KNIGHT: Object Detection and Tracking in (2008)
Surveillance Videos, Yun Zhai, Khurram Shafique, Aniket Vartak, Mubarak Shah
Abstract. In this paper, we present KNIGHT, a Windows-based standalone object detection and tracking software, which is built upon Microsoft Windows technologies, including MFC and DirectShow SDK....
Trajectory Association Across Multiple Airborne Cameras (2008)
Yaser Ajmal Sheikh, Mubarak Shah
A camera mounted on an aerial vehicle provides an excellent means to monitor large areas of a scene. Utilizing several such cameras on different aerial vehicles allows further flexibility, in terms...
Automatic Segmentation of High-Throughput RNAi Fluorescent Cellular Images (2008)
Pingkum Yan, Xiaobo Zhou, Mubarak Shah
Abstract—High-throughput genome-wide RNA interference (RNAi) screening is emerging as an essential tool to assist biologists in understanding complex cellular processes. The large number of images...
Jingen Liu, Yusuf Aytar, Bilal Orhan, Jenny Han, Mubarak Shah
In this paper, we describe our approaches and experiments in semantic video classification (high-level features extraction) and fully automatic topic search tasks of TRECVID 2007. We designed a...
University of Central Florida at TRECVID 2006 High-Level Feature Extraction and Video Search (2008)
Jingen Liu, Yun Zhai, Arslan Basharat, Bilal Orhan, Saad M. Khan, Humera Noor, ...
In this paper, we describe our experiments in high-level features extraction and interactive topic search tasks of TRECVID 2006. We designed a unified high-level features extraction framework for the...
AUTOMATIC VISUAL TRACKING FOR ANALYSIS OF LIFTING (2008)
This paper presents the tracking and analysis of lifting. Included in this paper is tracking along important regions of the body such as the torso. We propose a method which detects improper and...
Person and Vehicle Tracking in Surveillance Video (2008)
Andrew Miller, Arslan Basharat, Yn White, Jingen Liu, Mubarak Shah
This evaluation for person and vehicle tracking in surveillance presented some
appearance, shape, illumination, background, view point and scale of the object that result in enormous intra-class variations. An efficient detector should factor out as many of these variations as...
1 Introduction Video Understanding and Content-Based Retrieval (2008)
Yun Zhai, Jingen Liu, Xiaochun Cao, Arslan Basharat, Asaad Hakeem, Saad Ali, ...
Determining Scale and Sea State From Water Video (2008)
Lisa Spencer, Student Member, Mubarak Shah, Ratan K. Guha
Abstract—In most image processing and computer vision applications, real-world scale can only be determined when calibration information is available. Dynamic scenes further complicate most...
Spatio–temporal regularity flow (SPREF): Its Estimation and applications (2008)
Orkun Alatas, Pingkun Yan, Mubarak Shah
Abstract—Feature selection and extraction is a key operation in video analysis for achieving a higher level of abstraction. In this paper, we introduce a general framework to extract a new...
DOI 10.1007/s00138-006-0021-7 ORIGINAL PAPER Computer vision for nanoscale imaging (2008)
Eraldo Ribeiro, Mubarak Shah, E. Ribeiro (b
Abstract The main goal of Nanotechnology is to analyze and understand the properties of matter at the atomic and molecular level. Computer vision is rapidly expanding into this new and exciting field...
MVA manuscript No. (will be inserted by the editor) Layer-Based Video Registration (2008)
Abstract Registration of a mission video sequence with a reference image with-out any meta data (camera location, viewing angles, and reference DEMs) is still a challenging problem. This paper...
Estimating Geospatial Trajectory of a Moving Camera (2008)
Asaad Hakeem, Roberto Vezzani, Mubarak Shah, Rita Cucchiara
This paper proposes a novel method for estimating the geospatial trajectory of a moving camera. The proposed method uses a set of reference images with known GPS (global positioning system) locations...
AUTOMATIC QUERY EXPANSION FOR NEWS VIDEO RETRIEVAL ABSTRACT (2008)
Yun Zhai, Jingen Liu, Mubarak Shah
In this paper, we present an integrated system for news video retrieval. The proposed system incorporates both speech and visual information in the search mechanisms. The initial search is based on...
PEGASUS: An Information Mining System for TV News Videos. (2008)
Jingen Liu, Yun Zhai, Mubarak Shah
Content-based video retrieval (CBVR) problems have gained significant importance in today’s intelligence world demanding further insight. Compared to the traditional video indexing systems, CBVR...
Fahd Rafi, Saad Khan, Khurram Shafiq, Mubarak Shah
In this paper we present an algorithm for the autonomous navigation of an unmanned aerial vehicle (UAV) following a moving target. The UAV in consideration is a fixed wing aircraft that has physical...
Asaad Hakeem, Khurram Shafique, Mubarak Shah
This paper presents a novel object-based video coding framework for videos obtained from a static camera. As opposed to most existing methods, the proposed method does not require explicit 2D or 3D...
WHERE WAS THE PICTURE TAKEN: IMAGE LOCALIZATION IN ROUTE PANORAMAS USING EPIPOLAR GEOMETRY (2008)
Saad M. Khan, Fahd Rafi, Mubarak Shah
Finding the location where a picture was taken is an important problem for a variety of applications including surveying, interactive traveling and homeland security among others. The task becomes...
MAHALANOBIS OF LOCKHEED MARTIN CORP. Targets (2008)
Arslan Basharat, Asaad Hakeem, Mubarak Shah, Automatic Target
detection and recognition for video sensors requires a different method for each class of topology. Video sensor networks play a vital role in unattended wide-area surveillance. Most computer vision...
Automatic visual recognition of armed robbery (2008)
We propose a method by which to analyze silhouettes and recognize a classic holdup position of armed robbery. In such a situation, one actor levels his or her arm while another actor raises his or...
Video Scene Segmentation Using Markov (2008)
Chain Monte Carlo, Yun Zhai, Student Member, Mubarak Shah
Abstract—Videos are composed of many shots that are caused by different camera operations, e.g., on/off operations and switching between cameras. One important goal in video analysis is to group...
Jiangjian Xiao, Major Professor, Mubarak Shah, C Jiangjian Xiao
This dissertation deals with the image-based approach to synthesize a virtual scene using sparse images or a video sequence without the use of 3D models. In our scenario, a real dy-namic or static...
1 Introduction University of Central Florida at TRECVID 2004 (2008)
Yun Zhai, Xiaochun Cao, Yunjun Zhang, Omar Javed, Alper Yilmaz, Fahd Rafi, ...
3D Model based Object Class Detection in An Arbitrary View (2008)
Pingkun Yan, Saad M. Khan, Mubarak Shah
In this paper, a novel object class detection method based on 3D object modeling is presented. Instead of using a complicated mechanism for relating multiple 2D training views, the proposed method...
A homographic framework for the fusion of multi-view silhouettes (2008)
Saad M. Khan, Pingkun Yan, Mubarak Shah
This paper presents a purely image-based approach to fusing foreground silhouette information from multiple arbitrary views. Our approach does not require 3D constructs like camera calibration to...
Automatic Segmentation of High Throughput RNAi Fluorescent Cellular Images (2008)
Pingkun Yan, Xiaobo Zhou, Mubarak Shah
Abstract — High throughput genome-wide RNAi screening is emerging as an essential tool to assist biologists in understanding complex cellular processes. The large number of images produced in each...
Resolving Hand Over Face Occlusion (2008)
Abstract. This paper presents a method to segment the hand over complex backgrounds, such as the face. The similar colors and texture of the hand and face make the problem particularly challenging....
A Vision-Based System for a UGV to Handle a Road Intersection (2008)
Javed Ahmed, Mubarak Shah, Andrew Miller, Don Harper, M. N. Jafri
We propose a real-time computer vision system that enables a UGV to safely cross urban road-intersections. Specifically, when the UGV approaches the stop sign at a 4-way intersection, it must be...
IMPROVING SEMANTIC CONCEPT DETECTION AND RETRIEVAL USING CONTEXTUAL ESTIMATES (2008)
Yusuf Aytar, O. Bilal Orhan, Mubarak Shah
In this paper we introduce a novel contextual fusion method to improve the detection scores of semantic concepts in images and videos. Our method consists of three phases. For each individual...
Asaad Hakeem, Khurram Shafique, Mubarak Shah
This paper presents a novel object-based video coding framework for videos obtained from a static camera. As opposed to most existing methods, the proposed method does not require explicit 2D or 3D...
0 An Object-based Video Coding Framework for Video Sequences Obtained From Static Cameras (2008)
Khurram Shafique, Asaad Hakeem, Mubarak Shah, Khurram Shafique, Asaad Hakeem, Mubarak Shah
This paper presents a novel object-based video coding framework for videos obtained from a static camera. As opposed to most existing methods, the proposed method does not require explicit 2D or 3D...
Learning a$ne transformations (2008)
George Bebis, Michael Georgiopoulos, Mubarak Shah
Under the assumption of weak perspective, two views of the same planar object are related through an a$ne transformation. In this paper, we consider the problem of training a simple neural network to...
The main goal of Nanotechnology is to analyze and understand the properties of matter at the atomic and molecular level. Computer vision is rapidly expanding into this new and exciting field of...
Contexts for Tracking and Re-Acquiring Targets in Aerial Videos, IEEE (2008)
Resume Saad Ali, Saad Ali, Vladimir Reilly, Mubarak Shah, Saad Ali, Mubarak Shah, ...
BACHELOR THESIS: Developing Collective Intelligence in a Colony of Robots Using Neuro-Evolution RESEARCH INTERESTS Various areas of my interests in the field of Computer Vision are: � Surveillance,...
Ruo Zhang, Ruo Zhang, Ping-sing Tsai, Ping-sing Tsai, Mubarak Shah, Mubarak Shah
Traditional shape from shading techniques, using a single image, do not reconstruct accurate surfaces, and have difficulty with shadow areas. Traditional shape from photometric stereo techniques have...
We present a general approach to determine 3D motion and structure of multiple objects undergoing arbitrary motions. We segment the scene based on 3D motion parameters. First, the general motion...
To appear in VISION, IMAGE AND SIGNAL PROCESSING. Visual Gesture Recognition (2007)
This paper presents a method for recognizing human-hand gestures using a model-based approach. A nite state machine is used to model four qualitatively distinct phases of a generic gesture....
A Computer Vision Framework for Analyzing Projections from Video of Lectures (2007)
Michael Wallick Niels, Mubarak Shah
The overhead and computer projectors have become an essential element to the classroom and corporate settings. Users of web-based classes and conferences would like to have access to the projector...
Cen Rao, Alper Yilmaz, Mubarak Shah
Abstract. Analysis of human perception of motion shows that information for representing the motion is obtained from the dramatic changes in the speed and direction of the trajectory. In this paper,...
Alper Yilmaz, Khurram Shafique, Mubarak Shah
In this paper, we propose a robust approach for tracking targets in forward-looking infrared (FLIR) imagery taken from an airborne moving platform. First, the targets are detected using fuzzy...
ARTICLE NO. IV980679 Indexing Based on Algebraic Functions of Views (2007)
George Bebis, Michael Georgiopoulos, Mubarak Shah
In this paper, we propose the use of algebraic functions of views for indexing-based object recognition. During indexing, we consider groups of model points and we represent all the views (i.e.,...
Abstract Obtaining Body Measurements for Human Identification (2007)
David B. Bracewell, Mubarak Shah
We describe a method of human identification through relevant body measurements using a static camera. A minimal amount of calibration information about the camera’s scene is needed in order to...
Network Video Image Processing for Security, Surveillance, and (2007)
Situational Awareness Abhijit, Abhijit Mahalanobis, Jamie Cannon, S. Robert, Stanfill Robert Muise, Mubarak Shah
Lockheed Martin and the University of Central Florida (UCF) are jointly investigating the use of a network of COTS video cameras and computers for a variety of security and surveillance operations....
Is there a Primal Face of Pain? A methodology answer (2007)
Cité Internationale Lyon, Martin Schiavenato, Jacqueline Byers, Paul Scovanner, Piotr Windyga, Mubarak Shah
Abstract — Pain assessment is of high priority in the clinical setting. Facial Pain Scales (FPSs) are pain assessment tools generally used with school-aged children. The implicit theoretical bases...
M.: Automatically tuning background subtraction parameters using particle swarm optimization (2007)
A common trait of background subtraction algorithms is that they have learning rates, thresholds, and initial values that are hand-tuned for a scenario in order to produce the desired subtraction...
Content Based Video Matching Using Spatiotemporal Volumes (2007)
Arslan Basharat, Yun Zhai, Mubarak Shah
This paper presents a novel framework for matching video sequences using the spatiotemporal segmentation of videos. Instead of using appearance features for region matching across frames, we use...
Javed Ahmed, M. N. Jafri, Rawalpindi Pakistan, Mubarak Shah, Muhammad Akbar
We present a robust framework for a real-time visual tracking system, based on a BPNN-controlled fast normalized correlation (BCFNC) algorithm and a predictive open-loop car-following control...
Learning, detection and representation of multi-agent events in videos (2007)
In this paper, we model multi-agent events in terms of a temporally varying sequence of sub-events, and propose a novel approach for learning, detecting and representing events in videos. The...
Segmentation of Neighboring Structures by Modeling Their Interaction (2006)
The similarity of pixel intensities, presence of noise, existence of partial volume effect and so on make segmentation of neighboring structures in medical image a challenging task. In this paper, we...
Video compression using spatio– temporal regularity flow (2006)
Orkun Alatas, Omar Javed, Mubarak Shah
Abstract—We propose a new framework in wavelet video coding to improve the compression rate by exploiting the spatiotemporal regularity of the data. A sequence of images creates a spatiotemporal...
Abstract. Occlusion and lack of visibility in dense crowded scenes make it very difficult to track individual people correctly and consistently. This problem is particularly hard to tackle in single...
Video Scene Segmentation Using Markov Chain Monte Carlo (2006)
Monte Carlo, Yun Zhai, Student Member, Mubarak Shah
Abstract — Videos are composed of many shots that are caused by different camera operations, e.g., on/off operations and switching between cameras. One important goal in video analysis is to group...
Technical Report Spatiotemporal Regularity Flow (SPREF): Its Estimation and Applications (2006)
Orkun Alatas, Pingkun Yan, Mubarak Shah
Feature selection and extraction is a key operation in video analysis for achieving higher level of abstraction. In this report, we introduce a general framework to extract a new spatiotemporal...
Abstract Integrating multiple levels of zoom to enable activity analysis (2006)
In this paper, we present a multi-zoom framework for activity analysis in situations requiring combinations of both detailed and coarse views of the scene. The epipolar geometry is employed in...
Paul Smith, Major Professors, Mubarak Shah
In this thesis we present a system for detection of events in video. First we propose a multiview approach to automatically detect, track, and consistently label heads, hands, and other objects...
Bayesian modeling of dynamic scenes for object detection (2005)
Accurate detection of moving objects is an important precursor to stable tracking or recognition. In this paper, we present an object detection scheme that has three innovations over existing...
A Non-Iterative Greedy Algorithm for Multi-frame Point Correspondence (2005)
Khurram Shafique, Mubarak Shah
This paper presents a framework for finding point correspondences in monocular image sequences over multiple frames. The general problem of multi-frame point correspondence is NP Hard for three or...
Segmentation of Neighboring Organs in Medical Image With Model Competition (2005)
Pingkun Yan, Weijia Shen, Ashraf A. Kassim, Mubarak Shah
This paper presents a novel approach for image segmentation by introducing competition between neighboring shape models. Our method is motivated by the observation that evolving neighboring contours...
Temporalboost for event recognition (2005)
This paper contributes a new boosting paradigm to achieve detection of events in video. Previous boosting paradigms in vision focus on single frame detection and do not scale to video events. Thus...
A multi-level framework for video shot structuring (2005)
Abstract. Video shots provide the most basic meaningful segments for video analysis and understanding. In this paper, we present a detection and classification framework for the video shot...
Abstract. Registration of a mission video sequence with a reference image without any metadata (camera location, viewing angles, and reference DEMs) is still a challenging problem. This paper...
Xiaochun Cao, Yuping Shen, Mubarak Shah, Hassan Foroosh, X. Cao, Y. Shen, ...
Matting and compositing are important operations in the production of special effects [7]. During matting, foreground objects are extracted from a single image or video sequence. During compositing,...
Bayesian modeling of dynamic scenes for object detection (2005)
Yaser Sheikh, Student Member, Mubarak Shah
Abstract—Accurate detection of moving objects is an important precursor to stable tracking or recognition. In this paper, we present an object detection scheme that has three innovations over...
Accurate motion layer segmentation and matting (2005)
Given a video sequence, obtaining accurate layer segmentation and alpha matting is very important for various applications. However, when a non-textured or smooth area is present in the scene, the...
Motion layer based object removal in videos (2005)
Yunjun Zhang, Jiangjian Xiao, Mubarak Shah
This paper proposes a novel method to generate plausible video sequences after removing relatively large objects from the original videos. In order to maintain temporal coherence among the frames, a...
A Non-Iterative Greedy Algorithm for Multi-frame Point Correspondence (2005)
Khurram Shafique, Student Member, Mubarak Shah
Abstract—This paper presents a framework for finding point correspondences in monocular image sequences over multiple frames. The general problem of multiframe point correspondence is NP-hard for...
Automatic segmentation of home videos (2005)
Temporal video segmentation is one of the fundamental and essential tasks in video processing, understanding and management. In this paper, we present an automatic method for segmenting the home...
Adaptive Region-Based Video Registration (2005)
Jiangjian Xiao, Yunjun Zhang, Mubarak Shah
Video registration without meta data (camera location, viewing angles, and reference DEMs) is still a challenging problem. With the aim of handling this kind of problem, this paper presents an...
In this paper we present a multi-zoom framework for activity analysis in situations requiring combinations of both detailed and coarse views of the scene. The epipolar geometry is employed in several...
Story segmentation in news videos using visual and textual cues (2005)
Yun Zhai, Alper Yilmaz, Mubarak Shah
Abstract. In this paper, we present a framework for segmenting the news programs into different story topics. The proposed method utilizes both visual and text information of the video. We represent...
Contour-Based Object Tracking with Occlusion Handling in Video Acquired Using Mobile Cameras (2004)
Abstract—We propose a tracking method which tracks the complete object regions, adapts to changing visual features, and handles occlusions. Tracking is achieved by evolving the contour from frame...
University of central florida at trecvid 2004 (2004)
Yun Zhai, Zeeshan Rasheed, Mubarak Shah
In this paper, we describe the methods for shotboundary detection, story segmentation, and feature extraction developed at the Computer Vision Laboratory, UCF, for TRECVID 2003 forum. To detect shot...
Compressed Spatio-temporal Descriptors for Video Matching and (2004)
Orkun Alatas, Omar Javed, Mubarak Shah
The contents of a video can be described in terms of appearance and motion of the scenes. In this paper, we propose wavelet-based appearance descriptors and splinebased motion descriptors that can...
Jiangjian Xiao, Major Professor, Mubarak Shah
c ○ 2004 by Jiangjian Xiao This dissertation deals with the image-based approach to synthesize a virtual scene using sparse images or a video sequence without the use of 3D models. In our scenario,...
Automatic Target Recognition Using Multi-View Morphing (2004)
This paper describes a novel approach to automatically recognize the target based on a view morphing database constructed by our multi-view morphing algorithm. Instead of using single reference...
Integrating and employing multiple levels of zoom for activity recognition (2004)
To facilitate activity recognition, analysis of the scene at multiple levels of detail is necessary. Required prerequisites for our activity recognition are tracking objects across frames and...
Object contour tracking using level sets (2004)
Alper Yilmaz, Xin Li, Mubarak Shah
Abstract — High level vision tasks (recognition, understanding, etc.) for video processing require tracking of the complete contour of the objects. In general, objects undergo non-rigid...
A Hierarchical Event Representation for the Analysis of Videos (2004)
Asaad Hakeem, Yaser Sheikh, Mubarak Shah
A representational gap exists between low-level measurements (segmentation, object classification, tracking) and high-level understanding of video sequences. In this paper, we propose a novel...
Finite State Machines in Movie Scene Classification (2004)
Yun Zhai, Zeeshan Rasheed, Mubarak Shah
In this paper, we address the problem of the scene classifications in feature films and propose a robust framework for the stated problem. The framework utilizes the structural information of the...
Aligning `dissimilar' Images Directly (2004)
This paper introduces a hierarchical algorithm for the registration of corresponding images that do not necessarily have strong global similarity, such as multi-modal images, images with varying...
Khurram Shafique, Mubarak Shah
The mapping that relates the image irradiance to the image brightness (intensity) is known as the Radiometric Response Function or Camera Response Function. This usually unknown mapping is nonlinear...
This paper presents an e#cient image-based approach to navigate a scene based on only three wide-baseline uncalibrated images without the explicit use of a 3D model. After automatically recovering...
Contour-Based Object Tracking with Occlusion Handling in Video Acquired Using Mobile Cameras (2004)
Abstract—We propose a tracking method which tracks the complete object regions, adapts to changing visual features, and handles occlusions. Tracking is achieved by evolving the contour from frame...
Motion layer extraction in the presence of occlusion using graph cut (2004)
Extracting layers from video is very important for video representation, analysis, compression, and synthesis. Assuming that a scene can be approximately described by multiple planar regions, this...
A Probabilistic Framework For Object Recognition In Video (2004)
Omar Javed Mubarak, Omar Javed, Mubarak Shah
We propose a solution to the problem of object recognition given a continuous video sequence containing multiple views of an object. Initially, object models are acquired from images of the objects...
Ontology and Taxonomy Collaborated Framework for Meeting Classification (2004)
A framework for classification of meeting videos is proposed in this paper. Our goal is to utilize this framework to analyze human motion data to perform automatic meeting classification. We use a...
Region Completion in a Single Image (2004)
Yunjun Zhang, Jiangjian Xiao, Mubarak Shah
Natural images and Photographs sometimes may contain stains or undesired objects covering significant portions of the images. Region completion is a method to fill in such significant portions of an...
Motion Layer Extraction in the Presence of Occlusion using Graph Cut (2004)
Extracting layers from video is very important for video representation, analysis, compression, and recognition. Assuming that a scene can be approximately described by multiple planar regions, this...
Visual Monitoring of Railroad Grade Crossing (2004)
Yaser Sheikh, Yun Zhai, Khurram Shafique, Mubarak Shah
There are approximately 261,000 rail crossings in the United States according to the studies by the National Highway Tra#c Safety Administration (NHTSA) and Federal Railroad Administration (FRA)....
A Framework for Semantic Classification of Scenes Using Finite State Machines (2004)
Yun Zhai, Zeeshan Rasheed, Mubarak Shah
We address the problem of classifying scenes from feature films into semantic categories and propose a robust framework for this problem. We propose that the Finite State Machines (FSM) are suitable...
Review of computer vision education (2003)
George Bebis, Dwight Egbert, Mubarak Shah
Abstract—Computer vision is becoming a mainstream subject
Two-Frame Wide Baseline Matching (2003)
This paper describes a novel approach to automatically recover corresponding feature points and epipolar geometry over two wide baseline frames. Our contributions consist of several aspects: First,...
View-invariant alignment and matching of video sequences (2003)
Cen Rao, Alexei Gritai, Mubarak Shah
In this paper, we propose a novel method to establish temporal correspondence between the frames of two videos. The 3D epipolar geometry is used to eliminate the distortion generated by the...
Consistent labeling of tracked objects in multiple cameras with overlapping fields of view (2003)
In this paper, we address the issue of tracking moving objects in an environment covered by multiple uncalibrated cameras with overlapping fields of view, typical of most surveillance setups. In such...
Consistent labeling of tracked objects in multiple cameras with overlapping fields of view (2003)
Abstract—In this paper, we address the issue of tracking moving objects in an environment covered by multiple uncalibrated cameras with overlapping fields of view, typical of most surveillance...
M-KNIGHT: a real time surveillance system for multiple overlapping and nonoverlapping cameras (2003)
Omar Javed, Zeeshan Rasheed, Orkun Alatas, Mubarak Shah
In this paper, we present a wide area surveillance system that detects, tracks and classifies moving objects across multiple cameras. At the single camera level, tracking is performed using a voting...
Semantic Film Preview Classification Using Low-Level Computable Features (2003)
Zeeshan Rasheed Yaser, Yaser Sheikh, Mubarak Shah
This paper presents a framework for the classification of feature films into genres, based on computable visual cues. The authors view the work as a step towards high-level semantic film...
KNIGHT^M: A Multi-Camera Surveillance System (2003)
In this paper, we present an automated wide area surveillance system that detects, tracks, classifies moving objects across multiple cameras. In addition, it detects unusual activities carried out by...
Determining Driver Visual Attention with One Camera (2003)
Paul Smith, Student Member, Mubarak Shah
This paper presents a system for analyzing human driver visual attention. The system relies on estimation of global motion and color statistics to robustly track a person's head and facial...
A Non-Iterative Greedy Algorithm for Multi-frame Point Correspondence (2003)
Khurram Shafique, Mubarak Shah
This paper presents a framework for finding point correspondences in monocular image sequences over multiple frames. The general problem of multi-frame point correspondence is NP Hard for three or...
Determining Driver Visual Attention with One Camera (2003)
Paul Smith, Student Member, Mubarak Shah
This paper presents a system for analyzing human driver visual attention. The system relies on estimation of global motion and color statistics to robustly track a person's head and facial...
Review of Computer Vision Education (2003)
George Bebis Member, George Bebis, Dwight Egbert, Senior Member, Mubarak Shah
Computer vision is becoming a mainstream subject of study in computer science and engineering. With the rapid explosion of multimedia and the extensive use of video and image-based communications...
Tracking Across Multiple Cameras With Disjoint Views (2003)
Omar Javed Zeeshan, Omar Javed, Zeeshan Rasheed, Khurram Shafique, Mubarak Shah
Conventional tracking approaches assume proximity in space, time and appearance of objects in successive observations. However, observations of objects are often widely separated in time and space...
On the Use of Computable Features for Film Classification (2003)
Zeeshan Rasheed, Yaser Sheikh, Student Member, Student Member, Mubarak Shah
This paper presents a framework for the classification of feature films into genres, based only on computable visual cues. We view the work as a step towards high-level semantic film interpretation,...
Abstract. Computer vision is gradually making the transition from image understanding to video understanding. This is due to the enormous success in analyzing sequences of images that has been...
View-invariant Alignment and Matching of Video Sequences (2003)
Cen Rao, Alexei Gritai, Mubarak Shah, Tanveer Syeda-mahmood
In this paper, we propose a novel method to establish temporal correspondence between the frames of two videos. 3D epipolar geometry is used to eliminate the distortion generated by the projection...
Two-Frame Wide Baseline Matching (2003)
Jiangjian Xiao Mubarak, Mubarak Shah
This paper describes a novel approach to automatically recover corresponding feature points and epipolar geometry over two wide baseline frames. Our contributions consist of several aspects: First,...
A Graph Theoretic Approach for Scene Detection in Produced Videos (2003)
E#cient video browsing requires indexing of videos so that the users can quickly locate the segments of their interests. While browsing a video, the users often prefer to skim through the video by...
Target tracking in airborne forward looking infrared imagery (2003)
Alper Yilmaz, Khurram Shafique, Mubarak Shah
In this paper, we propose a robust approach for tracking targets in forward looking infrared (FLIR) imagery taken from an airborne moving platform. First, the targets are detected using fuzzy...
A Bayesian Approach to Object Contour Tracking Using Level Sets (2003)
Alper Yilmaz Xin, Xin Li, Mubarak Shah
High level vision tasks (recognition, understanding, etc.) for video processing require tracking of the complete contour of the objects. In general, objects undergo non-rigid deformations, which...
From Images to Video: View Morphing of Three Images (2003)
This paper presents a novel image-based approach to generate a video of a scene based on only three wide-baseline uncalibrated images without the use of a 3D model. After automatically recovering an...
Invariance in Motion Analysis of Videos (2003)
Cen Rao, Mubarak Shah, Tanveer Syeda-Mahmood
In this paper, we propose an approach that retrieves motion of objects from the videos based on the dynamic time warping of view invariant characteristics. The motion is represented as a sequence of...
View-invariant alignment and matching of video sequences (2003)
Cen Rao, Alexei Gritai, Mubarak Shah, Tanveer Syeda-mahmood
In this paper, we propose a novel method to establish temporal correspondence between the frames of two videos. 3D epipolar geometry is used to eliminate the distortion generated by the projection...
Estimation of rigid and non-rigid facial motion using anatomical face model (2002)
Alper Yilmaz, Khurram Shafique, Mubarak Shah
We present a model-based approach to recover the rigid and non-rigid facial motion parameters in video sequences. Our face model is based on anatomically motivated muscle actuator controls to model...
Estimation of Arbitrary Albedo and Shape from Shading for Symmetric Objects (2002)
In this paper, we propose a shape from shading (SFS) approach to recover both the shape and the reflectance properties of symmetric objects using a single image. The common constraint of constant or...
A computer vision system for monitoring production of fast food (2002)
Richard Russo, Mubarak Shah, Niels Lobo
A system is presented for monitoring the work of a fastfood employee using a single static camera. Skin detection, shadow detection, and region-growing are used as low-level techniques in order to...
A hierarchical approach to robust background subtraction using color and gradient information (2002)
Omar Javed, Khurram Shafique, Mubarak Shah
We present a background subtraction method that uses multiple cues to robustly detect objects in adverse conditions. The algorithm consists of three distinct levels i.e pixel level, region level and...
Guest Introduction: The Changing Shape of Computer Vision in the Twenty-First Century (2002)
This paper is an important step towards generating natural language script from a video; we need to encourage this kind of work in the future
Tracking And Object Classification For (2002)
Automated Surveillance Omar, Omar Javed, Mubarak Shah
In this paper we discuss the issues that need to be resolved before fully automated outdoor surveillance systems can be developed, and present solutions to some of these problems. Any outdoor...
Person-on-Person Violence Detection in Video Data (2002)
Ankur Datta, Mubarak Shah, Niels Da
We address the problem of detecting human violence in video, such as fist fighting, kicking, hitting with objects, etc. To detect violence we rely on motion trajectory information and on orientation...
Movie Genre Classification by Exploiting Audio-Visual Features of Previews (2002)
We present a method to classify movies on the basis of audio-visual cues present in the previews. A preview summarizes the main idea of a movie providing suitable amount of information to perform the...
View Interpolation for Dynamic Scenes (2002)
Jiangjian Xiao, Cen Rao, Mubarak Shah, Short Presentations
This paper describes a novel technique for synthesizing a dynamic scene from two images without the use of a 3D model. A scene containing rigid or non-rigid objects, in which each object can move in...
Alper Yilmaz, Omar Javed, Objectvideo Inc, Mubarak Shah
The goal of this article is to review the state-of-the-art tracking methods, classify them into different categories, and identify new trends. Object tracking, in general, is a challenging problem....
Human tracking in multiple cameras (2001)
Sohaib Khan, Omar Javed, Zeeshan Rasheed, Mubarak Shah
Multiple cameras are needed to cover large environments for monitoring activity. To track people successfully in multiple perspective imagery, one needs to establish correspondence between objects...
Mentoring Undergraduates in Computer Vision Research (2001)
The future of our society will be shaped by the young and talented minds going through our colleges and universities today. During the last 14 years roughly 130 undergraduate students from several...
A framework for segmentation of interview videos (2000)
Omar Javed, Sohaib Khan, Zeeshan Rasheed, Mubarak Shah
In this paper, we present a method to remove commercials from interview videos, and to segment interviews into host or interviewee shots. In our approach, we mainly rely on information contained in...
Autonomous video registration using sensor model parameter adjustments (2000)
Richard W. Cannata, Mubarak Shah, Steven G. Blask
Recently, airborne video surveillance platforms have gained greater acceptance for use in a variety of DoD missions due to their utility, affordability and autonomy. While a variety of airborne...
Camera handoff: Tracking in multiple uncalibrated stationary cameras (2000)
Omar Javed, Sohaib Khan, Zeeshan Rasheed, Mubarak Shah
Multiple cameras are needed to completely cover an environment for monitoring activity. To track people successfully in multiple perspective imagery, one needs to establish correspondence between...
M (2000)A view-invariant representation of human action (2000)
The representation plays an important role in recognition and understanding of human action from video sequences. A view-invariant representation of action consisting of dynamic instants and...
A Tutorial on VIDEO COMPUTING ACCV-2000 (2000)
Mubarak Shah School, Mubarak Shah
Contents .Introduction .Part I: Measurement of Image Motion .Part II: Change Detection and Tracking .Part III: Video Understanding .Part IV: Video Phones and MPEG-4 Multimedia .Text .Graphics .Audio...
Tracking People in Presence of Occlusion (2000)
Tracking humans is a difficult problem because of the non-rigid nature of the human body, and the frequent occlusion encountered among people. We present a framework to track multiple people in a...
A Virtual 3D Blackboard: 3D Finger Tracking using a Single Camera (2000)
Andrew Wu Mubarak, Andrew Wu, Mubarak Shah
We present a method for tracking the 3D position of a finger, using a single camera placed several meters away from the user. After skin detection, we use motion to identify the gesticulating arm....
Monitoring Head/Eye Motion for Driver Alertness with One Camera (2000)
We describe a system for analyzing human driver alertness. It relies on optical flow and color predicates to robustly track a person's head and facial features. Our system classifies rotation in...
Shape from Shading: A Survey (1999)
Ruo Zhang, Ping-sing Tsai, James Edwin Cryer, Mubarak Shah
this paper, six well-known SFS algorithms are implemented and compared. The performance of the algorithms was analyzed on synthetic images using mean and standard deviation of depth (Z) error, mean...
Toward 3-D Gesture Recognition (1999)
This paper presents a glove-free method for tracking hand movements using a set of 3-D models. In this approach, the hand is represented by five cylindrical models which are fit to the third...
Shape from Shading: A survey (1999)
Ruo Zhang, Ping-sing Tsai, James Edwin Cryer, Mubarak Shah
Since the rst shape-from-shading (SFS) technique was developed by Horn in the early 1970s, many di erent approaches have emerged. In this paper, six well-known SFS algorithms are imple-mented and...
Learning affine transformations (1999)
George Bebis, Michael Georgiopoulos, Mubarak Shah, Dr. George Bebis
Under the assumption of weak perspective, two views of the same planar object are related through an affine transformation. In this paper, weconsider the problem of training a simple neural network...
Indexing Based on Algebraic Functions of Views (1998)
George Bebis, Michael Georgiopoulos, Mubarak Shah
this paper, we propose the use of algebraic functions of views for indexing-based object recognition. During indexing, we consider groups of model points and we represent all the views (i.e., images)...
Visually Recognizing Speech Using Eigensequences (1997)
Nan Li, Shawn Dettmer, Mubarak Shah
this paper we use the spatiotemporal eigen decomposition, in which the set of eigenvectors span the space of all possible sequences.
INTRODUCTION AND A PERSPECTIVE MUBARAK SHAH Computer Vision Lab Computer ScienceDepartment University of Central Florida Orlando, FL 32816 AND RAMESH JAIN Electrical and Computer Engineering...
Recovering 3D Motion of Multiple Objects (1997)
Using Adaptive Hough, Tina Yu Tian, Mubarak Shah
We present a method to determine 3D motion and structure of multiple objects from two perspective views, using adaptive Hough transform. In our method, segmentation is determined based on a 3D...
James Edwin Cryer, Ping-sing Tsai, Mubarak Shah
Abstract--Stereo algorithms suffer from the lack of local surface texture due to smoothness of depth constraint, or local miss-matches in disparity estimates. Thus, most stereo methods only provide a...
Lipreading using eigensequences (1995)
Nan Li, Shawn Dettmer, Mubarak Shah
To enable computer systems to recognize meaningful lip movements is a potential means to let computers interact naturally with people. We consider the problem of recognizing spoken English alphabet,...
Motion-Based Recognition: A Survey (1995)
Motion perception and interpretation plays an important role in the human visual system. It helps us recognize different objects and their motion in a scene, infer their relative depth, their...
A Survey of Motion Analysis from Moving Light Displays (1994)
Motion-based recognition deals with the recognition of objects or motions directly from the motion information extracted from a sequence of images. There are two main steps in this approach. The...
Analysis of shape from shading techniques (1994)
Ruo Zhang, Ping-sing Tsai, James Edwin Cryer, Mubarak Shah
Since the first shape-from-shading technique was developed by Horn in the early 1970s, different approaches have been continuously emerging in the past two decades. Some of them improve existing...
Estimating 3d motion and shape of multiple objects using hough transform (1994)
We present a robust method to determine 3D motion and structure of multiple objects. Rather than segmenting the scene containing multiple motions using 2D parametric model, we use the general 3D...
James Davis, James Davis, Mubarak Shah, Mubarak Shah
This paper presents a method for recognizing human-hand gestures using a model-based approach. A finite state machine is used to model four qualitatively distinct phases of a generic gesture....
Recognizing Hand Gestures (1994)
. This paper presents a method for recognizing human-hand gestures using a model-based approach. A Finite State Machine is used to model four qualitatively distinct phases of a generic gesture....
Determining 3-D Hand Motion (1994)
This paper presents a glove-free method for tracking hand movements using a set of 3-D models. In this approach, the hand is represented by five cylindrical models which are fit to the third...
Visual Gesture Recognition (1994)
This paper presents a method for recognizing human-hand gestures using a model-based approach. A finite state machine is used to model four qualitatively distinct phases of a generic gesture....
Ruo Zhang, Ping-sing Tsai, Mubarak Shah
We introduce a new technique called shape from photomotion. It uses a series of 2-D Lambertian images, generated by moving a light source around a scene, to recover the depth map. In each of the...
Cyclic Motion Detection (1993)
Ping-sing Tsai, Mubarak Shah, Katharine Keiter, Katharine Keiter, Takis Kasparis, Takis Kasparis
The motion of a walking person is analyzed by examining cycles in the movement. Cycles are detected using autocorrelation and Fourier transform techniques of the smoothed spatio-temporal curvature...
Cyclic Motion Detection (1993)
Ping-sing Tsai, Mubarak Shah, Katharine Keiter, Takis Kasparis
The motion of a walking person is analyzed by examining cycles in the movement. Cycles are detected using autocorrelation and Fourier transform techniques of the smoothed spatio-temporal curvature...
Combining Shape from Shading and Stereo Using Human Vision Model (1992)
James Edwin Cryer, James Edwin Cryer, Ping-sing Tsai, Ping-sing Tsai, Mubarak Shah, Mubarak Shah
Stereo algorithms suffer from the lack of local surface texture due to smoothness of depth constraint, or local miss-matches in disparity estimates. Thus, the stereo methods only provide a coarse...
Mubarak Shah, Krishnan Rangarajan, Ping-sing Tsai
In this paper, we present a simple algorithm for selecting and linking interesting flow vectors across a sequence of frames for computing motion trajectories. We track tokens which have both...
Pulse and staircase models for detecting edges at multiple resolution (1985)
http://deepblue.lib.umich.edu/bitstream/2027.42/7546/5/bad2082.0001.001.pdf
Detecting time-varying corners (1983)
http://deepblue.lib.umich.edu/bitstream/2027.42/7545/5/bad2084.0001.001.pdf
M.: Camera calibration and light source estimation from images with shadows (1978)
In this paper, we describe how camera parameters and light source orientation can be recovered from two perspective views of a scene given only two vertical lines and their cast shadows. Compared to...
Shape From Shading Using Linear Approximation
In this paper, we present an extremely simple algorithm for shape from shading, which can be implemented in 25 lines of C code 1 . The algorithm is very fast, taking .2 seconds on a Sun...