130 likes | 146 Views
Join us for a lecture on 3D vision, where we will cover the fundamental problem of reconstructing 3D scenes from images, discuss various applications such as autonomous vehicles and real-time sports coverage, and explore the general steps involved in 3D vision.
E N D
Lecture 1 Overview and Introduction Invitation to 3D vision
Reconstruction from images – The Fundamental Problem Input: Corresponding “features” in multiple perspective images. Output: Camera pose, calibration, scene structure representation. Invitation to 3D vision
APPLICATIONS – Autonomous Highway Vehicles Image courtesy of California PATH Invitation to 3D vision
Rate: 10Hz; Accuracy: 5cm, 4o APPLICATIONS – Unmanned Aerial Vehicles (UAVs) Invitation to 3D vision Courtesy of Berkeley Robotics Lab
APPLICATIONS – Real-Time Virtual Object Insertion Invitation to 3D vision UCLA Vision Lab
APPLICATIONS – Real-Time Sports Coverage First-down line and virtual advertising Invitation to 3D vision Princeton Video Image, Inc.
APPLICATIONS – Image Based Modeling and Rendering Invitation to 3D vision Image courtesy of Paul Debevec
APPLICATIONS – Image Alignment, Mosaicing, and Morphing Invitation to 3D vision
GENERAL STEPS – Feature Selection and Correspondence • Small baselines versus large baselines • Point features versus line features Invitation to 3D vision
GENERAL STEPS – Structure and Motion Recovery • Two views versus multiple views • Discrete versus continuous motion • General versus planar scene • Calibrated versus uncalibrated camera • One motion versus multiple motions Invitation to 3D vision
GENERAL STEPS – Image Stratification and Dense Matching Left Right Invitation to 3D vision
GENERAL STEPS – 3-D Surface Model and Rendering • Point clouds versus surfaces (level sets) • Random shapes versus regular structures Invitation to 3D vision