|
|
|
Department
of |
Please check back this page
regularly as more projects will be added.
We are looking at several
studies related to virtual reality and aerospace simulations including the
effects of time delay in virtual environments and navigation through a virtual
environment. The project would involve the development of flexible
virtual environments for experimentation and the design and analysis of
experiments.
As part of a ongoing
research program we opportunities for work on research involving the depth
perception and three-dimensional displays. Several different projects are
ongoing ranging from studying human stereoscopic perception to the use of blur
as a depth cue in computer displays.
(Description
to be posted)
To provide visual surveillance over a large environment, many
surveillance cameras are typically deployed at widely dispersed locations. Making sense of activities within the
monitored space requires security personnel to map multiple events observed on
two-dimensional security monitors to the three-dimensional scene under surveillance. The cognitive load entailed rises quickly as
the number of cameras, complexity of the scene and amount of traffic increases.
This problem can be addressed by automatically pre-mapping
two-dimensional surveillance video data into three-dimensional
coordinates. Rendering the data directly
in three dimensions can potentially lighten the cognitive load of security
personnel and make human activities more immediately interpretable.
Mapping surveillance video to three-dimensional coordinates requires
construction of a virtual model of the three-dimensional scene. Such a model could be obtained by survey
(e.g., using LIDAR), but the cost and time required for each site would
severely limit deployment. Wide-baseline
uncalibrated stereo methods are developing and have potential utility, but require
careful sensor placement, and the difficulty of the correspondence problem
limits reliability.
This project will investigate a monocular method for inferring
three-dimensional context for video surveillance. The method will make use of the fact that
most urban scenes obey the so-called “Manhattan-world” assumption, viz., a
large proportion of the major surfaces in the scene are rectangles aligned with
a three-dimensional Cartesian grid (Coughlan & Yuille, 2003). This regularity provides strong linear
perspective cues that can potentially be used to automatically infer
three-dimensional models of the major surfaces in the scene (up to a scale
factor). These models can then be used
to construct a virtual environment in which to render models of human
activities in the scene.
Although the
The student will work closely with graduate students and postdoctoral
fellows at
For more information on the laboratory: www.elderlab.yorku.ca
Requirements: Good facility with applied mathematics
Facilities
planning at both city (e.g.,
The
density of permanent urban video surveillance camera installations has
increased dramatically over the last several years. These systems provide a potential source of
low-cost data from which flows can be estimated for planning purposes.
This
project will explore the use of computer vision algorithms for the automatic
estimation of pedestrian and vehicle flows from video surveillance data. The ultimate goal is to provide planners with
accurate, continuous, up-to-date information on facility usage to help guide
planning.
The student will work closely with graduate students and postdoctoral
fellows at
For more information on the laboratory: www.elderlab.yorku.ca
Requirements: Good facility with applied mathematics
Low-cost
three-dimensional face-scanning systems have a large range of potential
applications in security and retail markets.
Our laboratory at
The
project will involve systems design and development of a specialized real-time
3D face scanner. A combination of
hardware and software design will be required.
The student will work closely with graduate students
and postdoctoral fellows at
For more information on the laboratory: www.elderlab.yorku.ca
Requirements: Interest in both hardware and software design
at the systems level.
Human
target detection in search-and-rescue and other air-to-ground surveillance
applications is an imperfect process. Error
rates depend upon the spatial acuity and colour sensitivity of individual
observers, and fatigue is known to play a major role. Improved sensing technologies (e.g.,
range-gated near-IR, thermal IR) have the potential to improve
performance. Ultimately, however,
performance will be determined by how accurately the vast quantities of data
generated by these technologies are interpreted, either by computer or by the
human visual system. The goal of the
proposed project is to research and develop advanced imaging techniques that
will ensure that the power of these diverse sensing technologies is harnessed
effectively to yield faster and more reliable detection rates.
The
specific goal of the proposed project is to develop algorithms that will
improve human target detection rates by drawing visual attention to locations
in the data stream where target probability is higher. The SAR simulator at DRDC Toronto will serve
as a test-bed for evaluating the efficacy of all image enhancements.
Search and
rescue target detection is typically characterized by poor target resolution,
variability in data quality due to atmospheric effects etc., and imperfect
target knowledge. These challenges
suggest a statistical approach in which multiple weak but complementary
modalities and cues are combined to produce reliable inferences. We have demonstrated the efficacy of this
approach for indoor surveillance (Prince et al., 2005), and our first step will
be to transfer these techniques to the search-and-rescue context and evaluate
performance on airborne imagery from search-and-rescue flight trials. MATLAB and/or C++ implementations of these
algorithms will be transferred from
This work
may provide leverage in a number of other application areas, including: (1) monitoring of international water and
land boundaries, ports and airports, (2) security at critical infrastructure
locations (e.g., government buildings, power stations, city cores) and (3)
disaster management activities.
The student will work closely with graduate students and postdoctoral
fellows at
For more information on the laboratory: www.elderlab.yorku.ca
Requirements: Good facility with applied mathematics
In this project, the student is required to design and write a program
which can automatically search, etrieve, and normalize text data from the
Internet according to user's queries. The program needs to process each of
user's text queries and then search the processed query from some Internet
search sites and automatically retrieve and save the returned search results.
At last, the program needs to normalize and format the returned text and save
them for future uses. Since the program eventually will be used to
automatically process a large number of user queries, its efficiency is a key
issue in its design and development.
Required skills: basic programming skills; C/shell/Perl is a plus.
Duplication
and replication are two simple ways to quickly create larger groups of
objects. However, it is typically not
possible to manipulate originals and their copies directly (i.e. similar to
manipulating a repeated datebook entry). This project investigates new ways to
effect the manipulation of replicated/duplicated objects in 2D drawings and
evaluating them in a comparative user study.
Platform: any modern GUI toolkit or drawing system
Many
programming errors are due to pieces of code being copied from another location
but that has not been "perfectly" adapted to the new context. Such
errors are hard to find, especially if the old and new contexts are only subtly
different. This project involves fixing some problems in a existing implementation
of a context sensitive cut, copy & paste method (in Java), finding some
good examples/test cases, and then performing a user study that quantifies how
many cut, copy & paste errors are made with & without the technique.
Platform: Java, LAPIS
Displaying
suggestions during the drawing process can make it easier for the user to
create common and desirable configurations. This project investigates novel
user interface methods to make such a suggestive user interface easier to use.
Platform: any 2D drawing system, existing C-code for
some suggestions.
Large
projected displays often use cameras to allow for interaction (either with
touch technologies or laser pointers). However, such systems only work well if
the camera is well calibrated to the screen. This calibration needs to be
repeated whenever the screen is moved, the projector is changed or the camera
is touched. This project uses a camera on a robotic pan/tilt unit to automate
this calibration process. It also uses a laser diode and/or a laser range
finder to simultaneously detect the planarity of the projection surface as well
as increase the accuracy of the calibration.
This
project realizes a novel form of interaction devices for computers. These are
wireless styli, which use laser diodes to enable users to point to distant
projection surfaces as well as displays in front of the user. A touch detector
as well as a novel form of proximity detection enables further forms of
interaction.
Tangible
user interfaces provide the user with object that they can touch and use as
input devices. One example is the use of (tracked) toy houses to perform a city
planning task on a large surface. This project implements a new form of
tracking/identification scheme for tangible objects via LED arrays mounted on
them. Furthermore, and using robotic components, the tangible objects will have
the ability to move around autonomously, which enables important
functionalities such as undo and replay.
A
concurrent program may contain data races.
That is, the program may contain concurrent accesses of a particular
variable of which at least one is a write. For example, the following Java
program contains a data race on the attribute i.
Data races
may give rise to unexpected behaviors.
For example, for the above program the value read by the Reader can
either be 1 or 2. Therefore, it is
important to develop tools that can detect races.
Java
PathFinder is a model checker developed at NASA. With this tool, one can check properties of
Java programs. For Java PathFinder,
three different race detectors have been implemented.
The aims of
this project are
·
to
gain a good understanding of data races,
·
to
develop a test suite to check if the race detectors are correct, and
·
to
compare the performance of the race detectors.
To accomplish
these aims, the student, in collaboration with the supervisor, should
·
read
some papers/books that discuss race conditions,
·
search
the literature for small Java programs that contain (apparent) data races,
·
write
a large collection of small Java programs that contain (apparent) data races, and
·
run
the test suites for the different race detectors.
Required skills: basic knowledge of Java
Last updated: January 15, 2008.