DTAM: Dense Tracking and Mapping in Real-Time

Slides:



Advertisements
Similar presentations
TWO STEP EQUATIONS 1. SOLVE FOR X 2. DO THE ADDITION STEP FIRST
Advertisements

By D. Fisher Geometric Transformations. Reflection, Rotation, or Translation 1.
0 - 0.
SUBTRACTING INTEGERS 1. CHANGE THE SUBTRACTION SIGN TO ADDITION
Addition Facts
Photo Composition Study Guide Label each photo with the category that applies to that image.
Real-Time Template Tracking
Professor Horst Cerjak, Thomas Pock A Duality Based Approach for Realtime TV-L 1 Optical Flow ICG A Duality Based Approach for Realtime TV-L.
Active Appearance Models
Joint work with Andre Lieutier Dassault Systemes Domain Theory and Differential Calculus Abbas Edalat Imperial College Oxford.
A Robust Super Resolution Method for Images of 3D Scenes Pablo L. Sala Department of Computer Science University of Toronto.
Addition 1’s to 20.
Week 1.
Introduction Distance-based Adaptable Similarity Search
SURE-LET for Orthonormal Wavelet-Domain Video Denoising Florian Luisier, Member, IEEE, Thierry Blu, Senior Member, IEEE, and Michael Unser, Fellow, IEEE.
An Efficient and Fast Active Contour Model for Salient Object Detection Authors: Farnaz Shariat, Riadh Ksantini, Boubakeur Boufama
Optical Flow Estimation
CISC 489/689 Spring 2009 University of Delaware
Optimizing and Learning for Super-resolution
Various Regularization Methods in Computer Vision Min-Gyu Park Computer Vision Lab. School of Information and Communications GIST.
Investigation Into Optical Flow Problem in the Presence of Spatially-varying Motion Blur Mohammad Hossein Daraei June 2014 University.
Parallel Tracking and Mapping for Small AR Workspaces Vision Seminar
3/5/2002Phillip Saltzman Video Motion Capture Christoph Bregler Jitendra Malik UC Berkley 1997.
Computer Vision Optical Flow
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
Last Time Pinhole camera model, projection
Motion Estimation I What affects the induced image motion? Camera motion Object motion Scene structure.
Motion Detection And Analysis Michael Knowles Tuesday 13 th January 2004.
Motion Analysis (contd.) Slides are from RPI Registration Class.
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
Computing motion between images
The plan for today Camera matrix
Optical flow and Tracking CISC 649/849 Spring 2009 University of Delaware.
Motion Estimation Today’s Readings Trucco & Verri, 8.3 – 8.4 (skip 8.3.3, read only top half of p. 199) Numerical Recipes (Newton-Raphson), 9.4 (first.
Matching Compare region of image to region of image. –We talked about this for stereo. –Important for motion. Epipolar constraint unknown. But motion small.
CSCE 641 Computer Graphics: Image Registration Jinxiang Chai.
CSCE 641 Computer Graphics: Image-based Modeling (Cont.) Jinxiang Chai.
A plane-plus-parallax algorithm Basic Model: When FOV is not very large and the camera motion has a small rotation, the 2D displacement (u,v) of an image.
Generating panorama using translational movement model.
Digital Camera and Computer Vision Laboratory Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan, R.O.C.
Feature and object tracking algorithms for video tracking Student: Oren Shevach Instructor: Arie nakhmani.
1/20 Obtaining Shape from Scanning Electron Microscope Using Hopfield Neural Network Yuji Iwahori 1, Haruki Kawanaka 1, Shinji Fukui 2 and Kenji Funahashi.
KinectFusion : Real-Time Dense Surface Mapping and Tracking IEEE International Symposium on Mixed and Augmented Reality 2011 Science and Technology Proceedings.
Optical Flow Donald Tanguay June 12, Outline Description of optical flow General techniques Specific methods –Horn and Schunck (regularization)
CSCE 643 Computer Vision: Structure from Motion
Uses of Motion 3D shape reconstruction Segment objects based on motion cues Recognize events and activities Improve video quality Track objects Correct.
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
Joint Tracking of Features and Edges STAN BIRCHFIELD AND SHRINIVAS PUNDLIK CLEMSON UNIVERSITY ABSTRACT LUCAS-KANADE AND HORN-SCHUNCK JOINT TRACKING OF.
Looking at people and Image-based Localisation Roberto Cipolla Department of Engineering Research team
Bundle Adjustment A Modern Synthesis Bill Triggs, Philip McLauchlan, Richard Hartley and Andrew Fitzgibbon Presentation by Marios Xanthidis 5 th of No.
Motion Estimation I What affects the induced image motion?
Jeong Kanghun CRV (Computer & Robot Vision) Lab..
Representing Moving Images with Layers J. Y. Wang and E. H. Adelson MIT Media Lab.
Motion estimation Digital Visual Effects, Spring 2006 Yung-Yu Chuang 2005/4/12 with slides by Michael Black and P. Anandan.
Lucas-Kanade Image Alignment Iain Matthews. Paper Reading Simon Baker and Iain Matthews, Lucas-Kanade 20 years on: A Unifying Framework, Part 1
Motion estimation Digital Visual Effects, Spring 2005 Yung-Yu Chuang 2005/3/23 with slides by Michael Black and P. Anandan.
Energy minimization Another global approach to improve quality of correspondences Assumption: disparities vary (mostly) smoothly Minimize energy function:
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.
CPSC 641: Image Registration
COSC579: Image Align, Mosaic, Stitch
Motion and Optical Flow
Motion Detection And Analysis
Vision Reading Group, 2nd of May 2018 Martin Rünz
Representing Moving Images with Layers
Representing Moving Images with Layers
Announcements more panorama slots available now
Announcements Questions on the project? New turn-in info online
Announcements more panorama slots available now
Optical flow Computer Vision Spring 2019, Lecture 21
Presentation transcript:

DTAM: Dense Tracking and Mapping in Real-Time Newcombe, Lovegrove & Davison ICCV11 Amaury Dame Active Vision Lab Oxford Robotics Research Group adame@robots.ox.ac.uk

Introduction Input : Objective : Single hand held RGB camera Dense mapping Dense tracking Typical aims of surveillance: Detection of targets  Wide field of view beneficial Tracking of targets, Identification of targets  Small field of view beneficial Collaborative sensing Input image 3D dense map Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 2 Slide 2

System overview Plan : Depth map estimation : Notations, photometric error energy, TV optimisation Dense tracking Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 3 Slide 3

Depth map estimation Principle: Formulation: S depth hypothesis are considered for each pixel of the reference image Ir Each corresponding 3D point is projected onto a bundle of images Im Keep the depth hypothesis that best respects the color consistency from the reference to the bundle of images Typical aims of surveillance: Detection of targets  Wide field of view beneficial Tracking of targets, Identification of targets  Small field of view beneficial Collaborative sensing Formulation: : pixel position and depth hypothesis : number of valid reprojection of the pixel in the bundle : photometric error between reference and current image Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 4 Slide 4

Depth map estimation Reprojection in image bundle Example reference image pixel Typical aims of surveillance: Detection of targets  Wide field of view beneficial Tracking of targets, Identification of targets  Small field of view beneficial Collaborative sensing Photo error Depth hypotheses Reprojection of depth hypotheses on one image of bundle Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 5 Slide 5

Depth map filtering approach Problem: Uniform regions in reference image do not give discriminative enough photometric error Typical aims of surveillance: Detection of targets  Wide field of view beneficial Tracking of targets, Identification of targets  Small field of view beneficial Collaborative sensing Idea: Assume that depth is smooth on uniform regions Use total variational approach where depth map is the functional to optimize: photometric error defines the data term the smoothness constraint defines the regularization. Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 6 Slide 6

Depth map filtering approach Formulation: First term : regularization constraint, g is defined so that it is 0 for image gradients and 1 for uniform regions. So that gradient on depth map is penalized for uniform regions Second term : data term defined by the photometric error. Huber norm: differentiable replacement to L1 norm that better preserve discontinuities compared to L2. Typical aims of surveillance: Detection of targets  Wide field of view beneficial Tracking of targets, Identification of targets  Small field of view beneficial Collaborative sensing Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 7 Slide 7

Regularisation effect Total variational optimisation L2 norm L1 norm QU(f1)=1 QU(f2)=0.1 QU(f3)=0.01 TV(f1)=1 TV(f2)=1 TV(f3)=1 Regularisation effect Typical aims of surveillance: Detection of targets  Wide field of view beneficial Tracking of targets, Identification of targets  Small field of view beneficial Collaborative sensing Image denoising [Pock08] Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 8 Slide 8

Depth map filtering approach Formulation : Problem : optimizing this equation directly requires linearising of cost volume. Expensive and cost volume has many local minima. Typical aims of surveillance: Detection of targets  Wide field of view beneficial Tracking of targets, Identification of targets  Small field of view beneficial Collaborative sensing Approximation : Introduce as an auxiliary variable, can be optimized with heuristic search Second terms brings original and auxiliary variable together Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 9 Slide 9

Total variational optimisation Classical approaches: Time Marching Scheme: steepest descent method Linearization of the Euler-Lagrange Equation Problem: optimization badly conditioned as (uniform regions) Euler lagrange equation - Solved using Time marching scheme, similar to ;ost of approches used to solve level set methods - Solved using linearization of Euler lagrange ie Taylor expansion, result in sparse system to resolve that is usually solved using Jacobi or Gauss-Seidel methods Problem of previous solutions: degenerated as NablaU=0 Reformulation of regularization with primal dual method Dual variable p is introduced to compute the TV norm: Indeed: Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 10 Slide 10

Increasing solution accuracy ? Typical aims of surveillance: Detection of targets  Wide field of view beneficial Tracking of targets, Identification of targets  Small field of view beneficial Collaborative sensing Reminder: Before Approach: Q well modeled, perform Newton step on Q to update estimation a Equivalent to using Epsilon ? After one iteration Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 11 Slide 11

Dense tracking Inputs: Tracking as a registration problem 3D texture model of the scene Pose at previous frame Tracking as a registration problem First inter-frame rotation estimation : the previous image is aligned on the current image to estimate a coarse inter-frame rotation Estimated pose is used to project the 3D model into 2.5D image The 2.5D image is registered with the current frame to find the current pose. Euler lagrange equation - Solved using Time marching scheme, similar to ;ost of approches used to solve level set methods - Solved using linearization of Euler lagrange ie Taylor expansion, result in sparse system to resolve that is usually solved using Jacobi or Gauss-Seidel methods Problem of previous solutions: degenerated as NablaU=0 Two template matching problems Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 12 Slide 12

SSD optimisation Problem: Formulation: Hypothesis: Align template image T(x) with input image I(x). Formulation: find the transformation that best maps the pixels of the templates into the ones of the current image minimizing: are the displacement parameters to be optimized. Templates can be 2D, 2.5D, 3D as long as warp function defined to project model in 2D current image. Hypothesis: Know a coarse approximation of the template position (p0). Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 13 Slide 13

SSD optimisation Problem: Formulations: minimize The current estimation of p is iteratively updated to reach the minimum of the function. Formulations: Direct additional Direct compositional Inverse Euler lagrange equation - Solved using Time marching scheme, similar to ;ost of approches used to solve level set methods - Solved using linearization of Euler lagrange ie Taylor expansion, result in sparse system to resolve that is usually solved using Jacobi or Gauss-Seidel methods Problem of previous solutions: degenerated as NablaU=0 Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 14 Slide 14

SSD optimisation Example: Direct additive method Minimize : First order Taylor expansion: Solution: with: Euler lagrange equation - Solved using Time marching scheme, similar to ;ost of approches used to solve level set methods - Solved using linearization of Euler lagrange ie Taylor expansion, result in sparse system to resolve that is usually solved using Jacobi or Gauss-Seidel methods Problem of previous solutions: degenerated as NablaU=0 Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 15 Slide 15

SSD robustified Reminder: Method : Problem: In case of occlusion, the occluded pixels cause the optimum of the function to be changed. The occluded pixels have to be ignored from the optimization Euler lagrange equation - Solved using Time marching scheme, similar to ;ost of approches used to solve level set methods - Solved using linearization of Euler lagrange ie Taylor expansion, result in sparse system to resolve that is usually solved using Jacobi or Gauss-Seidel methods Problem of previous solutions: degenerated as NablaU=0 Method : Only the pixels with a difference lower than a threshold are selected. Threshold is iteratively updated to get more selective as the optimization reaches the optimum. Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 16 Slide 16

Template matching Applications to DTAM: First rotation estimation: the template is the previous image that is matched with current image. Warp is defined on the space of all rotations. The initial estimate of p is identity. Full pose estimation template is 2.5D, warp is defined by full 3D motion estimation, that is . The initial pose is given by the pose estimated at the previous frame and the inter frame rotation estimation. Euler lagrange equation - Solved using Time marching scheme, similar to ;ost of approches used to solve level set methods - Solved using linearization of Euler lagrange ie Taylor expansion, result in sparse system to resolve that is usually solved using Jacobi or Gauss-Seidel methods Problem of previous solutions: degenerated as NablaU=0 Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 17 Slide 17

Conclusion First live full dense reconstruction system... Limitation from the smoothness assumption on depth... Euler lagrange equation - Solved using Time marching scheme, similar to ;ost of approches used to solve level set methods - Solved using linearization of Euler lagrange ie Taylor expansion, result in sparse system to resolve that is usually solved using Jacobi or Gauss-Seidel methods Problem of previous solutions: degenerated as NablaU=0 Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 18 Slide 18

Important references [Pock Thesis08] Fast total variation for Computer Vision [Baker IJCV04] Lucas-Kanade 20 years on: A unifying framework Typical aims of surveillance: Detection of targets  Wide field of view beneficial Tracking of targets, Identification of targets  Small field of view beneficial Collaborative sensing Amaury Dame Active Vision Lab Oxford Robotics Research Group 28.02.2013 19 Slide 19