Surface Flow from Visual Cues
نویسندگان
چکیده
In this paper we study the estimation of dense, instantaneous 3D motion fields over non-rigidly moving surface observed by multi-camera systems. The motivation arises from multi-camera applications that require motion information for arbitrary subjects, in order to perform tasks such as surface tracking or segmentation. To this aim, we present a novel framework that allows to efficiently compute dense 3D displacement fields using low level visual cues and geometric constraints. The main contribution is a unified framework that combines flow constraints for small displacements with temporal feature constraints for large displacements and fuses them over the surface using local rigidity constraints. The resulting linear optimization problem allows for variational solutions and fast implementations. Experiments conducted on synthetic and real data demonstrate the respective interests of flow and feature constraints as well as their efficiency to provide robust surface motion cues when combined. Key-words: Surface, flow, 3D motion in ria -0 05 93 20 6, v er si on 2 17 M ay 2 01 1 Flot de surface à partir d’indices visuels Résumé : Dans ce papier nous nous intéressons à l’estimation des champs de déplacement denses d’une surface non rigide, en mouvement, capturée par un système multi-caméra. La motivation vient des applications multi-caméra qui nécessitent une information de mouvement pour accomplir des tâches telles que le suivi de surface ou la segmentation. Dans cette optique, nous présentons une approche nouvelle, qui permet de calculer efficacement un champ de déplacement 3D, en utilisant des informations visuelles de bas niveau et des contraintes géométriques. La contribution principale est la proposition d’un cadre unifié qui combine des contraintes de flot pour de petits déplacements et des correspondances temporelles éparses pour les déplacements importants. Ces deux types d’informations sont fusionnés sur la surface en utilisant une contrainte de rigidité locale. Le problème se formule comme une optimisation linéaire permettant une implémentation rapide grâce à une approche variationelle. Les expérimentations menées sur des données synthétiques et réelles démontrent les intérêts respectifs du flot et des informations éparses, ainsi que leur efficacité conjointe pour calculer les déplacements d’une surface de manière robuste. Mots-clés : Surface, flot, déplacements 3D in ria -0 05 93 20 6, v er si on 2 17 M ay 2 01 1 Surface Flow from Visual Cues 3
منابع مشابه
Perceived afterimage size in depth cue-conflict condition
In depth cue-conflict conditions, various depth cues could represent different extents of depth. Previous studies have investigated the perceived size of negative afterimage in depth cue-correlated conditions in which different cues introduce almost the same amounts of depth to the visual system. This study examined the perceived size of the afterimage in the human observers in a condition that...
متن کاملPerceived afterimage size in depth cue-conflict condition
In depth cue-conflict conditions, various depth cues could represent different extents of depth. Previous studies have investigated the perceived size of negative afterimage in depth cue-correlated conditions in which different cues introduce almost the same amounts of depth to the visual system. This study examined the perceived size of the afterimage in the human observers in a condition that...
متن کاملDesigning and Evaluation of Reliability and Validity of Visual Cue-Induced Craving Assessment Task for Methamphetamine Smokers
A B S T R A C TIntroduction: Craving to methamphetamine is a significant health concern and exposure to methamphetamine cues in laboratory can induce craving. In this study, a task designing procedure for evaluating methamphetamine cue-induced craving in laboratory conditions is examined. Methods: First a series of visual cues which could induce craving was identified by 5 discussion sessions b...
متن کاملHuman visual cortical responses to specular and matte motion flows
Determining the compositional properties of surfaces in the environment is an important visual capacity. One such property is specular reflectance, which encompasses the range from matte to shiny surfaces. Visual estimation of specular reflectance can be informed by characteristic motion profiles; a surface with a specular reflectance that is difficult to determine while static can be confident...
متن کاملOptical-flow based self-supervised learning of obstacle appearance applied to MAV landing
Monocular motion cues have been widely used by Micro Air Vehicles (MAVs) to detect obstacles during visual navigation. However, this approach requires significant movement, which reduces the efficiency of navigation and may even introduce risks in narrow spaces. In this paper, we introduce a novel setup of self-supervised learning (SSL), in which motion cues serve as a scaffold to learn the vis...
متن کاملذخیره 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 2011