Rama Chellappa

Followers

Following

Co-authors

Public Views

I have been involved in research and teaching in computer vision, pattern recognition, artificial intelligence and signal and image processing. I started my academic career at the University of Southern California (1981-1991) and was at the University of Maryland, College park, MD during 1991-2020. Effective August 1st, I am a Bloomberg Distinguished Professor at Johns Hopkins University with joint tenured appointments in the departments of Electrical and Computer Engineering and Biomedical Engineering (School of Medicine).

less

Interests

Uploads

Papers by Rama Chellappa

Age Estimation and Face Verification Across Aging Using Landmarks

by Pavan Turaga and Rama Chellappa

IEEE Transactions on Information Forensics and Security, 2000

ABSTRACT Age estimation and face verification across aging are important problems with a wide ran... more ABSTRACT Age estimation and face verification across aging are important problems with a wide range of applications. It is well known that age and identity information are encoded in both texture and shape of the face. Building on recent advances in landmark extraction and statistical techniques for landmark-based shape analysis, we consider these problems using facial shapes. We show that by using well-defined shape spaces and their associated geometry, one can obtain significant performance improvements in both age estimation and face verification. Toward this end, we propose to model the facial shapes as points on a Grassmann manifold. Age estimation and face verification are then considered as regression and classification problems on this manifold. Algorithms for regression and classification are designed to take into account the geometry of the underlying space. The proposed method is flexible and can be used as a standalone age estimator or classifier, and we also present methods for fusion with texture-based algorithms.

A Blur-Robust Descriptor with Applications to Face Recognition

by Pavan Turaga and Rama Chellappa

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000

Understanding the effect of blur is an important problem in unconstrained visual analysis. We add... more Understanding the effect of blur is an important problem in unconstrained visual analysis. We address this problem in the context of image-based recognition, by a fusion of image-formation models, and differential geometric tools. First, we discuss the space spanned by blurred versions of an image and then under certain assumptions, provide a differential geometric analysis of that space. More specifically, we create a subspace resulting from convolution of an image with a complete set of orthonormal basis functions of a pre-specified maximum size (that can represent an arbitrary blur kernel within that size), and show that the corresponding subspaces created from a clean image and its blurred versions are equal under the ideal case of zero noise, and some assumptions on the properties of blur kernels. We then study the practical utility of this subspace representation for the problem of direct recognition of blurred faces, by viewing the subspaces as points on the Grassmann manifold and present methods to perform recognition for cases where the blur is both homogenous and spatially varying. We empirically analyze the effect of noise, as well as the presence of other facial variations between the gallery and probe images, and provide comparisons with existing approaches on standard datasets.

Download

Statistical Computations on Grassmann and Stiefel Manifolds for Image and Video-Based Recognition

by Rama Chellappa and Pavan Turaga

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000

In this paper, we examine image and video based recognition applications where the underlying mod... more In this paper, we examine image and video based recognition applications where the underlying models have a special structure -the linear subspace structure. We discuss how commonly used parametric models for videos and image-sets can be described using the unified framework of Grassmann and Stiefel manifolds. We first show that the parameters of linear dynamic models are finite dimensional linear subspaces of appropriate dimensions. Unordered image-sets as samples from a finite-dimensional linear subspace naturally fall under this framework. We show that the study of inference over subspaces can be naturally cast as an inference problem on the Grassmann manifold.

Download

Statistical Methods on Special Manifolds for Image and Video Understanding

by Pavan Turaga and Rama Chellappa

Handbook of Statistics, 2013

A Constrained Probabilistic Petri Net Framework for Human Activity Detection in Video

by Massimiliano Albanese, Pavan Turaga, and Rama Chellappa

IEEE Transactions on Multimedia, 2000

Recognition of human activities in restricted settings such as airports, parking lots and banks i... more Recognition of human activities in restricted settings such as airports, parking lots and banks is of significant interest in security and automated surveillance systems. In such settings, data is usually in the form of surveillance videos with wide variation in quality and granularity. Interpretation and identification of human activities requires an activity model that a) is rich enough to handle complex multi-agent interactions, b) is robust to uncertainty in low-level processing and c) can handle ambiguities in the unfolding of activities. We present a computational framework for human activity representation based on Petri nets. We propose an extension -Probabilistic Petri Nets (PPN) -and show how this model is well suited to address each of the above requirements in a wide variety of settings. We then focus on answering two types of questions:

Download

Statistical Analysis on Manifolds and Its Applications to Video Analysis

by Rama Chellappa and Pavan Turaga

The analysis and interpretation of video data is an important component of modern vision applicat... more The analysis and interpretation of video data is an important component of modern vision applications such as biometrics, surveillance, motionsynthesis and web-based user interfaces. A common requirement among these very different applications is the ability to learn statistical models of appearance and motion from a collection of videos, and then use them for recognizing actions or persons in a new

Download

Learning action dictionaries from video

by Pavan Turaga and Rama Chellappa

2008 15th IEEE International Conference on Image Processing, 2008

Page 1. LEARNING ACTION DICTIONARIES FROM VIDEO Pavan Turaga and Rama Chellappa ... Let the set P... more

Blurring-invariant Riemannian metrics for comparing signals and images

by Eric Klassen, Pavan Turaga, and Rama Chellappa

2011 International Conference on Computer Vision, 2011

are by isometries, the orbits are compared via distances between orbits. We demonstrate this fram... more

Download

A Constrained Probabilistic Petri Net Framework for Human Activity Detection in Video*

by Pavan Turaga, Massimiliano Albanese, Antonio Picariello, and Rama Chellappa

IEEE Transactions on Multimedia, 2000

Download

Object Dependent Manifold Priors for Image Deconvolution

by Rama Chellappa, Pavan Turaga, and Jie Ni

Imaging and Applied Optics Congress, 2010

Deblurring is an inverse problem which has traditionally been studied from a signal processing pe... more Deblurring is an inverse problem which has traditionally been studied from a signal processing perspective. In this paper we consider the role of extra information in the form of prior knowledge of the object class to solve this problem. Specifically, we incorporate unlabeled image data of the object class, say natural images, in the form of a patch-manifold prior for the object class. The manifold is implicitly estimated from the given unlabeled data. We show how the patch manifold prior effectively exploits the availability of the sample class data for regularizing the deblurring problem.

Download

Advances in Video-Based Human Activity Analysis

by Rama Chellappa and Pavan Turaga

Advances in Computers, 2010

Videos play an ever increasing role in our everyday lives with applications ranging from news, en... more Videos play an ever increasing role in our everyday lives with applications ranging from news, entertainment, scientific research, security, and surveillance. Coupled with the fact that cameras and storage media are becoming less expensive, it has resulted in people producing more video content than ever before. Analysis of human activities in video is important for several important applications. Interpretation and identification of human activities requires approaches that address the following questions (a) what are the appropriate atomic primitives for human activities, (b) how to combine primitives to produce complex activities, (c) what are the required invariances for inference algorithms, and (d) how to build computational models for each of these. In this chapter, we provide a broad overview and discussion of these issues. We shall review state-of-the-art computer vision algorithms that address these issues and then provide a unified perspective from which specific algorithms can be derived. We will then present supporting experimental results.

Video-Based Face Recognition Algorithms

by Pavan Turaga and Rama Chellappa

Advances in Pattern Recognition, 2009

... Rama Chellappa, Manuele Bicego, and Pavan Turaga ... R. Chellappa (B) Department of Electrica... more

Moving vistas: Exploiting motion for describing scenes

by Pavan Turaga and Rama Chellappa

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

and challenging problem with wide applications. In this paper, we study the role of scene dynamic... more and challenging problem with wide applications. In this paper, we study the role of scene dynamics for improved representation of scenes. We subsequently propose dynamic attributes which can be augmented with spatial attributes of a scene for semantically meaningful categorization of dynamic scenes. We further explore accurate and generalizable computational models for characterizing the dynamics of unconstrained scenes. The large intra-class variation due to unconstrained settings and the complex underlying physics present challenging problems in modeling scene dynamics. Motivated by these factors, we propose using the theory of chaotic systems to capture dynamics. Due to the lack of a suitable dataset, we compiled a dataset of 'inthe-wild' dynamic scenes. Experimental results show that the proposed framework leads to the best classification rate among other well-known dynamic modeling techniques. We also show how these dynamic features provide a means to describe dynamic scenes with motion-attributes, which then leads to meaningful organization of the video data.

Download

Compressive Acquisition of Linear Dynamical Systems

by Pavan Turaga and Rama Chellappa

SIAM Journal on Imaging Sciences, 2013

ABSTRACT Compressive sensing (CS) enables the acquisition and recovery of sparse signals and imag... more ABSTRACT Compressive sensing (CS) enables the acquisition and recovery of sparse signals and images at sampling rates significantly below the classical Nyquist rate. Despite significant progress in the theory and methods of CS, little headway has been made in compressive video acquisition and recovery. Video CS is complicated by the ephemeral nature of dynamic events, which makes direct extensions of standard CS imaging architectures and signal models difficult. In this paper, we develop a new framework for video CS for dynamic textured scenes that models the evolution of the scene as a linear dynamical system (LDS). This reduces the video recovery problem to first estimating the model parameters of the LDS from compressive measurements and then reconstructing the image frames. We exploit the low-dimensional dynamic parameters (the state sequence) and high-dimensional static parameters (the observation matrix) of the LDS to devise a novel compressive measurement strategy that measures only the time-varying parameters at each instant and accumulates measurements over time to estimate the time-invariant parameters. This enables us to lower the compressive measurement rate considerably. We validate our approach and demonstrate its effectiveness with a range of experiments involving video recovery and scene classification.

Locally time-invariant models of human activities using trajectories on the grassmannian

by Pavan Turaga and Rama Chellappa

2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009

Human activity analysis is an important problem in computer vision with applications in surveilla... more Human activity analysis is an important problem in computer vision with applications in surveillance and summarization and indexing of consumer content. Complex human activities are characterized by non-linear dynamics that make learning, inference and recognition hard. In this paper, we consider the problem of modeling and recognizing complex activities which exhibit time-varying dynamics. To this end, we describe activities as outputs of linear dynamic systems (LDS) whose parameters vary with time, or a Time-Varying Linear Dynamic System (TV-LDS). We discuss parameter estimation methods for this class of models by assuming that the parameters are locally time-invariant. Then, we represent the space of LDS models as a Grassmann manifold. Then, the TV-LDS model is defined as a trajectory on the Grassmann manifold. We show how trajectories on the Grassmannian can be characterized using appropriate distance metrics and statistical methods that reflect the underlying geometry of the manifold. This results in more expressive and powerful models for complex human activities. We demonstrate the strength of the framework for activity-based summarization of long videos and recognition of complex human actions on two datasets. shows how KL avg varies with δ for different activities. As is evident, the statistical properties of the activity vary smoothly but significantly over time even for these simple actions. This suggests that complex human activities cannot

Download

Statistical Methods and Models for Video-Based Tracking, Modeling, and Recognition

by Pavan Turaga and Rama Chellappa

Foundations and Trends® in Signal Processing, 2009

... Institute of Technology) Vivek Goyal (MIT) Sinan Gunturk (Courant Institute) Christine Guille... more

The role of geometry in age estimation

by Pavan Turaga and Rama Chellappa

International Conference on Acoustics, Speech, and Signal Processing, 2010

Understanding and modeling of aging in human faces is an important problem in many real-world app... more Understanding and modeling of aging in human faces is an important problem in many real-world applications such as biometrics, authentication, and synthesis. In this paper, we consider the role of geometric attributes of faces, as described by a set of landmark points on the face, in age perception. Towards this end, we show that the space of landmarks can be

Download

Semantic Video Content Analysis

by Pavan Turaga and Rama Chellappa

Studies in Computational Intelligence, 2010

In recent years, there has been significant interest in the area of automatically recognizing act... more In recent years, there has been significant interest in the area of automatically recognizing activities occurring in a camera’s field of view and detecting abnormalities. The practical applications of such a system could include airport tarmac monitoring, or monitoring of activities in secure installations, to name a few. The difficulty of the problem is compounded by several factors: detection of primitive actions in spite of changes in illumination, occlusions and noise; complexmultiagent interaction;mapping of higher-level activities to lower-level primitive actions; variations in which the same semantic activity can be performed. In this chapter, we develop a theory of semantic activity analysis that addresses each of these issues in an integrated manner. Specifically, we discuss ontological representations of knowledge of a domain, integration of domain knowledge and statistical models for achieving semantic mappings, definition of logical languages to describe activities, and design of frameworks which integrate all the above aspects in a coherent way, thus laying the foundations of effective Semantic Video Content Analysis systems.

Unsupervised view and rate invariant clustering of video sequences

by Rama Chellappa and Pavan Turaga

Computer Vision and Image Understanding, 2009

Videos play an ever increasing role in our everyday lives with applications ranging from news, en... more Videos play an ever increasing role in our everyday lives with applications ranging from news, entertainment, scientific research, security and surveillance. Coupled with the fact that cameras and storage media are becoming less expensive, it has resulted in people producing more video content than ever before. This necessitates the development of efficient indexing and retrieval algorithms for video data. Most state-of-the-art techniques index videos according to the global content in the scene such as color, texture, brightness, etc. In this paper, we discuss the problem of activity-based indexing of videos. To address the problem, first we describe activities as a cascade of dynamical systems which significantly enhances the expressive power of the model while retaining many of the computational advantages of using dynamical models. Second, we also derive methods to incorporate view and rate-invariance into these models so that similar actions are clustered together irrespective of the viewpoint or the rate of execution of the activity. We also derive algorithms to learn the model parameters from a video stream and demonstrate how a single video sequence may be clustered into different clusters where each cluster represents an activity. Experimental results for five different databases show that the clusters found by the algorithm correspond to semantically meaningful activities.

Download

Face Tracking and Recognition in Video

by Pavan Turaga and Rama Chellappa

In this chapter, we describe the utility of videos in enhancing performance of image-based recogn... more In this chapter, we describe the utility of videos in enhancing performance of image-based recognition tasks. We discuss a joint tracking-recognition framework that allows for using the motion information in a video to better localize and identify the person in the video using still galleries. We discuss how to jointly capture facial appearance and dynamics to obtain a parametric representation

Download

Rama Chellappa

Uploads

Papers by Rama Chellappa

Log In