Modelling Dynamic Scenes by Registrating Multi-View Image Sequences
نویسندگان
چکیده
We present a new variational method for multi-view stereovision and non-rigid threedimensional motion estimation from multiple video sequences. Our method minimizes the prediction error of the estimated shape and motion. Both problems then translate into a generic image registration task. The latter is entrusted to a similarity measure chosen depending on imaging conditions and scene properties. In particular, our method can be made robust to appearance changes due to non-Lambertian materials and illumination changes. Our method results in a simpler, more flexible, and more efficient implementation than existing deformable surface approaches. The computation time on large datasets does not exceed thirty minutes. Moreover, our method is compliant with a hardware implementation with graphics processor units. Our stereovision algorithm yields very good results on a variety of datasets including specularities and translucency. We have successfully tested our scene flow algorithm on a very challenging multi-view video sequence of a non-rigid event. Key-words: stereovision, non-rigid 3D motion, scene flow, registration, prediction error, variational method, cross correlation, mutual information, non-Lambertian, level sets. Modélisation de Scènes Dynamiques par Recalage de Séquences d’Images Multi-Caméras Résumé : Nous présentons une nouvelle méthode variationnelle pour la stéréovision multi-caméras et l’estimation du mouvement tridimensionnel non-rigide à partir de plusieurs séquences vidéos. Notre méthode minimise l’erreur de prédiction de la forme et du mouvement estimés. Les deux problèmes se ramènent alors à une tâche générique de recalage d’images. Cette dernière est confiée à une mesure de similarité choisie en fonction des conditions de prise de vue et des propriétés de la scène. En particulier, notre méthode peut être rendue robuste aux changements d’apparence dus aux matériaux non-lambertiens et aux changements d’illumination. Notre méthode aboutit à une implémentation plus simple, plus souple et plus efficace que les approches par déformation de surface existantes. Le temps de calcul sur de gros jeux de données ne dépasse pas trente minutes. De plus, notre méthode est compatible avec une implémentation matérielle à l’aide de cartes graphiques. Notre algorithme de stéréovision donne de très bons résultats sur de nombreux jeux de données comportant des spécularités et des transparences. Nous avons testé avec succès notre algorithme d’estimation du mouvement sur une séquence vidéo multi-caméras d’une scène non-rigide. Mots-clés : stéréovision, mouvement 3D non-rigide, recalage, erreur de prédiction, méthode variationnelle, corrélation croisée, information mutuelle, non-lambertien, ensembles de niveaux. Modelling Dynamic Scenes by Registrating Multi-View Image Sequences 3
منابع مشابه
Recovery of Dynamic Scene Structure from Multiple Image Sequences
Despite significant progress in automatic recovery of static scene structure from range images, little effort has been made toward extending these approaches to dynamic scenes. This disparity is in large part due to the lack of range sensors with the high sampling rates needed to accurately capture dynamic scenes. We have developed a system that overcomes this problem by exploiting video camera...
متن کاملPhotorealistic 3-D Surface Reconstructions Using TOF Cameras
TOF (Time-of-Flight) technology enables the real-time 3-D surface reconstruction of the current field of view of a TOF camera with a constant lateral resolution. We propose algorithms for the calibration of a TOF camera which in combination with rigidly mounted standard cameras enables the photorealistic 3-D surface reconstruction of the current field of view by registrating the optical centres...
متن کاملMulti-view Synchronization of Human Actions and Dynamic Scenes
This paper deals with the temporal synchronization of image sequences. Two instances of this problem are considered: (a) synchronization of human actions and (b) synchronization of dynamic scenes with view changes. To address both tasks and to reliably handle large view variations, we use self-similarity matrices which remain stable across views. We propose time-adaptive descriptors that captur...
متن کاملSMOR: A Semantic Multi-View Object Representation System in 2D Image Sequences
In this work, we propose a framework for segmenting and tracking objects in a static scene using 2D image sequences taken from different viewpoints. The system includes the use of a set of simple algorithms to segment, identify, group and track the semantic objects modeled as a set of regions with compatible surface features. The integration of these algorithms for design of the system is the m...
متن کاملModelling Non-Rigid Dynamic Scenes from Multi-View Image Sequences
This chapter focuses on the problem of obtaining a complete spatio-temporal description of some objects undergoing a non-rigid motion, given several calibrated and synchronized videos of the scene. Using stereovision and scene flow methods in conjunction, the three-dimensional shape and the non-rigid three-dimensional motion field of the objects can be recovered. We review the unrealistic photo...
متن کامل