| Grant title: Object Detection in Naval Environments Using Information-Theoretic Approaches. |
29 Jan 2010 |
8 pages |
| Authors:
Margrit Betke; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
 | The authors have investigated image analysis methods for tracking moving objects in marine environments. They focused on information-theoretic approaches that compare image regions of interest with the statistical models of the objects to be tracked. They evaluated the tracking performance of mean-shift and block-matching algorithms on videos of waterways. It is challenging to track naval vessels in these videos due to glare from the water surface, up and down movements ... |
|
| Complexity Bounds for Quantum Computation |
22 JUN 2007 |
16 pages |
| Authors:
Steven Homer; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| This project focused on upper and lower bounds for quantum computability using constant depth quantum circuits, and on the complexity theory of such circuits. It established significant differences between resource bounded quantum and classical computation models, particularly emphasizing new examples of where quantum circuits are more powerful than their classical counterparts. A second focus and outgrowth of this work was the creation of efficient quantum algorithms for specific problems and ... |
|
| Multi-scale 3D Scene Flow from Binocular Stereo Sequences (Preprint) |
JUN 2007 |
30 pages |
| Authors:
Rui Li; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| Scene flow methods estimate the three-dimensional motion field for points in the world using multi-camera video data. Such methods combine multi-view reconstruction with motion estimation. This paper describes an alternative formulation for dense scene flow estimation that provides reliable results using only two cameras by fusing stereo and optical flow estimation into a single coherent framework. Internally, the proposed algorithm generates probability distributions for optical flow and disparity. Taking into ... |
|
| An Energy-conscious Transport Protocol for Multi-hop Wireless Networks |
Jan 2007 |
15 pages |
| Authors:
N Riga; I Matta; A Medina; C Partridge; J Redi; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| We present a transport protocol whose goal is to reduce power consumption without compromising delivery requirements of applications. To meet its goal of energy efficiency, our transport protocol (1) contains mechanisms to balance end-to- end vs. local retransmissions; (2) minimizes acknowledgment traffic using receiver regulated rate-based flow control combined with selected acknowledgements and in-network caching of packets; and (3) aggressively seeks to avoid any congestion-based packet loss. Within a recently ... |
|
| Small Depth Quantum Circuits |
2007 |
15 pages |
| Authors:
Debajyoti Bera; Frederic Green; Steven Homer; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| Small depth quantum circuits have proved to be unexpectedly powerful in comparison to their classical counterparts. We survey some of the recent work on this and present some open problems. |
|
| JTP: An Energy-conscious Transport Protocol for Wireless Ad Hoc Networks |
2006 |
11 pages |
| Authors:
Niky Riga; Ibrahim Matta; Alberto Medina; Jason Redi; Craig Partridge; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| Within a recently developed low-power ad hoc network system, we present a transport protocol (JTP) whose goal is to reduce power consumption without trading off delivery requirements of applications. JTP has the following features: it is lightweight whereby end-nodes control in-network actions by encoding delivery requirements in packet headers; JTP enables applications to specify a range of reliability requirements, thus allocating the right energy budget to packets; JTP minimizes feedback ... |
|
| An Invariant Representation for Matching Trajectories Across Uncalibrated Video Streams |
MAY 2005 |
11 pages |
| Authors:
Walter Nunziati; Stan Sclaroff; Alberto Del Bimbo; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| We introduce a view point invariant representation of moving object trajectories that can be used in video database applications. It is assumed that trajectories lie on a surface that can be locally approximated with a plane. Raw trajectory data is first locally approximated with a cubic spline via least squares fitting. For each sampled point of the obtained curve, a projective invariant feature is computed using a small number of ... |
|
| Learning Euclidean Embeddings for Indexing and Classification |
12 APR 2004 |
19 pages |
| Authors:
Vassilis Athitsos; Joni Alon; Stan Sclaroff; George Kollios; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| BoostMap is a recently proposed method for efficient approximate nearest neighbor retrieval in arbitrary non-Euclidean spaces with computationally expensive and possibly non-metric distance measures. Database and query objects are embedded into a Euclidean space, in which similarities can be rapidly measured using a weighted Manhattan distance. The key idea is formulating embedding construction as a machine learning task, where AdaBoost is used to combine simple, ID embeddings into a multidimensional ... |
|
| Analysis of Origin Destination Flows (Raw Data) |
10 NOV 2003 |
57 pages |
| Authors:
Anukool Lakhina; Konstantina Papagiannaki; Mark Crovella; Christophe Diot; Eric D. Kolaczyk; Nina Taft; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| In a recent paper, Structural Analysis of Network Traffic Flows [BUCS-TR-2003-021], we analyzed the set of Origin Destination traffic flows from the Sprint-Europe and Abilene backbone networks. This report presents the complete set of results from analyzing data from both networks. The results in this report are specific to the Sprint-1 and Abilene datasets studied in the above paper. |
|
| The Specialized Mappings Architecture |
10 APR 2003 |
36 pages |
| Authors:
Romer Rosales; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| A probabilistic, nonlinear supervised learning model is proposed: the Specialized Mappings Architecture (SMA). The SMA employs a set of several forward mapping functions that are estimated automatically from training data. Each specialized function maps certain domains of the input space (e.g., image features) onto the output space (e.g., articulated body parameters). The SMA can model ambiguous, one-to-many mappings that may yield multiple valid output hypotheses. Once learned, the mapping functions ... |
|
| Discovering Clusters in Motion Time-Series Data (Preprint) |
26 MAR 2003 |
8 pages |
| Authors:
Jonathan Alon; Stan Sclaroff; George Kollios; Vladimir Pavlovic; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| A new approach is proposed for clustering time-series data. The approach can be used to discover groupings of similar object motions that were observed in a video collection. A finite mixture of hidden Markov models (HMMs) is fitted to the motion data using the expectation-maximization (EM) framework. Previous approaches for HMM-based clustering employ a k-means formulation, where each sequence is assigned to only a single HMM. In contrast, the formulation ... |
|
| On the Size Distribution of Autonomous Systems |
17 JAN 2003 |
17 pages |
| Authors:
Marwan Fayed; Paul Krapivsky; John Byers; Mark Crovella; David Finkel; Sid Redner; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| This paper explores reasons for the high degree of variability in the sizes of ASes that have recently been observed, and the processes by which this variable distribution develops. AS size distribution is important for a number of reasons. First, when modeling network topologies, an AS size distribution assists in labeling routers with an associated AS. Second, AS size has been found to be positively correlated with the degree of ... |
|
| On the Emergence of Highly Variable Distributions in the Autonomous System Topology |
2003 |
10 pages |
| Authors:
Marwan Fayed; Paul Krapivsky; John Byers; Mark Crovella; David Finkel; Sid Redner; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| Recent studies have noted that vertex degree in the autonomous system (AS) graph exhibits a highly variable distribution [15, 22]. The most prominent explanatory model for this phenomenon is the Barab asi-Albert (B-A) model [5, 2]. A central feature of the B-A model is preferential connectivity meaning that the likelihood a new node in a growing graph will connect to an existing node is proportional to the existing node nodes ... |
|
| Surface Reconstruction from Multiple Views Using Rational B-Splines |
JUN 2001 |
9 pages |
| Authors:
Matheen Siddiqui; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| A method for reconstructing 3D rational B-spline surfaces from multiple views is proposed. The method takes advantage of the projective invariance properties of rational Bsplines. Given feature correspondences in multiple views, the 3D surface is reconstructed via a four step framework. First, corresponding features in each view are given an initial surface parameter value (s; t), and a 2D B-spline is fitted in each view. After this initialization, an iterative ... |
|
| Retrieval by Shape Population: An Index Tree Approach |
JUN 2001 |
7 pages |
| Authors:
Lifeng Liu; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| Based on our previous work in deformable shape model based object detection, a new method is proposed that uses index trees for organizing shape features to support content based retrieval applications. In the proposed strategy, different shape feature sets can be used in index trees constructed for object detection and shape similarity comparison respectively. There is a direct correspondence between the two shape feature sets. As a result, application-specific features ... |
|
| 3D Hand Pose Reconstruction Using Specialized Mappings |
APR 2001 |
9 pages |
| Authors:
Romer Rosales; Vassilis Athitsos; Leonid Sigal; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| A system for recovering 3D hand pose from monocular color sequences is proposed. The system employs a non-linear supervised learning framework, the specialized mappings architecture (SMA), to map image features to likely 3D hand poses. The SMA's fundamental components are a set of specialized forward mapping functions, and a single feedback matching function. The forward functions are estimated directly from training data, which in our case are examples of hand ... |
|
| Region Segmentation via Deformable Model-Guided Split and Merge |
APR 2001 |
8 pages |
| Authors:
Lifeng Liu; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| An improved method for deformable shape based image segmentation is described. Image regions are merged together and/or split apart, based on their agreement with an a priori distribution on the global deformation parameters for a shape template. Perceptually motovated crtieria are used to determine where/how to split regions, based on the local shape properties of the regions group's bounding contour. A globally consistent interpretation is determined in part by the ... |
|
| Lattice Hydrodynamics |
FEB 2001 |
11 pages |
| Authors:
Bruce M. Boghosian; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| This document is the final report for AFOSR Grant F49620-99-1-0070, 'Lattice Hydrodynamics'. Under the terms of this grant, the Center for Computational Science at Boston University provided theoretical and computational support to the Lattice-Gas Theory and Computation group at the Space Vehicles Directorate of Air Force Research Laboratory (AFOSR task 2304CP). The principal research topics were the development of quantum lattice-gas models for implementation on quantum computers, and classical lattice ... |
|
| Automatic 3D Registration of Lung Surfaces in Computed Tomography Scans |
2001 |
17 pages |
| Authors:
Margrit Betke; Harrison Hong; Jane P. Ko; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| We developed an automated system that registers chest CT scans temporally. Our registration method matches corresponding anatomical landmarks to obtain initial registration parameters. The initial point-to-point registration is then generalized to an iterative surface-to-surface registration method. Our "goodness-of-fit" measure is evaluated at each step in the iterative scheme until the registration performance is sufficient. We applied our method to register the 3D lung surfaces of 11 pairs of chest CT ... |
|
| Gallium Nitride Static Induction Power Transistors |
30 JUN 2000 |
21 pages |
| Authors:
Charles R. Eddy Jr.; Theodore D. Moustakas; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| This report summarizes a one year program to investigate issues related to fabrication and performance of III-V nitride static induction power transistors. To understand vertical conduction mechanisms in this device a nearly ideal, vertical Schottky barrier diode was fabricated and analyzed. By applying the diffusion theory of Schottky barriers, a vertical mobility of ^950 sq cm/Vs was measured which, when compared to a lateral mobility ... |
|
| Recursive Estimation of Motion and Planer Structure |
MAR 2000 |
8 pages |
| Authors:
Jonathan Alon; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| A specialized formulation of Azarbayejani and Pentland's framework for recursive recovery of motion, structure and focal length from feature correspondences tracked through an image sequence is presented. The specialized formulation addresses the case where all tracked points lie on a plane. This planarity constraint reduces the dimension of the original state vector, and consequently the number of feature points needed to estimate the state. Experiments with synthetic data and real ... |
|
| Shape and Motion Categorization for Content-Based Image and Video Database Search |
31 AUG 1999 |
7 pages |
| Authors:
Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| The aim of this project is to represent shape categories for interactive, image database search. The work involves developing representations of images of objects to facilitate content-based retrieval and indexing, especially of deformable objects. This is a final progress report for work conducted under a three year period, under the Office of Naval Research Young Investigator's Program. |
|
| Non-Rigid Shape from Image Streams |
AUG 1999 |
9 pages |
| Authors:
Stan Sclaroff; Jonathan Alon; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| We present a framework for estimating 3D relative structure (shape) and motion given objects undergoing nonrigid deformation as observed from a fixed camera, under perspective projection. Deforming surfaces are approximated as piece-wise planar, and piece-wise rigid. Robust registration methods allow tracking of corresponding image patches from view to view and recovery of 3D shape despite occlusions, discontinuities, and varying illumination conditions. Many relatively small planar/rigid image patch trackers are scattered ... |
|
| Deformable Shape Detection and Description via Model-Based Region Grouping |
AUG 1999 |
8 pages |
| Authors:
Lifeng Liu; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| A method for deformable shape detection and recognition is described. Deformable shape templates are used to partition the image into a globally consistent interpretation, determined in part by the minimum description length principle. Statistical shape models enforce the prior probabilities on global, parametric deformations for each object class. Once trained, the system autonomously segments deformed shapes from the background, while not merging them with adjacent objects or shadows. The formulation ... |
|
| Recovery of Piece-Wise Planar and Piece-Wise Rigid Models from Non-Rigid Motion |
AUG 1999 |
13 pages |
| Authors:
Jonathan Alon; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| We present a framework for estimating 3D relative structure (shape) and nation given objects undergoing non-rigid deformation as observed from a fixed camera, under perspective projection. Deforming surfaces are approximated as piece wise planar, and piece wise rigid. Robust registration methods allow tracking of corresponding image patches from view to view and recovery of 3D shape despite occlusions, discontinuities, and varying illumination conditions. Many relatively small planar/rigid image patch trackers ... |
|
| Fast, Reliable Head Tracking Under Varying Illumination |
AUG 1999 |
8 pages |
| Authors:
Marco La Cascia; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| An improved technique for 3D head tracking under varying illumination conditions is proposed. The head is modeled as a texture mapped cylinder. Tracking is formulated as an image registration problem in the cylinder's texture map image. To solve the registration problem in the presence of lighting variation and head motion, the residual error of registration is modeled as a linear combination of texture warping templates and orthogonal illumination templates. Fast ... |
|
| Automatic Deformable Shape Segmentation for Image Database Search Applications |
AUG 1999 |
9 pages |
| Authors:
Lifeng Liu; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| A method for shape based. image database indexing is described. Deformable shape templates are used to group color image regions into globally consistent configurations. A statistical shape model is used to enforce the prior probabilities on global, parametric deformations for each object class. The segmentation is determined in part by the minimum description length (MDL) principle. Once trained; the system autonomously segments deformed shapes from he background, while not merging ... |
|
| Combinations of Non-Rigid Deformable Appearance Models |
AUG 1999 |
13 pages |
| Authors:
Saratendu Sethi; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| A framework for object recognition via combinations of nonrigid deformable appearance models is described. An object category is represented as a combination of deformed prototypical images. An object in an image can be represented in terms of its geometry (shape) and its texture (visual appearance) . We employ finite element based methods to represent the shape deformations more reliably and automatically register the object images by warping them onto the ... |
|
| Combinations of Deformable Shape Prototype |
AUG 1999 |
17 pages |
| Authors:
Saratendu Sethi; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| We present a model-based technique for encoding non-rigid object classes in terms of object prototypes. Objects from the same class can be parameterized by identifying shape and appearance invariants of the class to devise low-level representations. The approach presented here creates a flexible model for an object class from a set of prototypes. This model is them used to estimate the parameters of low-level representation of novel objects as combinations ... |
|
| Lattice-Gas Models of Complex-Fluid Hydrodynamics |
31 MAR 1999 |
17 pages |
| Authors:
Bruce M. Boghosian; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| This document is the final report for AFOSR Grant F49620-97-1-0172, "Lattice-Gas Models of Complex-Fluid Hydrodynamics." Under the terms of this grant, the Center for Computational Science at Boston University provided theoretical and computational support to the Lattice-Gas Theory and Computation group at the Space Vehicles Directorate of Air Force Research Laboratory (AFOSR task 2304CP). The principal research topics were the development of lattice-gas and ... |
|
| Head Tracking via Robust Registration in Texture Map Images |
AUG 1998 |
8 pages |
| Authors:
Marco LaCascia; John Isidoro; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| A novel method for 3D head tracking in the presence of large head rotations and facial expression changes is described. Tracking is formulated in terms of color image registration in the texture map of a 3D surface model. Model appearance is recursively updated via image mosaicking in the texture map as the head orientation varies. The resulting dynamic texture map provides a stabilized view of the face that can be ... |
|
| Active Voodoo Dolls: A Vision Based Input Device for Nonrigid Control |
AUG 1998 |
8 pages |
| Authors:
John Isidoro; Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| A vision based technique for nonrigid control is presented that can be used for animation and video game applications. The user grasps a soft, squishable object in front of a camera that can be moved and deformed in order to specify motion. Active blobs, a nonrigid tracking technique is used to recover the position, rotation and nonrigid deformations of the object. The resulting transformations can be applied to a texture ... |
|
| Active Blobs |
AUG 1998 |
9 pages |
| Authors:
Stan Sclaroff; John Isidoro; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| A new region-based approach to nonrigid motion tracking is described. Shape is defined in terms of a deformable triangular mesh that captures object shape plus a color texture map that captures object appearance. Photometric variations are also modeled. Nonrigid shape registration and motion tracking are achieved by posing the problem as an energy-based, robust minimization procedure. The approach provides robustness to occlusions, wrinkles, shadows, and specular highlights. The formulation is ... |
|
| Shape and Motion Categorization for Content-Based Image and Video Database Search |
AUG 97 |
10 pages |
| Authors:
Stan Sclaroff; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| The aim of this project is to represent shape categories for interactive image database search. The work involves developing representations of images of objects to facilitate content-based retrieval and indexing, especially of deformable objects. This progress report gives detail of work completed from 1 September 1996 to 31 August 1997. |
|
| OS Support for Portable Bulk Synchronous Parallel Programs |
05 DEC 1994 |
11 pages |
| Authors:
Abdelsalam Heddaya; Amr F. Fahmy; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| For parallel programs to become portable, they must be executable with uniform efficiency oil a variety of hardware platforms which is not the case at present. In 1990, Valiant proposed Bulk-Synchronous Parallelism ( BSP ) as a model on which portable parallel programs can be built [Val90a]. We argue that shared-memory BSP is efficiently implementable on a wide variety of parallel hardware and that BSP forms a useful basis for ... |
|
| CLEOPATRA: Building Responsive Systems from Physically-Correct Specifications |
1993 |
27 pages |
| Authors:
Azer Bestavros; BOSTON UNIV MA DEPT OF COMPUTER SCIENCE
|
| Predictability- the ability to foretell that an implementation will not violate a set of specified reliability and timeliness requirements is a crucial, highly desirable property of responsive embedded systems. This paper overviews a development methodology for responsive systems, which enhances predictability by eliminating potential hazards resulting from physically-unsound specifications. The backbone of our methodology is the Time-constrained Reactive Automaton (TRA) formalism, which adopts a fundamental notion of space and time ... |
|
Reports by Corporate Author
