|
|
Multiscale
Texture Element Detection
D
Blostein, S Jackson
In
an image containing texture elements at a range of scales, detect all
elements,
their relative locations and mutual containment relationships
| Demo
|
Details | Publications
| Back to Theme |
|
|
|
Shape from Texture
D
Blostein
Given the image of a homogeneously textured planar
surface at unknown orientation relative to the camera, and the output
of a multiscale image region detector, estimate the surface orientation
| Demo
|
Details| Publications
| Back to Theme |
|
|
|
3D Motion and Structure Estimation
Y
Cui, C Debrunner, X Hu, T Huang,
Y Liu, J Weng
Given a video sequence showing a dynamic scene from a
still or a moving camera at unknown
viewpoint(s), estimate the 3D depth map and motion characteristics
|Demo
|Details |Publications
|Back to Theme |
|
|
|
Integrated Motion and Structure
Estimation and Motion Segmentation
R
Charan, C Debrunner, J Ma, T Srikanth, S Sull
Given a video sequence showing a dynamic scene from an
unknown viewpoint, delineate the independently moving objects as well
as estimate the 3D depth map and motion characteristics for each
|
Demo
|
Details | Publications
| Back to Theme |
|
|
|
Two-View Matching
R
Haralick, X Hu, T Huang, K Iwasaki, F Kishino, Z Liang, L Magin, H Pan,
X Zhuang
Given two images of a dynamic scene, taken from a
still or a moving camera, at two different times and representing two
different viewpoints, find the corresponding scene points in the images
| Demo
| Details | Publications
| Back to Theme |
|
|
|
Motion and Structure from Two Views
T
Huang, J Ma, M Tabb, J Weng
Given two images of a dynamic scene, taken from a
still or a moving camera, at two different times and representing two
different viewpoints, find the 3D motion and structure
| Demo
| Details | Publications
| Back to Theme |
|
|
|
Surfaces from Binocular Spatial
Stereo
W
Hoff,
E Altman
Given multiple images of a scene, taken from multiple
cameras and different viewpoints, find the 3D depth map and surfaces
| Demo
| Details | Publications
| Back to Theme |
|
|
|
3D Surfaces and Illumination from
Stereo and Shading
D
Hougen,
M Singh
Given multiple images of a scene, estimate the scene
surfaces, illumination and/or reflectance
map
| Demo
| Details | Publications
| Back to Theme |
|
|
|
Surfaces from Silhouettes in
Trinocular Spatial Stereo
T
Joshi, J Ponce
Given a trinocular stereo camera configuration viewing
the dynamically changing silhouette of a moving object, estimate the 3D
surface and motion of the object from the video sequence
|
Demo
|
Details | Publications
| Back to Theme |
|
|
|
Surfaces from Active Binocular
Stereo
L
Abbott,
S Das, N Srinivasa
Given an active stereo vision system capable of active
and dynamic control of imaging parameters, such as aperture, focus,
zoom and gaze direction, integrate the information in the control
parameters and image features to estimate the 3D surfaces across a wide
scene with a large depth range
|
Demo
| Details
| Publications
| Back to Theme |
|
|
|
Integrated Analysis Guided
Synthesis of Video Sequences for Augmented Reality
S
Sull
Given a video sequence of a dynamic scene, select
and/or add multiple image features that are 3D consistent, to enhance
the visual perception of a priori chosen 3D scene characteristics such
as relative motion
| Demo
| Details
| Publications
| Back to Theme |
|
|
|
Omnifocus Nonfrontal Imaging
Camera
(NICAM)
M
Aggarwal, A Krishnan, A Castano, J Hart
Acquisition of panoramic images by panning a camera
across a scene of arbitrary width and depth, with all objects captured
in focus irrespective of their depths, along with a registered image of
depth-from-focus estimates
| Demo
| Details
| Publications
| Back to Theme |
|
|
|
Panoramic Imaging with Infinite
Dynamic Range
M
Aggarwal
Acquisition of panoramic images by panning a camera
across a scene of arbitrary width and depth, with all objects captured
within the sensitivity range of the sensor irrespective of their
brightnesses
| Demo
| Details | Publications
| Back to Theme |
|
|
|
Split Aperture Imaging
M
Aggarwal
Real time acquisition of a multimodal image of a scene
by acquiring each mode in parallel from the same viewpoint and in
registration, capturing each on an independent sensor in parallel, and
fusing the modal images into a single vector image
|
Demo | Details
| Publications | Back to Theme |
|
|
|
A New Imaging Model
M
Aggarwal, H Hua
To develop a model of image formation that captures
the geometric and photometric relationships between the scene and the
image sufficiently accurately to allow the design of special cameras
such as NICAM and Multicam
| Demo
| Details | Publications
| Back to Theme |
|
|
|
Automatic Multiscale Image
Segmentation
T
Courtney, M Tabb, M
Yang
Given a univariate or multivariate image, in two or
higher dimensions, identify all different visually perceived regions in
it accurately, regardless of their a priori unknown geometric,
topological and photometric complexity, and represent the resulting
segmentation as a tree
| Demo
| Details | Publications
| Back
to Theme |
|
|
|
Automatic Detection of
Hierarchical Perceptual Structure in Dot Patterns
P
Bajcsy, R Charan, R
Dugad, A Jain, M Tuceryan
Given a dot pattern in two or higher dimensions,
identify all different visually perceived dot groupings in it
accurately, regardless of their a priori unknown geometric and
topological complexity, and represent the resulting segmentation as a
tree
| Demo
| Details | Publications
| Back
to Theme |
|
|
|
Random Mosaic Models of Textures
T
Dubitzki,
A Rosenfeld, B Schachter
To represent, analyze and synthesize homogeneous 2D
texture images using random geometric pattern generation and coloring
processes that capture the important, region level, visual attributes
of the texture
| Demo
| Details | Publications
| Back
to Theme |
|
|
|
Pixel-Based Models of Statistical
Image Homogeneity
P
Bajcsy, R Chellappa, L Davis, R Haralick, R Kashyap, D Milgram, A
Rosenfeld
To represent and extract statistically homogeneous
image regions using probabilistic models of spatial distributions of
pixel values
| Demo
| Details | Publications
| Back
to Theme |
|
|
|
2D and 3D Shape Representation
B
An, K Bowyer, H Chen, J Chuang, C Dyer, O Faugeras, W Hoff, T Huang, K
Ikeuchi, R Jain, W Lai, J Mundy, A Pentland, B Schachter
Develop methods for the representation of a
preidentified array of 2D or 3D regions that are computationally
efficient and/or yield computationally efficient representations
| Demo
| Details | Publications
| Back
to Theme |
|
|
|
Generation of Octree
Representations of 3D Objects
S
Srivastava, J Veenstra
To generate the Octree of an object from the
information contained in its silhouettes observed from multiple known
viewpoints
| Demo
| Details | Publications
| Back
to Theme |
|
|
|
Maintenance of Octree
Representation of Moving 3D Objects
C
Nash,
W Osse, J Weng
To efficiently update the octree representation of an
object as the object translates or rotates
| Demo
| Details | Publications
| Back
to Theme |
|
|
|
Learning of Low-level
Spatiotemporal Structural Patterns
T
Huang, B Perrin, N Srinivasa, J Weng
Given an image or a video sequence, a prespecified set
of low level, spatial and/or temporal descriptors of the image/video
structure, and a higher level interpretation of the structure, use
computational learning methods to derive a succinct relationship
between the interpretation and the low level structural description
| Demo
| Details | Publications
| Back to Theme |
|
|
|
Learning for Object Recognition
D
Roth, M Yang
A learning
algorithm accounting for the problem of object
recognition is developed within the PAC (Probably Approximately
Correct) model of learnability. We evaluate this apporach using the
COIL-100
database and exhibit its advantages over conventional methods
| Demo
| Details
| Publications
| Back to Theme |
|
|
|
Face Detection
D
Kriegman, D Roth, M
Yang
To identify and locate faces in still grayscale images
using
staistical learning methods
| Demo
| Details | Publications
| Back to Theme |
|
|
|
Face Recognition
F
Kishino, Y Kitamura, J Ma, C Neti, J Ohya, A Senior, , M
Yang
To develop methods to tell the identity of a person
from a frontal
image and evaluate its performance with state-of-the-art methods
| Demo
| Details
| Publications
| Back to Theme |
|
|
|
Gesture Recognition
E
Altman, F Kishino, M
Yang
Recognize and interpret sign gestures of
American Sign Language from a video sequence based on an integrated
method of motion
segmentation, shape, size and color
| Demo
| Details | Publications
| Back to Theme |
|
|
|
Sketch-Based Object Selection in
Images
K
Tan
To assist humans in referring to specific parts of an
image, and performing desired operations on these parts, through
natural-like interpersonal communication, e.g. by freely drawing
sketches over the image which mean specific editorial operations such
as move, expand and delete
| Demo
| Details
| Publications
| Back to Theme |
|
|
|
Structure Based Image Compression
K
Ratakonda
Given an image and its hierarchical segmentation
representing its natural multiscale structure, use the compactness of
the structural description for best image compression
| Demo
| Details
| Publications
| Back to Theme
|
|
|
|
Structure Based Image
Magnification or Superresolution
K
Ratakonda
Given an image and its hierarchical segmentation
representing its natural multiscale structure, use the explicit, known
geometry for image scaling, e.g., image expansion for superresolution
| Demo
| Details | Publications
| Back to Theme
|
|
|
|
Structure Based Image Denoising
P
Ishwar, P Moulin, K Ratakonda, M Singh
Given an image and its hierarchical segmentation
representing its natural multiscale structure, use the knowledge of the
image regions to smooth out the noise in the region interiors without
blurring borders
| Demo
| Details | Publications
| Back to Theme
|
|
|
|
Segmentation Based Video Coding
K
Ratakonda , S Yoon
Given a video sequence and a hierarchical segmentation
representing the natural multiscale spatiotemporal structure, identify
the interframe redundancy for efficient video coding which is adaptive
to the desired level of coded detail
| Demo
| Details
| Publications
| Back to Theme
|
|
|
|
Video Frame Interpolation
S Yoon
Given a video sequence with missing frames, generate
the missing frames by interpolating nearby available frames
| Demo
| Details
| Publications
| Back to Theme
|
|
|
|
Transform Domain Magnification or
Superresolution
R
Dugad, K
Ratakonda
To
develop fast algorithms for magnification or demagnification of a
compressed
image by a given amount directly in the compressed image format
| Demo | Details
| Publications | Back to Theme |
|
|
|
Transform-Domain Watermarking
R
Dugad, K Ratakonda
To develop a watermarking method that does not use the
original image for watermark detection and resilient to image quality
degradation
| Demo
| Details
| Publications
| Back to Theme
|
|
|
|
Linear
Transforms over arbitrary supports
R
Dugad, K Ratakonda
We
present a novel iterative approach to define any multidimensional
linear
transform over an arbitrary shape given that we know its definition
over a
hypercube
| Demo | Details | Publications | Back to Theme |
|
|
|
Video Denoising
R
Dugad
Combine spatial and temporal filtering to suppress
noise in each frame of a video sequence
| Demo
| Details
| Publications
| Back to Theme
|
|
|
|
Video Shot Detection
R Dugad, K Ratakonda
Given a video sequence, identify those frames that
represent changes in the parts of the scene being imaged
| Demo
| Details | Publications
| Back to Theme
|
|
|
|
DSP Algorithms
M
Aggarwal
To
improve the Throughput of Flexible-Precision DSPs via Algorithm
Transformation
| Demo
| Details | Publications
| Back to Theme |
|
|
|
Efficient Algorithms and
Architectures
A
Choudhary, S Das, C Debrunner, J Patel, M Sharma, S Swamy
To develop computationally efficient, e.g.,
divide-and-conquer or DSP chip oriented, algorithms for different
classes of computer vision algorithms, and to define special purpose,
e.g., parallel multiprocessor, architectures that efficiently execute
the algorithms
| Demo
| Details | Publications
| Back to Theme |
|
|
|
Collision Detection
N
Bridwell, J Chuang, F Kishino, Y Kitamura, H Takemura, R Yen, R Chien
Given a set of objects moving in a known fashion and a
set of still obstacles, detect or predict collisions between specific
pairs of objects
| Demo
| Details | Publications
| Back to Theme |
|
|
|
Path Planning
J
Chuang, Y Hwang, R Ruff
Given a mobile object required to move from a source
location/orientation to a destination location/orientation, compute a
path that it can follow and the orientation and velocity values it must
assume along the path to efficiently and smoothly move from the source
to the destination
|
Demo
| Details
| Publications
| Back to Theme |
|
 |
Six-legged Robot Design
J
Cocatre-Zilgien, F
Delcomyn, Z Ding, J Hart, G
Kremesec, L Lu, M Nelson, J Reichler, K Tan
Design and implementation of a pneumatic, six-legged
robot with the geometry, number of leg joints, and joint functionality
modeled after the American Cockroach
|Demo|Details|Presentation|Poster|Publications|Back to Theme|
|
|
|
Head-mounted projective display
technology
L
Brown, C Gao, H Hua
To optimize a novel visualization device referred to
as head-mounted projective display (HMPD), and develop a multi-user
interactive workbench with tele-presence capability
| Demo
| Details | Publications
| Back to Theme
|
|
|
|
Tele-collaboration in interactive
augmented environments
L
Brown, C Gao, H Hua
To demonstrate the featured capabilities of the HMPD
technology, and explore its application for distance collaboration in
interactive augmented environments
| Demo
| Details | Publications
| Back to Theme
|
|
| |
