Karel Lebeda, Simon Hadfield, Richard Bowden

Slides:



Advertisements
Similar presentations
Gestures Recognition. Image acquisition Image acquisition at BBC R&D studios in London using eight different viewpoints. Sequence frame-by-frame segmentation.
Advertisements

Towards Geographical Referencing of Monocular SLAM Reconstruction Using 3D City Models: Application to Real- Time Accurate Vision-Based Localization Reporter.
Probabilistic Tracking and Recognition of Non-rigid Hand Motion
The fundamental matrix F
DDDAS: Stochastic Multicue Tracking of Objects with Many Degrees of Freedom PIs: D. Metaxas, A. Elgammal and V. Pavlovic Dept of CS, Rutgers University.
For Internal Use Only. © CT T IN EM. All rights reserved. 3D Reconstruction Using Aerial Images A Dense Structure from Motion pipeline Ramakrishna Vedantam.
EUCLIDEAN POSITION ESTIMATION OF FEATURES ON A STATIC OBJECT USING A MOVING CALIBRATED CAMERA Nitendra Nath, David Braganza ‡, and Darren Dawson EUCLIDEAN.
Tracking Learning Detection
Recent work in image-based rendering from unstructured image collections and remaining challenges Sudipta N. Sinha Microsoft Research, Redmond, USA.
Patch to the Future: Unsupervised Visual Prediction
Activity Recognition Aneeq Zia. Agenda What is activity recognition Typical methods used for action recognition “Evaluation of local spatio-temporal features.
Object Recognition & Model Based Tracking © Danica Kragic Tracking system.
Online Multiple Classifier Boosting for Object Tracking Tae-Kyun Kim 1 Thomas Woodley 1 Björn Stenger 2 Roberto Cipolla 1 1 Dept. of Engineering, University.
3D Face Modeling Michaël De Smet.
Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.
EVENTS: INRIA Work Review Nov 18 th, Madrid.
Robust Object Tracking via Sparsity-based Collaborative Model
2D Human Pose Estimation in TV Shows Vittorio Ferrari Manuel Marin Andrew Zisserman Dagstuhl Seminar July 2008.
Modeling 3D Deformable and Articulated Shapes Yu Chen, Tae-Kyun Kim, Roberto Cipolla Department of Engineering University of Cambridge.
Computer Vision REU Week 2 Adam Kavanaugh. Video Canny Put canny into a loop in order to process multiple frames of a video sequence Put canny into a.
Robust Moving Object Detection & Categorization using self- improving classifiers Omar Javed, Saad Ali & Mubarak Shah.
Adam Rachmielowski 615 Project: Real-time monocular vision-based SLAM.
Real-Time Non-Rigid Shape Recovery via AAMs for Augmented Reality Jackie Zhu Oct. 24, 2006.
Image-Based Rendering using Hardware Accelerated Dynamic Textures Keith Yerex Dana Cobzas Martin Jagersand.
CSCE 641 Computer Graphics: Image-based Modeling (Cont.) Jinxiang Chai.
Jacinto C. Nascimento, Member, IEEE, and Jorge S. Marques
1 Video Surveillance systems for Traffic Monitoring Simeon Indupalli.
Multiple View Geometry in Computer Vision Slides modified from Marc Pollefeys’ online course materials Lecturer: Prof. Dezhen Song.
Computer vision: models, learning and inference
Sequential Reconstruction Segment-Wise Feature Track and Structure Updating Based on Parallax Paths Mauricio Hess-Flores 1, Mark A. Duchaineau 2, Kenneth.
Action recognition with improved trajectories
Tracking by Sampling Trackers Junseok Kwon* and Kyoung Mu lee Computer Vision Lab. Dept. of EECS Seoul National University, Korea Homepage:
A General Framework for Tracking Multiple People from a Moving Camera
Dynamic 3D Scene Analysis from a Moving Vehicle Young Ki Baik (CV Lab.) (Wed)
What Does Motion Reveal About Transparency ? Moshe Ben-Ezra and Shree K. Nayar Columbia University ICCV Conference October 2003, Nice, France This work.
Example: line fitting. n=2 Model fitting Measure distances.
ESR 2 / ER 2 Testing Campaign Review A. CrivellaroY. Verdie.
BAGGING ALGORITHM, ONLINE BOOSTING AND VISION Se – Hoon Park.
1 Reconstructing head models from photograph for individualized 3D-audio processing Matteo Dellepiane, Nico Pietroni, Nicolas Tsingos, Manuel Asselot,
Raquel A. Romano 1 Scientific Computing Seminar May 12, 2004 Projective Geometry for Computer Vision Projective Geometry for Computer Vision Raquel A.
Sparse Bayesian Learning for Efficient Visual Tracking O. Williams, A. Blake & R. Cipolloa PAMI, Aug Presented by Yuting Qi Machine Learning Reading.
Lecture 9 Feature Extraction and Motion Estimation Slides by: Michael Black Clark F. Olson Jean Ponce.
Yannick FranckenChris HermansPhilippe Bekaert Hasselt University – tUL – IBBT Expertise Centre for Digital Media, Belgium
Automatic 3D modelling of Architecture Anthony Dick 1 Phil Torr 2 Roberto Cipolla 1 1 Department of Engineering 2 Microsoft Research, University of Cambridge.
MASKS © 2004 Invitation to 3D vision. MASKS © 2004 Invitation to 3D vision Lecture 1 Overview and Introduction.
Max-Confidence Boosting With Uncertainty for Visual tracking WEN GUO, LIANGLIANG CAO, TONY X. HAN, SHUICHENG YAN AND CHANGSHENG XU IEEE TRANSACTIONS ON.
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.
Using Clouds Shadows to Infer Scene Structure and Camera Calibration
Signal and Image Processing Lab
Paper – Stephen Se, David Lowe, Jim Little
Motion Segmentation with Missing Data using PowerFactorization & GPCA
Tracking Objects with Dynamics
L-infinity minimization in geometric vision problems.
Generalized Principal Component Analysis CVPR 2008
Object Tracking Based on Appearance and Depth Information
Modeling the world with photos
Combining Geometric- and View-Based Approaches for Articulated Pose Estimation David Demirdjian MIT Computer Science and Artificial Intelligence Laboratory.
Single Image Rolling Shutter Distortion Correction
Image processing and computer vision
Noah Snavely.
KFC: Keypoints, Features and Correspondences
Video Compass Jana Kosecka and Wei Zhang George Mason University
Part-based visual tracking with online latent structural learning -Rui Yao et al. ICCV 2013 Cvlab Jung ilchae.
Introduction to Object Tracking
SENSOR BASED CONTROL OF AUTONOMOUS ROBOTS
Unrolling the shutter: CNN to correct motion distortions
Learning complex visual concepts
Cengizhan Can Phoebe de Nooijer
INDOOR DENSE DEPTH MAP AT DRONE HOVERING
Robust Feature Matching and Fast GMS Solution
Presentation transcript:

Karel Lebeda, Simon Hadfield, Richard Bowden 2D Or Not 2D: Bridging the Gap Between Tracking and Structure from Motion Karel Lebeda, Simon Hadfield, Richard Bowden ACCV 2014

TWININGS Testing trackers since 2009 Babenko et al.: Visual Tracking with Online Multiple Instance Learning. CVPR 2009.

LIVER RUN Long-term tracking sequence Many challenges: extreme length, disappearance, varying illumination,... No significant viewpoint changes! Lebeda et al.: Long-Term Tracking through Failure Cases. VOT 2013.

MOTIVATION Real-world sequences contain out-of-plane rotations Tracker often has to rapidly learn a change in appearance... But the object does not change! Only the viewpoint has changed, why not model it explicitly?

- bringing together Tracking, SfM & SLAM TMAGIC racking, odelling Reconstruction nd aussian-process nference ombined T M A G I C - bringing together Tracking, SfM & SLAM

Three Basic Principles (I) M A G I C Tracking: - given a video-sequence and a 3D model of the object, we can estimate camera pose - model-based 3D tracking, SLAM

Three Basic Principles (II) M A G I C Modelling: - given a videosequence and the camera poses, we can estimate a feature cloud and model the shape - Structure from Motion, SLAM ...

Three Basic Principles (III) M A G I C Gaussian-process Inference: - given a video-sequence and a shape model, we can validate newly detected features

Three Basic Principles M A G I C Combined: - estimating everything simultaneously

Algorithm Overview T M GI 2D TRACKING CAMERA ESTIMATION BUNDLE ADJUSTMENT MODEL TRAINING FEATURE GENERATION T M GI

Algorithm Overview T M GI 2D TRACKING CAMERA ESTIMATION BUNDLE ADJUSTMENT MODEL TRAINING FEATURE GENERATION T M GI

2D Features & Tracking - point features (DoG+HAff) - line features (LSD) - tracked independently - geometric verification Lebeda et al.: Long-Term Tracking through Failure Cases. VOT 2013.

Algorithm Overview T M GI 2D TRACKING CAMERA ESTIMATION BUNDLE ADJUSTMENT MODEL TRAINING FEATURE GENERATION T M GI

3D Features & Camera Pose Estimation - PnP? PnL? - optimisation approach (conditional gradient method) - fixed during tracking - updating using bundle adjustment

Algorithm Overview T M GI 2D TRACKING CAMERA ESTIMATION BUNDLE ADJUSTMENT MODEL TRAINING FEATURE GENERATION T M GI

Surface Shape Modelling - Gaussian Process Regression - modelling radii - GP advantages: few training data, non-parametric, probabilistic, no over-fitting

Algorithm Overview T M GI 2D TRACKING CAMERA ESTIMATION BUNDLE ADJUSTMENT MODEL TRAINING FEATURE GENERATION T M GI

Feature Generation & Validation - tracking: only a small part of the image - back-projecting extracted features - must intersect the shape model - 3D position initialisation

Algorithm Overview T M GI 2D TRACKING CAMERA ESTIMATION BUNDLE ADJUSTMENT MODEL TRAINING FEATURE GENERATION T M GI

Outputs of the Tracker - camera trajectory - surface shape model 2D trajectory (segmentation)

Results Example

Results Example

Final Shape Model

Results - localisation error & overlap - on standard sequences comparable to SOTA (22 %) - on sequences with strong out-of-plane rotation highly superior (58 %) (out-of-plane rotations beneficial)

Summary - explicitly 3D tracker - combining approaches from tracking, SfM and SLAM - modelling the object shape as a Gaussian Process - limitations (= future work): - non-rigid objects - long-term tracking, redetection - dense reconstruction

Summary