Bayesian statistical fusion models based on constraints and multiple criteria in image processing and computer vision

点击翻译按钮获取中文摘要

My research program investigates the use of new unsupervised probabilistic or energy-based fusion models for understanding, analyzing, and manipulating still, moving and multidimensional or multi-modal images. More precisely, this research program will attempt to propose new statistical models to integrate multiple (low or higher level) and complementary image cues (e.g., color, texture, edges, corner and interest point detection, symmetry detection, Gestalt laws of perceptual organization, etc.) and/or to exploit one or several low-level applications (segmentation, edge map, restored image, etc.) for the reliable estimation of a final high-level computer vision task (e.g., motion detection/segmentation, occlusion map, complex shape localization, 3D reconstruction, etc.). These problems have a wide range of applications in several fields, including multi-modal medical image applications, geoscience and hyperspectral imagery and more generally in all multi-camera or multi-modal recognition and reconstruction systems of the next generation.