Irfan Essa’s Academic Activities

• R. Hamid, S. Maddi, A. Bobick, I. Essa (2007). Structure from Statistics - Unsupervised Activity Analysis using Suffix Trees, At theInternational Conference on Computer Vision 2007. October 2007, Rio de Janeiro, BRAZIL

Abstract

Models of activity structure for unconstrained environments are generally not available a priori. Recent representational approaches to this end are limited by their computational complexity, and ability to capture activity structure only up to some fixed temporal scale. In this work, we propose Suffix Trees as an activity representation to efficiently extract structure of activities by analyzing their constituent event-subsequences over multiple temporal scales. We empirically compare Suffix Trees with some of the previous approaches in terms of feature cardinality, discriminative prowess, noise sensitivity and activity-class discovery. Finally, exploiting properties of Suffix Trees, we present a novel perspective on anomalous subsequences of activities, and propose an algorithm to detect them in linear-time. We present comparative results over experimental data, collected from a kitchen environment to demonstrate the competence of our proposed framework.

• R. Hamid, S. Maddi, A. Bobick, I. Essa. “Unsupervised Analysis of Activity Sequences Using Event Motifs”, In proceedings of 4th ACM International Workshop on Video Surveillance and Sensor Networks (in conjunction with ACM Multimedia 2006).

Abstract

We present an unsupervised framework to discover characterizations of everyday human activities, and demonstrate how such representations can be used to extract points of interest in event-streams. We begin with the usage of Suffix Trees as an efficient activity-representation to analyze the global structural information of activities, using their local event statistics over the entire continuum of their temporal resolution. Exploiting this representation, we discover characterizing event-subsequences and present their usage in an ensemble-based framework for activity classification. Finally, we propose a method to automatically detect subsequences of events that are locally atypical in a structural sense. Results over extensive data-sets, collected from multiple sensor-rich environments are presented, to show the competence and scalability of the proposed framework.

Learning Temporal Sequence Model from Partially Labeled Data (IEEEXplore)

Yifan Shi Bobick, A. Essa, I.
Georgia Institute Of Technology, Atalanta
This paper appears in: Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on
Publication Date: 2006
Volume: 2
On page(s): 1631 - 1638
ISSN: 1063-6919
ISBN: 0-7695-2597-0
Digital Object Identifier: 10.1109/CVPR.2006.174
Posted online: 2006-10-09 11:11:21.0

Abstract

Graphical models are often used to represent and recognize activities. Purely unsupervised methods (such as HMMs) can be trained automatically but yield models whose internal structure - the nodes - are difficult to interpret semantically. Manually constructed networks typically have nodes corresponding to sub-events, but the programming and training of these networks is tedious and requires extensive domain expertise. In this paper, we propose a semi-supervised approach in which a manually structured, Propagation Network (a form of a DBN) is initialized from a small amount of fully annotated data, and then refined by an EM-based learning method in an unsupervised fashion. During node refinement (the M step) a boosting-based algorithm is employed to train the evidence detectors of individual nodes. Experiments on a variety of data types - vision and inertial measurements - in several tasks demonstrate the ability to learn from as little as one fully annotated example accompanied by a small number of positive but non-annotated training examples. The system is applied to both recognition and anomaly detection tasks.

Vivek Kwatra, Irfan Essa, Aaron Bobick, and Nipun Kwatra (2005), “Texture optimization for example-based synthesis” In ACM Transactions on Graphics (TOG) Volume 24 , Issue 3 (July 2005) Proceedings of ACM SIGGRAPH 2005, Pages: 795 - 802, ISSN:0730-0301 (DOI|PDF|Project Site|Video|Talk)

ABSTRACT

We present a novel technique for texture synthesis using optimization. We define a Markov Random Field (MRF)-based similarity metric for measuring the quality of synthesized texture with respect to a given input sample. This allows us to formulate the synthesis problem as minimization of an energy function, which is optimized using an Expectation Maximization (EM)-like algorithm. In contrast to most example-based techniques that do region-growing, ours is a joint optimization approach that progressively refines the entire texture. Additionally, our approach is ideally suited to allow for controllable synthesis of textures. Specifically, we demonstrate controllability by animating image textures using flow fields. We allow for general two-dimensional flow fields that may dynamically change over time. Applications of this technique include dynamic texturing of fluid animations and texture-based flow visualization.

Propagation networks for recognition of partially ordered sequential action (IEEEXplore)

Yifan Shi Yan Huang Minnen, D. Bobick, A. Essa, I.
GVU Center, Georgia Inst. of Technol., Atlanta, GA, USA
This paper appears in: Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on
Publication Date: 27 June-2 July 2004
Volume: 2
On page(s): II-862 - II-869 Vol.2
Number of Pages: 2001
ISSN: 1063-6919
ISBN: 0-7695-2158-4
INSPEC Accession Number:8161557
Digital Object Identifier: 10.1109/CVPR.2004.1315255
Posted online: 2004-07-19 11:09:30.0

Abstract

We present propagation networks (P-nets), a novel approach for representing and recognizing sequential activities that include parallel streams of action. We represent each activity using partially ordered intervals. Each interval is restricted by both temporal and logical constraints, including information about its duration and its temporal relationship with other intervals. P-nets associate one node with each temporal interval. Each node is triggered according to a probability density function that depends on the state of its parent nodes. Each node also has an associated observation function that characterizes supporting perceptual evidence. To facilitate real-time analysis, we introduce a particle filter framework to explore the conditional state space. We modify the original condensation algorithm to more efficiently sample a discrete state space (D-condensation). Experiments in the domain of blood glucose monitor calibration demonstrate both the representational power of P-nets and the effectiveness of the D-condensation algorithm.

Vivek Kwatra, Arno Schödl, Irfan Essa, Greg Turk, Aaron Bobick (2003), “Graphcut textures: image and video synthesis using graph cuts” In ACM Transactions on Graphics (TOG), Volume 22 , Issue 3, Proceedings of ACM SIGGRAPH 2003, Pages: 277 - 286, July 2003, ISSN:0730-0301. (DOI|Paper| SIGGRAPH Video (160 MB, 50 MB) | Video Results 87 MB | Project Site)

ABSTRACT

In this paper we introduce a new algorithm for image and video texture synthesis. In our approach, patch regions from a sample image or video are transformed and copied to the output and then stitched together along optimal seams to generate a new (and typically larger) output. In contrast to other techniques, the size of the patch is not chosen a-priori, but instead a graph cut technique is used to determine the optimal patch region for any given offset between the input and output texture. Unlike dynamic programming, our graph cut technique for seam optimization is applicable in any dimension. We specifically explore it in 2D and 3D to perform video texture synthesis in addition to regular image synthesis. We present approximative offset search techniques that work well in conjunction with the presented patch size optimization. We show results for synthesizing regular, random, and natural images and videos. We also demonstrate how this method can be used to interactively merge different images to generate new scenes.

Award#0121661 - ITR/SY: The Aware Home: Sustaining the Quality of Life for an Aging Population
ABSTRACT

This is a standard award. The focus of this project is on development of a domestic environment that is cognizant of the whereabouts and activities of its occupants and can support them in their everyday life. While the technology is applicable to a range of domestic situations, the emphasis in this work will be on support for aging in place; through collaboration with experts in assistive care and cognitive aging, the PI and his team will design, demonstrate, and evaluate a series of domestic services that aim to maintain the quality of life for an aging population, with the goal of increasing the likelihood of a “stay at home” alternative to assisted living that satisfies the needs of an aging individual and his/her distributed family. In particular, the PI will explore two areas that are key to sustaining quality of life for an independent senior adult: maintaining familial vigilance, and supporting daily routines. The intention is to serve as an active partner, aiding the senior occupant without taking control. This research will lead to advances in three research areas: human-computer interaction; computational perception; and software engineering. To achieve the desired goals, the PI will conduct the research and experimentation in an authentic domestic setting, a novel research facility called the Residential Laboratory recently completed next to the Georgia Tech campus. Together with experts in theoretical and practical aspects of aging, the PI will establish a pattern of research in which informed design of ubiquitous computing technology can be rapidly deployed, evaluated and evolved in an authentic setting. Special attention will be paid throughout to issues relating to privacy and trust implications. The PI will transition the products of this project to researchers and practitioners interested in performing more large-scale observations of the social and economic impact of Aware Home technologies.