Joint motion estimation and layer segmentation in transparent image sequences - Application to transparent-motion-compensated noise reduction in X-ray image sequences

نویسندگان

  • Vincent Auvray
  • Jean Liénard
چکیده

This paper is concerned with the estimation of the motions and the segmentation of the spatial supports of the different layers involved in transparent X-ray image sequences. Classical motion estimation methods fail on sequences involving transparent effects since they do not explicitly model this phenomenon. We propose a method that comprises three main steps: initial block-matching for two-layer transparent motion estimation, motion clustering with 3D Hough transform, and joint transparent layer segmentation and parametric motion estimation. It is validated on synthetic and real clinical X-ray image sequences. Secondly, we derive an original transparent motion compensation method compatible with any spatio-time filtering technique. A direct transparent motion compensation method is proposed. To overcome its limitations, a novel hybrid filter is introduced which locally selects which type of motion compensation is to be carried out for optimal denoising. Convincing experiments on synthetic and real clinical images are also reported. Key-words: X-ray, Motion estimation, Motion compensation, Noise reduction, Transparent motion estimation. ∗ IRISA/INRIA, Vista Team, 35042 Rennes, France † General Electric Healthcare, Advanced Medical Application Team, 78533 Buc, France in ria -0 03 48 01 2, v er si on 1 17 D ec 2 00 8 Estimation et segmentation jointe des mouvements transparents Application au débruitage compensé en mouvement transparents de séquences d’images en rayons X Résumé : Ce document porte sur l’estimation des mouvements et la segmentation des supports spatiaux des différentes couches impliquées dans les séquences d’images transparentes par rayons X. Les méthodes d’estimation de mouvement classiques échouent sur les séquences contenant des effets de transparence puisqu’elles ne modélisent pas explicitement ce phénomène. Nous proposons une méthode qui comporte trois étapes majeures: une mise en correspondance par blocs initiale pour l’estimation locale de deux mouvements transparents, une extraction des mouvements avec une transformée de Hough 3D, et une estimation de mouvement paramétrique jointe à une segmentation en couches. La méthode est validée sur des séquences cliniques par rayons X synthétiques et réelles. D’autre part, nous introduisons une méthode originale de compensation des mouvements qui est compatible avec toute méthode de filtrage spatiotemporel. Une méthode de compensation directe des mouvements transparents est proposée. Pour dépasser ses limitations, nous introduisons un filtre hybride qui choisit localement quel type de compensation de mouvement doit être effectuée pour aboutir à un débruitage optimal. Nous présentons des résultats convaincants obtenus sur images synthétiques et réelles. Mots-clés : Rayons X, estimation de mouvement, compensation de mouvement, réduction de bruit, estimation de mouvement transparent in ria -0 03 48 01 2, v er si on 1 17 D ec 2 00 8 Joint transparent motion compensation 3

برای دانلود 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

Joint Motion Estimation and Layer Segmentation in Transparent Image Sequences - Application to Noise Reduction in X-Ray Image Sequences

This paper is concerned with the estimation of the motions and the segmentation of the spatial supports of the different layers involved in transparent X-ray image sequences. Classical motion estimation methods fail on sequences involving transparent effects since they do not explicitly model this phenomenon. We propose a method that comprises three main steps: initial blockmatching for two-lay...

متن کامل

Motion-Based Segmentation of Transparent Layers in Video Sequences

We present a method for segmenting moving transparent layers in video sequences. We assume that the images can be divided into areas containing at most two moving transparent layers. We call this configuration (which is the mostly encountered one) bi-distributed transparency. The proposed method involves three steps: initial blockmatching for two-layer transparent motion estimation, motion clus...

متن کامل

Computation Optical Flow Using Pipeline Architecture

Accurate estimation of motion from time-varying imagery has been a popular problem in vision studies, This information can be used in segmentation, 3D motion and shape recovery, target tracking, and other problems in scene analysis and interpretation. We have presented a dynamic image model for estimating image motion from image sequences, and have shown how the solution can be obtained from a ...

متن کامل

Spatio-temporal filters for transparent motion segmentation

An image is ideally a projection of the 3-D scene. However, the imaging process is always imperfect and constrained by the physical environment. This paper is concerned with image sequences acquired in such situations, the so-called transparency, for example, viewing through a window with reflections. When such situation occurs, the image sequence contains undesirable transparent motion, for ex...

متن کامل

Pseudo Zernike Moment-based Multi-frame Super Resolution

The goal of multi-frame Super Resolution (SR) is to fuse multiple Low Resolution (LR) images to produce one High Resolution (HR) image. The major challenge of classic SR approaches is accurate motion estimation between the frames. To handle this challenge, fuzzy motion estimation method has been proposed that replaces value of each pixel using the weighted averaging all its neighboring pixels i...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008