Dense reconstruction from uncalibrated video

                     Martin Bujnak

This work aims to create complete 3D reconstruction of real scene from
uncalibrated video sequence. It deals with image features
correspondence problem reduced to feature tracking throughout image
sequence, camera tracking with retrieving camera positions and camera
calibration, and finally dense scene reconstruction.

Even input consists of un-calibrated images, algorithm assumes that
images were taken by camera with these restrictions to intrinsic
parameters: zero-skew, principal point is at image center and aspect
ratio of 1. Camera focal length can vary across the sequence. Images
must be processed in the order of how they were captured and motion
between two consequent frames is assumed to be small. Reconstruction
pipeline contains algorithm for filtering unsharp and redundant
images. This allows using both high frame rate and low frame rate
cameras.  Main contribution of this work is in simple feature detector
and tracker, novel fast on-line structure from motion algorithm based
on two-view geometry, dense reconstruction based on new stereo
algorithm and 3D mesh extraction. In this work I also describe linear
method for calibrating cameras only from input image
(self-calibration). Experimental method for lens radial distortion
detection based on two-view geometry is also presented here.

Keywords: 

Structure-from-motion, Uncalibrated video, Self calibration, Feature
tracking, Dense reconstruction, Sharpness and redundancy Filter