Motion and shape recovery based on iterative stabilization for modest deviation from planar motion

Abstract

We describe an iterative stabilization method that can simultaneously recover camera motion and 3D shape from an image sequence captured under modest deviation from planar motion. This technique iteratively applies a factorization method based on planar motion and can approximate the observed image points to the 2D points projected under planar motion by stabilizing the camera motion. We apply the proposed method to aerial images acquired by a helicopter-borne camera and show better reconstruction of both motion and shape than Christy-Horaud's perspective factorization. Moreover, we confirm that the reprojection errors calculated from the recovered camera motion and 3D shape are very similar to the optimum results yielded by bundle adjustment.

Robust Factorization Methods Using a Gaussian/Uniform Mixture Model

“…Hence, the problem reduces to affine factorization followed by Euclidean upgrade. Numerous iterative algorithms have been suggested in the literature for estimating the perspectivedistortion parameters associated with each 2-D observation, both with uncalibrated and calibrated cameras (Sturm and Triggs 1996;Christy and Horaud 1996;Mahamud and Hebert 2000;Mahamud et al 2001;Miyagawa and Arakawa 2006;Oliensis and Hartley 2007) to cite just a few. One possibility is to perform weak-perspective iterations.…”

“…The generalization of affine factorization to deal with perspective implies the estimation of depth values associated with each reconstructed point. This is generally performed iteratively (Sturm and Triggs 1996;Christy and Horaud 1996;Mahamud and Hebert 2000;Mahamud et al 2001;Miyagawa and Arakawa 2006;Oliensis and Hartley 2007). It is not yet clear at all how to combine iterative robust methods with iterative projective/perspective factorization methods.…”

Robust Factorization Methods Using a Gaussian/Uniform Mixture Model

“…The generalization of affine factorization to deal with perspective implies the estimation of depth values associated with each reconstructed point. This is generally performed iteratively [37], [6], [24], [25], [29], [31]. It is not yet clear at all how to combine iterative robust methods with iterative projective/perspective factorization methods.…”

Range Identification for Perspective Vision Systems: A Position-Based Approach

“…The estimation of the range, which is an unmeasurable nonlinear signal, is usually done by mounting a camera on a moving vehicle such as an unmanned aerial vehicle (UAV) or a mobile robot that travels through the environment and takes images of static objects or features. Range identification makes significant impact on several applications including autonomous vehicle navigation, aerial tracking, path planning, surveillance of ground based, stationary or moving objects (Fukao et al, 2003;Kanade et al, 2004;Redding et al, 2006;Dobrokhodov et al, 2006) and terrain mapping systems (Kim and Sukkarieh, 2003;Jung and Lacroix, 2003;Miyagawa and Arakawa, 2006).…”