample F 1 F 2. subsample blur subsample. blur

Technion - Computer Science Department - Tehnical Report CIS

Motion. 1 Introduction. 2 Optical Flow. Sohaib A Khan. 2.1 Brightness Constancy Equation

Announcements. Computer Vision I. Motion Field Equation. Revisiting the small motion assumption. Visual Tracking. CSE252A Lecture 19.

Computer Vision I - Basics of Image Processing Part 2

Local Image Features

Optical Flow Estimation with CUDA. Mikhail Smirnov

CS5670: Computer Vision

EE795: Computer Vision and Intelligent Systems

Global Flow Estimation. Lecture 9

Autonomous Navigation for Flying Robots

Feature Based Registration - Image Alignment

Kanade Lucas Tomasi Tracking (KLT tracker)

Comparison Between The Optical Flow Computational Techniques

Local Image Features

Motion Estimation with Adaptive Regularization and Neighborhood Dependent Constraint

All good things must...

Image stitching. Announcements. Outline. Image stitching

Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting

Robust Model-Free Tracking of Non-Rigid Shape. Abstract

CS4670: Computer Vision

CS 565 Computer Vision. Nazar Khan PUCIT Lectures 15 and 16: Optic Flow

arxiv: v1 [cs.cv] 2 May 2016

Salient Region Extraction for 3D-Stereoscopic Images

Transcription:

Optical Flow CS 637 Fuxin Li With materials from Kristen Grauman, Richard Szeliski, S. Narasimhan, Deqing Sun

Motion and perceptual organization Sometimes, motion is the only cue

Motion and perceptual organization Sometimes, motion is the foremost cue

Motion and perceptual organization Even impoverished motion data can evoke a strong percept

Motion and perceptual organization Even impoverished motion data can evoke a strong percept

Motion estimation: Optical flow Will start by estimating motion of each pixel separately Then will consider motion of entire image

Image Warping non-parametric Specify more detailed warp function Examples: splines triangles optical flow (per-pixel motion) 2/1/2005 Motion estimation 7

Image Warping non-parametric Move control points to specify spline warp 2/1/2005 Motion estimation 8

Local Patch Analysis How certain are the motion estimates? CSE 576, Spring 2008 Motion estimation 9

The aperture problem Perceived motion

The aperture problem Actual motion

The barber pole illusion http://en.wikipedia.org/wiki/barberpole_illusion

The barber pole illusion http://en.wikipedia.org/wiki/barberpole_illusion

Aperture Problem in Real Life 14

Human Motion System Illusory Snakes 15

Why estimate motion? Lots of uses Track object behavior Correct for camera jitter (stabilization) Align images (mosaics) 3D shape reconstruction Special effects

Problem definition: optical flow How to estimate pixel motion from image H to image I? Solve pixel correspondence problem given a pixel in H, look for nearby pixels of the same color in I Key assumptions color constancy: a point in H looks the same in I For grayscale images, this is brightness constancy small motion: points do not move very far This is called the optical flow problem

Local Patch Analysis How certain are the motion estimates? CSE 576, Spring 2008 Motion estimation 18

Two Directions of Estimating Optical Flow Consider 2D motion field as projections of 3D scene flow Lucas-Kanade algorithm Scene Flow Cost Volume Processing (CVPR 2017 paper) Will talk about in the second part of the course Don t care about 3D, directly estimate 2D motion Horn-Schunck Classic-NL EpicFlow, FlowFields etc.

20 Horn & Schunck algorithm Regularize for ill conditioned areas of the image. ( ) + + = j i ij v ij j u i I j i I E, 2 2 1, ), ( ), ( ), ( min v u v u Initial cost (Color constancy) ( ) ] ) ( ) ( ) ( ) [( ), ( ), ( ), ( 2, 1, 2, 1, 2, 1, 2, 1,, 2 2 1 j i j i j i j i j i j i j i j i j i ij ij v v v v u u u u v j u i I j i I E + + + + + + = + + + + λ v u Unary + pairwise!

Dense Optical Flow ~ Michael Black s method Michael Black took this one step further, starting from the regularized cost: E( u, v) = i, j ( ) 2 I ( i, j) I ( i + u, j + v ) + λρ( u, ) 1 2 ij ij v He replaced the inner distance metric, a quadradic: with a Lorentzian robust regularization: E( u, v) = Ψ i, j ( I ( i, j) I ( i + u, j + v )) + λρ( u, ) 1 2 ij ij v Where Ψ looks something like Basically, one could say that Black s method adds ways to handle occlusion, non-common fate, and temporal dislocation 21

Example

Optical Flow Result

Low Texture Region - Bad gradients have small magnitude

Edges so,so (aperture problem) large gradients, all the same

High Textured Region - Good gradients are different, large magnitudes

Secrets of Optical Flow Estimation Paper Deqing Sun s paper in CVPR 2010 tests many variants of this approach Sun, Roth and Black. Secrets of Optical Flow Estimation and Their Principles. CVPR 2010

Coarse-to-Fine In a coarse layer Compute flow Median filter (Wedel et al. 2008) Warp the 2 nd image Upsample Compute flow Median Filter

1 st : Loss Function Tested Charbonnier (L1) (Classic-C) L2 (HS) Lorentzian (Classic-L) Results:

2 nd : Features for the Loss Color constancy Gradient constancy Gaussian + XY constancy i, j + ψ i, j (8 variants tested in the paper) ( I1 ( i, j) I 2( i + uij, j v ij )) ( di ( i, j) di ( i + u, j ) ψ + i, j ψ 2 + i, j 1 ij v ij ) ( I1( i, j) I 2( i + uij, j + vij )) + ψ ( dx1( i, j) dx2( i + uij, j + vij )) ψ ( dy ( i, j) dy ( i + u, j + v )) 1 2 ij ij i, j

3 rd : Interpolation In optical flow one needs to find image intensity/gradient values of non-integral image points Authors found bi-cubic interpolation of both the image and its derivative image is better than bi-linear interpolation or bi-cubic interpolation of the image only Among trials of 7-8 things

4 th : GNC Graduated non-convexity A continuation method to solve the non-convex optimization 3 stages (Quadratic loss EE qq, quadratic + L1 loss 1 2 (EE qq + EE), then EE Without this performance is significantly worse Quadratic helps improve the diagonal of the Hessian, hence problem being more likely to be convex

5 th : More Loss Functions Generalized Charbonnier ρρ xx = xx 2 + εε 2 αα

6 th : Coarse-to-Fine and Median Filtering Coarse-to-Fine estimation (standard approach) Important step in upsampling Median filtering

What s going on in Median Filtering? 5x5 median filtering imposes smoothness constraints over 5x5 region A more connected graph than the original 4-connected! Median is related to L1 optimization (Lee and Osher 2009) New Fully-Connected Term

Convert to auxiliary flow field Split variables into 2 sets Introduce an auxiliary flow field for the new regularization term Proximal point method Allows approaches such as ADMM Improve convexity from the quadratic term

Problem with Median Filtering Oversmoothing in sharp regions Solution: weighted median filtering Represents how similar II(ii, jj) is to II(ii, jjj)

After adding weights Weighted median filtering improves results significantly

More ablation experiments Reconfirms that LAB is the best color space (0.221 error) Color difference most important in weighted median filtering

Qualitative Results

More Qualitative Results

Take-home Many computer vision common-place tricks Coarse-to-fine Filtering Robust loss function Non-local neighborhoods Weighted (regularization only on the same object) Tricks, tricks and more tricks Edge-aware smoothing important in computer vision