Francesca Manerba - Academia.edu (original) (raw)

Uploads

Papers by Francesca Manerba

Proceedings of SPIE, May 30, 2003

Proceedings of SPIE, Dec 22, 2003

Les avancees en matiere d'acquisition et de stockage des donnees ont conduit a la disponibili... more Les avancees en matiere d'acquisition et de stockage des donnees ont conduit a la disponibilite de grandes bases de donnees video numeriques pour l'utilisateur grand-public. Neanmoins l'interaction avec les donnees multimedia et video en particulier necessite des outils de description, organisation et gestion de ces donnees video. La majorite des documents multimedia sont produits sous forme compressee. De plus comme les utilisateurs demandent des reponses a leur requetes les plus rapides possible, l'extraction d'information en temps reel meme si celle-ci n'est pas tres precise est devenue un objectif important. Basee sur des hypotheses formulees ci-dessus, une nouvelle tendance en matiere d'analyse pour l'indexation multimedia est parue, elle peut etre qualifiee comme paradigme de "rough indexing" ou "indexation grossiere". Nous pouvons inclure notre travail dans cette mouvance d'indexation rapide et approximative dans laquelle uniquement les donnees imprecises telles que les vecteurs du mouvement et les images DC sont exploitees pour produire une indexation fine des objets en avant-plan. Dans ce paradigme nous proposons de combiner a la fois les informations du mouvement et la segmentation basee-couleur pour extraire les objets pertinents des flux video compresses. Il peut arriver que le mouvement d'un objet soit tres similaire au mouvement de la camera ou que l'objet soit statique, aucun objet ne sera alors detecte. Neanmoins, comme un objet ne peut raisonnablement pas apparaitre et disparaitre durant une coute sequence d'images, nous proposons de filtrer les sequences d'objets le long de l'axe temporel. Pour ce faire nous proposons une modelisation de la sequence des objets par une super-quadrique. La methode proposee donne des resultats prometteurs : les rates de la detection ou les sur-detections peuvent etre corriges par la methode de filtrage spatio-temporel proposee.

Multimedia and Expo, 2007 IEEE International Conference on, 2007

In the past decades, most of the research on image and video compression has focused on addressin... more In the past decades, most of the research on image and video compression has focused on addressing highly bandwidthconstrained environments. However, for some applications of high resolution and high quality image and video compression, as the case of High Definition Television or Digital Cinema, the primary constraints are related to quality and flexibility. This paper presents a comparison, for video sequence coding, between scalable wavelet-based video codecs and the state of the art in single point encoding and it investigates the performances in terms of compression efficiency obtained using temporal decomposition with respect to pure intra coding.

Http Www Theses Fr, 2005

Indexing deals with the automatic extraction of information with the objective of automatically d... more Indexing deals with the automatic extraction of information with the objective of automatically describing and organizing the content. Thinking of a video stream, different types of information can be considered semantically important. Since we can assume that the most relevant one is linked to the presence of moving foreground objects, their number, their shape, and their appearance can constitute a good mean for content description. For this reason, we propose to combine both motion information and regionbased color segmentation to extract moving objects from an MPEG2 compressed video stream starting only considering lowresolution data. This approach, which we refer to as “rough indexing, ” consists in processing P-frame motion information first, and then in performing I-frame color segmentation. Next, since many details can be lost due to the low-resolution data, to improve the object detection results, a novel spatiotemporal filtering has been developed which is constituted by a...

This paper describes a new approach to extract foreground objects in MPEG1,2 video streams, in th... more This paper describes a new approach to extract foreground objects in MPEG1,2 video streams, in the framework of "rough indexing paradigm", that is starting from rough data obtained by only partially decoding the compressed stream. In this approach we use both P-frame motion information and I-frame colour information to identify and extract foreground objects. The particularity of our approach with regards to the state of the art methods consists in a robust estimation of camera motion and its use for localisation of real objects and filtering of parasite zones. Secondly, a spatio-temporal filtering of roughly segmented objects at DC resolution is fulfilled using motion trajectory and gaussian-like shape characteristic function. This paradigm results in content description in real time, maintaining a good level of details.

Medical Imaging 2003: Visualization, Image-Guided Procedures, and Display, 2003

Interactivity is a main requirement for D visualization of medical images in a variety of clinica... more Interactivity is a main requirement for D visualization of medical images in a variety of clinical applications. The good matching between segmentation and rendering techniques allows to design easy to use interactive systems which assist the physicians in dynamically creating and manipulating 'diagnostically relevant' images from volumetric data sets. In this work we consider the above problem within an original interactive visualization paradigm. By this paradigm we want to highlight the twofold clinical requirement of a) detecting and visualizing structures of diagnostic interest (SoDI's) and b) adding to the 3D scene some other structures to create a meaningful visual context. Being the opacity modulation of the different structures a crucial point, we propose an opacity management which reflects the paradigm ideas and operates by means of a twofold indexed look-up table (2iLUT). The 2iLUT consists of a combination of attribute based and object based opacity management and is here designed and tested in order to combine the time interaction benefits of an indexed opacity setting with the effective handling of the above classification and visualization clinical requirements.

Storage and Retrieval Methods and Applications for Multimedia 2004, 2003

In the domain of video indexing, one of the research topics is the automatic extraction of inform... more In the domain of video indexing, one of the research topics is the automatic extraction of information to reach the objective of automatically describing and organizing the content. Thinking of a video stream, different kinds of information can be taken into account, but we can suppose that most of the information is contained in the foreground objects so that number

EURASIP Journal on Advances in Signal Processing, 2008

Indexing deals with the automatic extraction of information with the objective of automatically d... more Indexing deals with the automatic extraction of information with the objective of automatically describing and organizing the content. Thinking of a video stream, different types of information can be considered semantically important. Since we can assume that the most relevant one is linked to the presence of moving foreground objects, their number, their shape, and their appearance can constitute a good mean for content description. For this reason, we propose to combine both motion information and regionbased color segmentation to extract moving objects from an MPEG2 compressed video stream starting only considering lowresolution data. This approach, which we refer to as "rough indexing," consists in processing P-frame motion information first, and then in performing I-frame color segmentation. Next, since many details can be lost due to the low-resolution data, to improve the object detection results, a novel spatiotemporal filtering has been developed which is constituted by a quadric surface modeling the object trace along time. This method enables to effectively correct possible former detection errors without heavily increasing the computational effort.

Multimedia and Expo, 2007 IEEE International Conference on, 2007

In the past decades, most of the research on image and video compression has focused on addressin... more In the past decades, most of the research on image and video compression has focused on addressing high bandwidth-constrained environments. However, for high resolution and high quality image and video compression, as in the case of high definition television (HDTV) or digital cinema (DC), the primary constraints are related to quality and flexibility. This paper presents a comparison between scalable wavelet-based video codecs and the state of the art in single point encoding and it investigates the obtainable compression efficiency when using temporal correlation with respect to pure intra coding.

Proceedings of SPIE, May 30, 2003

Proceedings of SPIE, Dec 22, 2003

Multimedia and Expo, 2007 IEEE International Conference on, 2007

Http Www Theses Fr, 2005

Medical Imaging 2003: Visualization, Image-Guided Procedures, and Display, 2003

Storage and Retrieval Methods and Applications for Multimedia 2004, 2003

EURASIP Journal on Advances in Signal Processing, 2008

Indexing deals with the automatic extraction of information with the objective of automatically d... more Indexing deals with the automatic extraction of information with the objective of automatically describing and organizing the content. Thinking of a video stream, different types of information can be considered semantically important. Since we can assume that the most relevant one is linked to the presence of moving foreground objects, their number, their shape, and their appearance can constitute a good mean for content description. For this reason, we propose to combine both motion information and regionbased color segmentation to extract moving objects from an MPEG2 compressed video stream starting only considering lowresolution data. This approach, which we refer to as "rough indexing," consists in processing P-frame motion information first, and then in performing I-frame color segmentation. Next, since many details can be lost due to the low-resolution data, to improve the object detection results, a novel spatiotemporal filtering has been developed which is constituted by a quadric surface modeling the object trace along time. This method enables to effectively correct possible former detection errors without heavily increasing the computational effort.

Multimedia and Expo, 2007 IEEE International Conference on, 2007

In the past decades, most of the research on image and video compression has focused on addressin... more In the past decades, most of the research on image and video compression has focused on addressing high bandwidth-constrained environments. However, for high resolution and high quality image and video compression, as in the case of high definition television (HDTV) or digital cinema (DC), the primary constraints are related to quality and flexibility. This paper presents a comparison between scalable wavelet-based video codecs and the state of the art in single point encoding and it investigates the obtainable compression efficiency when using temporal correlation with respect to pure intra coding.