Sequential Reconstruction Segment-Wise Feature Track and Structure Updating Based on Parallax Paths Mauricio Hess-Flores 1, Mark A. Duchaineau 2, Kenneth.

Slides:



Advertisements
Similar presentations
Vanishing points  .
Advertisements

A Robust Super Resolution Method for Images of 3D Scenes Pablo L. Sala Department of Computer Science University of Toronto.
The fundamental matrix F
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.
Department of Electrical and Electronic Engineering, The University of Hong Kong, Pokfulam Road, Hong Kong Three-dimensional curve reconstruction from.
MASKS © 2004 Invitation to 3D vision Lecture 7 Step-by-Step Model Buidling.
Chapter 6 Feature-based alignment Advanced Computer Vision.
Tracking Multiple Occluding People by Localizing on Multiple Scene Planes Saad M. Khan and Mubarak Shah, PAMI, VOL. 31, NO. 3, MARCH 2009, Donguk Seo
Intelligent Systems Lab. Extrinsic Self Calibration of a Camera and a 3D Laser Range Finder from Natural Scenes Davide Scaramuzza, Ahad Harati, and Roland.
Bayesian Robust Principal Component Analysis Presenter: Raghu Ranganathan ECE / CMR Tennessee Technological University January 21, 2011 Reading Group (Xinghao.
Structure from motion.
Active Calibration of Cameras: Theory and Implementation Anup Basu Sung Huh CPSC 643 Individual Presentation II March 4 th,
Plenoptic Stitching: A Scalable Method for Reconstructing 3D Interactive Walkthroughs Daniel G. Aliaga Ingrid Carlbom
1 MURI review meeting 09/21/2004 Dynamic Scene Modeling Video and Image Processing Lab University of California, Berkeley Christian Frueh Avideh Zakhor.
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
Epipolar geometry. (i)Correspondence geometry: Given an image point x in the first view, how does this constrain the position of the corresponding point.
Structure from motion. Multiple-view geometry questions Scene geometry (structure): Given 2D point matches in two or more images, where are the corresponding.
Flexible Bump Map Capture From Video James A. Paterson and Andrew W. Fitzgibbon University of Oxford Calibration Requirement:
Lecture 11: Structure from motion CS6670: Computer Vision Noah Snavely.
Planar Matchmove Using Invariant Image Features Andrew Kaufman.
Multiple View Geometry Marc Pollefeys University of North Carolina at Chapel Hill Modified by Philippos Mordohai.
Lecture 12: Structure from motion CS6670: Computer Vision Noah Snavely.
3-D Scene u u’u’ Study the mathematical relations between corresponding image points. “Corresponding” means originated from the same 3D point. Objective.
EE392J Final Project, March 20, Multiple Camera Object Tracking Helmy Eltoukhy and Khaled Salama.
Automatic Camera Calibration
Metric Self Calibration From Screw-Transform Manifolds Russell Manning and Charles Dyer University of Wisconsin -- Madison.
Path-Based Constraints for Accurate Scene Reconstruction from Aerial Video Mauricio Hess-Flores 1, Mark A. Duchaineau 2, Kenneth I. Joy 3 Abstract - This.
Lecture 11 Stereo Reconstruction I Lecture 11 Stereo Reconstruction I Mata kuliah: T Computer Vision Tahun: 2010.
WP3 - 3D reprojection Goal: reproject 2D ball positions from both cameras into 3D space Inputs: – 2D ball positions estimated by WP2 – 2D table positions.
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
Geometry and Algebra of Multiple Views
1 Preview At least two views are required to access the depth of a scene point and in turn to reconstruct scene structure Multiple views can be obtained.
The Brightness Constraint
Course 12 Calibration. 1.Introduction In theoretic discussions, we have assumed: Camera is located at the origin of coordinate system of scene.
3D SLAM for Omni-directional Camera
Flow Separation for Fast and Robust Stereo Odometry [ICRA 2009]
MESA LAB Multi-view image stitching Guimei Zhang MESA LAB MESA (Mechatronics, Embedded Systems and Automation) LAB School of Engineering, University of.
Visualization of Scene Structure Uncertainty in a Multi-View Reconstruction Pipeline Shawn Recker 1, Mauricio Hess- Flores 1, Mark A. Duchaineau 2, and.
An Information Fusion Approach for Multiview Feature Tracking Esra Ataer-Cansizoglu and Margrit Betke ) Image and.
Image stitching Digital Visual Effects Yung-Yu Chuang with slides by Richard Szeliski, Steve Seitz, Matthew Brown and Vaclav Hlavac.
Visibility map (high low) Surveillance with Visual Tagging and Camera Placement J. Zhao and S.-C. Cheung — Center for Visualization and Virtual Environment,
Ray Divergence-Based Bundle Adjustment Conditioning for Multi-View Stereo Mauricio Hess-Flores 1, Daniel Knoblauch 2, Mark A. Duchaineau 3, Kenneth I.
© 2005 Martin Bujňák, Martin Bujňák Supervisor : RNDr.
Communication Systems Group Technische Universität Berlin S. Knorr A Geometric Segmentation Approach for the 3D Reconstruction of Dynamic Scenes in 2D.
A Flexible New Technique for Camera Calibration Zhengyou Zhang Sung Huh CSPS 643 Individual Presentation 1 February 25,
Plane-based external camera calibration with accuracy measured by relative deflection angle Chunhui Cui , KingNgiNgan Journal Image Communication Volume.
Feature Matching. Feature Space Outlier Rejection.
FREE-VIEW WATERMARKING FOR FREE VIEW TELEVISION Alper Koz, Cevahir Çığla and A.Aydın Alatan.
3D reconstruction from uncalibrated images
Computer vision: models, learning and inference M Ahad Multiple Cameras
High Resolution Surface Reconstruction from Overlapping Multiple-Views
Lecture 9 Feature Extraction and Motion Estimation Slides by: Michael Black Clark F. Olson Jean Ponce.
Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.
Image-Based Rendering Geometry and light interaction may be difficult and expensive to model –Think of how hard radiosity is –Imagine the complexity of.
EECS 274 Computer Vision Projective Structure from Motion.
MASKS © 2004 Invitation to 3D vision. MASKS © 2004 Invitation to 3D vision Lecture 1 Overview and Introduction.
Correspondence and Stereopsis. Introduction Disparity – Informally: difference between two pictures – Allows us to gain a strong sense of depth Stereopsis.
Zhaoxia Fu, Yan Han Measurement Volume 45, Issue 4, May 2012, Pages 650–655 Reporter: Jing-Siang, Chen.
The Brightness Constraint
Mauricio Hess-Flores1, Mark A. Duchaineau2, Kenneth I. Joy3
Epipolar geometry.
Structure from motion Input: Output: (Tomasi and Kanade)
The Brightness Constraint
Persistent Surveillance
Session: Video Analysis and Action Recognition, Friday 9 November 2012
Multiple View Geometry for Robotics
Autonomous Vehicle Competition
Persistent Surveillance
Structure from motion Input: Output: (Tomasi and Kanade)
Presentation transcript:

Sequential Reconstruction Segment-Wise Feature Track and Structure Updating Based on Parallax Paths Mauricio Hess-Flores 1, Mark A. Duchaineau 2, Kenneth I. Joy 3 Abstract - This paper presents a novel method for multi-view sequential scene reconstruction scenarios such as in aerial video, that exploits the constraints imposed by the path of a moving camera to allow for a new way of detecting and correcting inaccuracies in the feature tracking and structure computation processes. The main contribution of this paper is to show that for short, planar segments of a continuous camera trajectory, parallax movement corresponding to a viewed scene point should ideally form a scaled and translated version of this trajectory when projected onto a parallel plane. This creates two constraints, which differ from those of standard factorization, that allow for the detection and correction of inaccurate feature tracks and to improve scene structure. Results are shown for real and synthetic aerial video and turntable sequences, where the proposed method was shown to correct outlier tracks, detect and correct tracking drift, and allow for a novel improvement of scene structure, additionally resulting in an improved convergence for bundle adjustment optimization. 1,3 Institute for Data Analysis and Visualization, University of California, Davis, USA Introduction Algorithm (continued) Results Accurate 3D scene models obtained from aerial video can form a base for large- scale multi-sensor networks that support activities in detection, surveillance, tracking, registration, terrain modeling, and ultimately semantic scene analysis. Due to varying lighting conditions, occlusions, repetitive patterns and other issues, feature tracks may not be perfect and this skews subsequent calibration and structure estimation. For short, planar segments of a continuous camera trajectory, parallax movement corresponding to a viewed scene point should ideally form a scaled and translated version of this trajectory, or a parallax path, when projected onto a parallel plane. This introduces two strong constraints, which differ from classical factorization and RANSAC, that can be used to detect and correct inaccurate feature tracks, while allowing for a very simple structure computation This work was supported in part by the Department of Energy, National Nuclear Security Agency through Contract No. DE-GG52-09NA This work was performed in part under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA Lawrence Livermore National Laboratory, Livermore, CA, USA ** Each path on the reconstruction plane, computed for a given track, is placed in a position-invariant reference, where ideally each differs only by scale: I) Bundle adjustment convergence analysis. Total reprojection error ε in pixels, processing time t in seconds and iterations I of Levenberg-Marquardt, for bundle adjustment applied using the output of the proposed algorithm (PPBA) versus bundle adjustment applied using original feature tracks and structure (TBA), along with number of scene points N SP : Input images Algorithm flowchart Consensus path Locus line Scaled paths II) Drift detection and track correction results (Dinosaur dataset): Ray equation: C t = (X 0,Y 0,Z 0 ) = camera center at time t, P t + = projection matrix pseudo-inverse, x kt = pixel position for track k at time t, reconstruction plane = (A,B,C,D), Xkt = (X d,Y d,Z d ) = any 3D position along a ray Position-invariant reference Algorithm **This author is now at Google, Inc. Inaccurate dense reconstruction Parallax paths Ray-plane intersection: Initial parallax path calculation (assuming known cameras) Original parallax paths At the position-invariant reference, where paths only differ by scale s Inter and intra-camera constraints In this reference, inter-camera consensus path and intra-camera locus line constraints are defined, whose intersections (‘perfect grid’) predict how inaccurate tracks should be corrected: Top view of replicas Structure computation after k th track correction Original tracks Corrected tracks Detected drift III) Improvement in scene structure (Stockton aerial dataset): Position-invariant reference Path differences from perfect grid Original (left) versus corrected structure (right) Occlusions Repetitive patterns Camera path Structure Replica  Computed per segment, relative to an anchor frame  Corrections are concatenated across consecutive segments Perfect grid X k = computed 3D position, C 1 = anchor camera center, s k = parallax scale, T k,1 = corrected parallax path coordinates on the reconstruction plane for the anchor camera DatasetPPBA ε (px)PPBA t (s)I PP TBA ε (px)TBA t (s)ITIT N SP Stockton Stockton-dense fountain-P Dinosaur 1.208e dinoRing Palmdale Constrained paths