3D Reconstruction from Images：Image-based Street-side City Modeling

3D Reconstruction from Images Image-based Street-side City Modeling Paper ID:0238 2009,Siggraph A complete pipeline from pixels to finalized 3D objects through object segmentation and recognition

3D Reconstruction from Images 2009, Siggraph A complete pipeline from pixels to finalized 3D objects through object segmentation and recognition

Vision geometry Structure from motion or 3d reconstruction or sLAM EXample par excellence of modern computer vision integrating feature detection, object recognition and geometry computation ■ Camera poses Positioning visual GPs, for gPs denied environments such as indoors, cities Localization for automation by machine vision ■3 D reconstruction Obstacle avoidance, navigation, planning, and environment learning

Vision geometry ◼ Structure from motion, or 3D reconstruction, or SLAM ◼ Example par excellence of modern computer vision integrating feature detection, object recognition and geometry computation ◼ Camera poses ◼ Positioning, visual GPS, for GPS denied environments such as indoors, cities … ◼ Localization, for automation by machine vision ◼ 3D reconstruction ◼ Obstacle avoidance, navigation, planning, and environment learning

The objects of study in geometry ■ Lines to points Corners to feature points a Match correlation to descriptors of high dimension a Descriptors to recognition, beyond the geometry scope More deterministic computational models ■ Robust statistics ■ Large-scale

The objects of study in geometry ◼ Lines to points ◼ Corners to feature points ◼ Match correlation to descriptors of high dimension ◼ Descriptors to recognition, beyond the geometry scope ◼ More deterministic computational models ◼ Robust statistics ◼ Large-scale

New book Image-based modeling Long QUAN, pringer-verlag 2010

New book Image-based Modeling, Long QUAN, Springer-Verlag, 2010

My perspective Part I What is computer vision? What is 3D reconstruction? From pixels to 3D points Structure from motion A quasi-dense approach From 3D points to objects Small-scale objects Smooth surfaces. Hairs. Trees Large-scale buildings Facade, Buildings, Cities Part ll Large-scale automatic 3D mapping Conclusions

My perspective • Part I – What is computer vision? – What is 3D reconstruction? – From pixels to 3D points • Structure from motion • A quasi-dense approach – From 3D points to objects • Small-scale objects – Smooth surfaces, Hairs, Trees • Large-scale buildings – Façade, Buildings, Cities • Part II – Large-scale automatic 3D mapping • Conclusions

Overview Introduction to projective geometry I view geometry(calibration,.) 2-view geometry(stereo, motion,.) 3-and N-view geometr Autocalibration(metric reconst Application

6 Overview • Introduction to projective geometry • 1 view geometry (calibration, …) • 2-view geometry (stereo, motion, …) • 3- and N-view geometry • Autocalibration (metric reconst.) • Application

Basic geometric concepts to understand Affine Euclidean geometries (inhomogeneous coordinates) projective geometry(homogeneous coordinates) plane at infinity: attine geometry absolute conic: Euclidean geometry

7 Basic geometric concepts to understand • Affine, Euclidean geometries (inhomogeneous coordinates) • projective geometry (homogeneous coordinates) • plane at infinity: affine geometry • absolute conic: Euclidean geometry

Introduction to projective geometry Intuitive ideas from projective geometr (Formal definition of projective spaces)

8 Introduction to projective geometry • Intuitive ideas from projective geometry • (Formal definition of projective spaces)

Intuitive introduction R E=A WIth dot prod A P=R+pts at inf Naturally everything starts from the known vector space add two vector multiply any vector by any scalar zero vector - origin finite basis

9 with dot prod. n n E = A pts at inf. n n A n P = R + n R    Naturally everything starts from the known vector space • add two vectors • multiply any vector by any scalar • zero vector – origin • finite basis Intuitive introduction

Vector space to affine: isomorph, one-to-one Pts, lines, parallelism vector to Euclidean as an enrichment: scalar prod Angle, distances, circles affine to projective as an extension add ideal elements Pts at infinity

10 • Vector space to affine: isomorph, one-to-one • vector to Euclidean as an enrichment: scalar prod. • affine to projective as an extension: add ideal elements Pts, lines, parallelism Angle, distances, circles Pts at infinity