A Two-Stage Robust Statistical Method for Temporal Registration from Features of Various Type

نویسندگان

  • Gilles Simon
  • Marie-Odile Berger
چکیده

A model registration system capable of tracking an object, the model of which is known, in an image sequence is presented. It integrates tracking, pose determination and updating of the visible features. The heart of our system is the pose computation method, which handles various features (points, lines and free-form curves) in a very robust way. It consists in using robust estimators in a two-stage process: a robust residual is computed for each feature and a robust function of these residuals is minimized. Our method is therefore able to give a correct estimate of the pose even when tracking errors occur. This method is also used to update the set of model features along the sequence, by nding the 2D contours that are tracked when new 3D features become visible. The reliability of the system has been shown on a 300-image sequence of a bridge shot at dusk time, for an augmented reality project. Une m ethode statistique robuste a deux niveaux pour le recalage temporel a partir de primitives de type dii erent R esum e : Nous pr esentons un syst eme de recalage temporel 3D/ 2D, capable de suivre dans une s equence d'images un objet 3D dont le mod ele est connu. Il comporte le suivi des primitives, le calcul du point de vue et la mise a jour des primitives visibles. Le coeur de notre syst eme est la m ethode de calcul du point de vue, qui prend en compte de faa con tr es robuste des primitives de type dii erent (points, droites et courbes 3D non n ecessairement d eenies param etriquement). Cette m ethode consiste a utiliser des estimateurs robustes dans un processus a deux niveaux : un r esidu robuste est calcul e pour chaque primitive et une fonction robuste de ces r esidus est minimis ee. Notre m ethode est donc capable de donner une estimation correcte du point de vue m^ eme lorsque des erreurs de suivi se produisent. Elle est aussi utilis ee pour mettre a jour l'ensemble des primitives prises en compte sur toute la s equence, en d eterminant les contours 2D qui sont suivis lorsque de nouvelles primitives 3D apparaissent. Nous montrons la abilit e de notre syst eme dans le cadre d'un projet de r ealit e augment ee.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

DPML-Risk: An Efficient Algorithm for Image Registration

Targets and objects registration and tracking in a sequence of images play an important role in various areas. One of the methods in image registration is feature-based algorithm which is accomplished in two steps. The first step includes finding features of sensed and reference images. In this step, a scale space is used to reduce the sensitivity of detected features to the scale changes. Afterw...

متن کامل

Contourlet-Based Edge Extraction for Image Registration

Image registration is a crucial step in most image processing tasks for which the final result is achieved from a combination of various resources. In general, the majority of registration methods consist of the following four steps: feature extraction, feature matching, transform modeling, and finally image resampling. As the accuracy of a registration process is highly dependent to the fe...

متن کامل

A two-stage robust model for portfolio selection by using goal programming

In portfolio selection models, uncertainty plays an important role. The parameter’s uncertainty leads to getting away from optimal solution so it is needed to consider that in models. In this paper we presented a two-stage robust model that in first stage determines the desired percentage of investment in each industrial group by using return and risk measures from different industries. One rea...

متن کامل

Optimal Feature Extraction for Discriminating Raman Spectra of Different Skin Samples using Statistical Methods and Genetic Algorithm

Introduction: Raman spectroscopy, that is a spectroscopic technique based on inelastic scattering of monochromatic light, can provide valuable information about molecular vibrations, so using this technique we can study molecular changes in a sample. Material and Methods: In this research, 153 Raman spectra obtained from normal and dried skin samples. Baseline and electrical noise were eliminat...

متن کامل

Offline Language-free Writer Identification based on Speeded-up Robust Features

This article proposes offline language-free writer identification based on speeded-up robust features (SURF), goes through training, enrollment, and identification stages. In all stages, an isotropic Box filter is first used to segment the handwritten text image into word regions (WRs). Then, the SURF descriptors (SUDs) of word region and the corresponding scales and orientations (SOs) are extr...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1998