Tracking Persons-of-Interest via Unsupervised Representation Adaptation

Multi-face tracking in unconstrained videos is a challenging problem as faces of one person often appear drastically
different in multiple shots due to significant variations in scale, pose, expression, illumination, and make-up. Existing multi-target tracking methods often use low-level features which are not sufficiently discriminative for identifying faces with such large appearance variations. Read More “Tracking Persons-of-Interest via Unsupervised Representation Adaptation”

Low-level multiscale video segmentation

Unsupervised video segmentation is a challenging problem because it involves a large amount of data, and image segments undergo noisy variations in color, texture and motion with time. However, there are significant redundancies that can help disambiguate the effects of noise. To exploit these redundancies and obtain the most spatio-temporally consistent video segmentation, we formulate the problem as a consistent labeling problem by exploiting higher order image structure. Read More “Low-level multiscale video segmentation”

Isotropy Based Clustering and Application to Image Segmentation

We present a novel scale adaptive, non-parametric approach to clustering point patterns. Clusters are detected by moving all points to their cluster cores using shift vectors. First, we propose a novel scale selection criterion based on local density isotropy which determines the neighborhoods over which the shift vectors are computed. We then construct a directed graph induced by these shift vectors. Read More “Isotropy Based Clustering and Application to Image Segmentation”

Low-level multiscale image segmentation

This research theme is concerned with the problem of low level image segmentation, or partitioning an image into regions, that represent low level image structure. A region is characterized as possessing a certain degree of interior homogeneity and a contrast with the surround which is large compared to the interior variation. Read More “Low-level multiscale image segmentation”

Estimation and Segmentation of Images Using Parametric Image Models

Statistical models

Statistical models of pixel value variations have been developed and analyzed. Some of the work focuses on kernel density estimators to develop such models. Consequently, statistical theory of density estimators can be used for various tasks including segmentation of locally/globally parametric image signals; scale estimation and object registration. The main projects of this sub-theme are “Bandwidth Selection for Kernel Density Estimators” and “Estimation and Segmentation of Images Using Parametric Image Models” detailed below. Read More “Estimation and Segmentation of Images Using Parametric Image Models”

Bandwidth Selection for Kernel Density Estimators

Statistical models

Statistical models of pixel value variations have been developed and analyzed. Some of the work focuses on kernel density estimators to develop such models. Consequently, statistical theory of density estimators can be used for various tasks including segmentation of locally/globally parametric image signals; scale estimation and object registration. The main projects of this sub-theme are “Bandwidth Selection for Kernel Density Estimators” and “Estimation and Segmentation of Images Using Parametric Image Models” detailed below. Read More “Bandwidth Selection for Kernel Density Estimators”