CSE4080

Updated: March 14, 2012

Projects will be added to this page until the beginning of the summer term.

If you have an idea for a project that is not listed here, you are welcome to contact CSE faculty members to find out if they are willing to supervise it. (If you are not sure who to approach as a potential supervisor for a particular project you have in mind, ask the course coordinator.)

Most of the projects listed here are intended for CSE4080. A project is only suitable for CSE4480 if it has a significant security component.

Supervisor: James Elder

Requirements: Good facility with applied mathematics

Description: 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 Manhattan world assumption provides powerful constraints, there are many technical challenges that must be overcome before a working prototype can be demonstrated. The prototype requires six stages of processing: 1)The major lines in each video frame are detected. 2) These lines are grouped into quadrilaterals projecting from the major surface rectangles of the scene. 3) The geometry of linear perspective and the Manhattan world constraint are exploited to estimate the three-dimensional attitude of the rectangles from which these quadrilaterals project. 4) Trihedral junctions are used to infer three-dimensional surface contact and ordinal depth relationships between these surfaces. 5) The estimated surfaces are rendered in three-dimensions. 6) Human activities are tracked and rendered within this virtual three-dimensional world.

The student will work closely with graduate students and postdoctoral fellows at York University, as well as researchers at other institutions involved in the project. The student will develop skills in using MATLAB, a very useful mathematical programming environment, and develop an understanding of basic topics in image processing and vision.

For more information on the laboratory: http://www.elderlab.yorku.ca.

Supervisor: James Elder

Requirements: Good facility with applied mathematics

Description: Facilities planning at both city (e.g., Toronto) and institutional (e.g., York University) scales requires accurate data on the flow of people and vehicles throughout the environment. Acquiring these data can require the costly deployment of specialized equipment and people, and this effort must be renewed at regular intervals for the data to be relevant.

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 York University, as well as researchers at other institutions involved in the project. The student will develop skills in using MATLAB, a very useful mathematical programming environment, and develop an understanding of basic topics in image processing and vision.

For more information on the laboratory: http://www.elderlab.yorku.ca.

Supervisor: Suprakash Datta

Required Background: The student should have completed undergraduate courses in Algorithms and Signals and Systems.

Recommended Background: Some background in Statistics is desirable but not essential.

Description: DNA sequences of organisms have many repeated substrings. These are called repeats in Biology, and include both exact as well as approximate repeats. Repeats are of two main types: interspersed repeats (which are spread across a genome) and tandem repeats, which occur next to each other. Tandem repeats play important roles in gene regulation and are also used as markers that have several important uses, including human identity testing.

Finding tandem repeats is an important problem in Computational Biology. The techniques that have been proposed for it fall into two classes: string matching algorithms and signal processing techniques. In this project, we will explore fast, accurate algorithms for detecting tandem repeats and evaluate the outputs of the algorithms studied by comparing their outputs with those of available packages, including mreps, SRF and TRF.

Supervisor: Michael Jenkin

Required Background: General prerequisites, knowledge of Python helpful

Description: We are constructing a fleet of autonomous watercraft based on RC motorboats. These vessels run using a collection of ROS (Robot Operating System) nodes. Testing new software on the devices is difficult, especially in winter. This project involves building a ROS-based graphical simulator for the vehicles and then demonstrating the system using data collected from the real robots operating on Stong Pond.

Supervisor: Michael Jenkin

Required Background: General prerequisites, knowledge of Python helpful, knowledge of linux helpful

Description: An alpha version of the control system for a fleet of autonomous watercraft has been built using ROS (Robot Operating System) nodes. Based on field trials of the vehicles we are now at the point to build a final version of the software and to conduct extensive tests of a group of the vehicles operating in a group. This project will involve modifying the existing code, validating the system, and then testing the vehicles in both Tait Pool and Stong Pond.

Supervisor: Professor M. Balko

Required Background: CSE3461

Recommended Background: Micro controller (Arduino) programming or a willingness and aptitude to learn

Description: Voice banking involves the gathering of speech samples from an individual's speech to form an acoustic model that is subsequently used in a speech synthesis module. This allows for the synthesis of speech that resembles the individual's speech (for example, once the individual loses his or her voice due to the progression of disease). Current systems require the user to spend hours sitting in front of the computer, recording samples of prompted speech. In this project, a wireless tangible interface will be designed to work with existing voice banking software. The interface will be placed in the individual's everyday environment and will unobtrusively prompt, elicit and gather speech samples.

Supervisor: Suprakash Datta

Required Background: CSE4480 prerequisites

Description: A key infrastructural problem in wireless networks is localization (or the determination of geographical locations) of nodes. A related problem is the tracking of mobile targets as they move through the radio ranges of the wireless nodes.

If security is not a concern, then any of numerous existing algorithms can be implemented to get reasonably accurate location estimates of nodes or targets. These algorithms typically involve nodes sharing locations and assume that there are no malicious nodes and no privacy issues in sharing locations. However, localization or target tracking in the presence of malicious nodes or nodes that do not wish to disclose their locations is much more difficult.

This project will look at current research on localization algorithms. The student will read papers to learn about existing work and then implement a few algorithms to compare their performance. Then, with assistance from the supervisor, (s)he will attempt to propose improvements and/or combinations of ideas from the papers in a Java/C/C++/MatLab simulator.

Expected learning outcomes: Apart from familiarity with the current literature, the project will provide the student an introduction to scientific research and analysis of experimental data.

Skills required: Proficiency with one of Java, C, C++, MatLab; interest in developing algorithms for distributed systems; interest in experimental approaches to problems.

References:

1. Multiple target localisation in sensor networks with location privacy, Matthew Roughan, Jon Arnold· Proceedings of the 4th European conference on Security and privacy in ad-hoc and sensor networks (ESAS'07), Springer-Verlag, 2007

2. Defending Wireless Sensor Networks against Adversarial Localization, Neelanjana Dutta, Abhinav Saxena, Sriram Chellappan, Proceedings of the 2010 Eleventh International Conference on Mobile Data Management (MDM '10).

The student will implement existing spectral algorithms based on Fourier Transforms and on an autoregressive model. He will then make changes suggested by the supervisor, and evaluate the effect of the modifications. Throughout the course, the student is required to maintain a course Web site to report any progress and details about the project.