CSE4080

User Tools

Site Tools

You are here: EECS 4080.03, EECS 4081.06, EECS 4082.06, EECS 4084.06, EECS 4088.06, EECS 4090.06 and EECS 4480.03 » Proposed Projects for Winter 2014
Trace:
projects

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
projects [2013/09/09 00:55] – pdprojects [2014/04/24 18:52] (current) – vlajic
Line 1: Line 1:
-====== Proposed Projects for Fall 2013 ======+====== Proposed Projects for Winter 2014 ======
  
 \\ \\
 +====== Assistive Technology & Vision Impairment ======
 +
 +**Supervisor**: Melanie Baljko
 +
 +**Required Background**: General CSE4080 prerequisites
 +
 +**Recommended Background**: Experience with data collection and/or experimental design (e.g., CSE4441, CSE4443), principles of usability (CSE3461); students who do not have this background may be suitable, to be determined by supervisor
 +
 +**Topic**: Assistive technology to circumvent barrariers arising from severe vision impairment. Student will undertake a 13-week research study, case study format.
 +
 +Expectations:
 +  * Identify top open-source tools for OS navigation and web browser navigation (screen reading apps) [windows platform] with a particular focus on sw that takes advantage of haptic feedback devices; compare & contrast these apps with Kurzweil and JAWS; develop recommendations [2-3 weeks];
 +  * Conduct evaluation using a single subject design (participant is already confirmed and committed) [8-9 weeks];
 +  * Analysis & summarization of results [2 weeks].
 +
 +An objective of this project is to submit the results for publication in a venue related to Assistive Technology. 
 +
 +
 +\\
 +====== Automatic 3D Traffic Analysis from COMPASS Highway Camera Data ======
 +
 +**Supervisor**: James Elder
 +
 +**Required Background**: Good programming skills. Good math skills. Knowledge of MATLAB programming language.
 +
 +With the availability of highway camera networks, such as the COMPASS system operated by the Ministry of Transportation Ontario (MTO), there is opportunity to use continuous video data to monitor highway traffic.  Video can be analyzed by human experts but this is costly and cannot be done thoroughly on a continuous basis. The goal of the proposed project is to research and develop a fully-automated traffic analysis software, demonstrated and evaluated on MTO's COMPASS system of highway cameras.
 +
 +This technology will be developed in four stages:
 +  - Automatic real-time calibration methods for estimating camera focal length and camera pose
 +  - Automatic real-time video rectification, providing plan view or other desired perspectives
 +  - Accurate automatic video detection and tracking of individual vehicles
 +  - Accurate automatic estimation of vehicle speed
 +
 +
 +Solutions for the calibration and rectification problems are crucial for the success of the following objectives, since a) speed cannot be accurately estimated unless focal length and tilt angle are known, b) traffic incidents cannot be reliably geo-located and flow cannot be accurately measured unless pan angle is also known.  
 +
 +In particular, working with a senior graduate student or postdoctoral fellow, the successful applicant will:
 +
 +  - Adapt our novel method for pre-attentive Bayesian fusion of multiple weak cues [5], proven to be successful for human pedestrian detection, to the vehicle detection problem. 
 +  - Develop a novel appearance model, Kalman-filter tracker and optimal bipartite inter-frame matching algorithm specifically for highway vehicle tracking. 
 +  - Further develop and deploy shadow removal methods currently under development in the 
laboratory for another application (sports videography). 
 +
 +For more information about the lab, visit www.elderlab.yorku.ca.
 +
 +\\
 +
 ====== Attentive Sensing for Better Two-Way Communication in Remote Learning Environments ====== ====== Attentive Sensing for Better Two-Way Communication in Remote Learning Environments ======
  
Line 19: Line 65:
   - Evaluate these algorithms in a real-classroom setting, using proprietary attentive sensing technology   - Evaluate these algorithms in a real-classroom setting, using proprietary attentive sensing technology
  
 +\\
 ====== Attentive Sensing for Sport Video Recording Markets ====== ====== Attentive Sensing for Sport Video Recording Markets ======
  
Line 36: Line 82:
 2.     Evaluate current attentive algorithms on these datasets 2.     Evaluate current attentive algorithms on these datasets
 3.     Modify these algorithms to improve performance on these datasets 3.     Modify these algorithms to improve performance on these datasets
-  
------------- 
    
  
Line 58: Line 102:
  
 **Required Background:** General CSE408x prerequisites **Required Background:** General CSE408x prerequisites
-\\  + 
-------------+
 \\  \\ 
 ======Hybrid 2D/3D User Interfaces for 3D Rotation ====== ======Hybrid 2D/3D User Interfaces for 3D Rotation ======
Line 68: Line 112:
  
 This project implements and evaluates a new method for 3D Rotation where the user uses both a 2D and 3D user interface to complete the task. The fundamental idea is to use the 3D interface for large-scale manipulation, but the 2D interface for precise adjustments. The project will use a Leap Motion or similar technology for 3D tracking. This project implements and evaluates a new method for 3D Rotation where the user uses both a 2D and 3D user interface to complete the task. The fundamental idea is to use the 3D interface for large-scale manipulation, but the 2D interface for precise adjustments. The project will use a Leap Motion or similar technology for 3D tracking.
-\\  + 
-------------+
 \\  \\ 
 ====== Immersive Virtual Reality Kitchen Planner ====== ====== Immersive Virtual Reality Kitchen Planner ======
Line 78: Line 122:
  
 This project implements a kitchen planner application for an immersive virtual reality system. The implementation will be based on Unity 4. This project implements a kitchen planner application for an immersive virtual reality system. The implementation will be based on Unity 4.
-\\  + 
-------------+
 \\  \\ 
 ======3D Interaction in Immersive Virtual Reality====== ======3D Interaction in Immersive Virtual Reality======
Line 88: Line 132:
  
 This project implements and tests various 3D Navigation and 3D Interaction methods in an immersive virtual reality system. The target is to enable the user to roam freely in a large environment while still being able to interact with the environment. The implementation will be based on Unity 4. This project implements and tests various 3D Navigation and 3D Interaction methods in an immersive virtual reality system. The target is to enable the user to roam freely in a large environment while still being able to interact with the environment. The implementation will be based on Unity 4.
-\\  + 
-------------+
 \\ \\
 ====== Leveraging binary instrumentation to support monitoring and debugging of large scale software system in the field====== ====== Leveraging binary instrumentation to support monitoring and debugging of large scale software system in the field======
Line 97: Line 141:
  
 **Short Description:** Many large scale software systems ranging from e-commerce websites (e.g., eBay) to telecommunication infrastructures (e.g., AT&T) are required to be available and ready to service by millions of users all the time. It is essential to monitor the behavior of these systems in the field and troubleshoot problems whenever they arise. On one hand, many existing monitoring tools (e.g., PerfMon and pidstat) mainly focus on the high level resource usage data (e.g., CPU and memory). On other hand, although profilers (e.g., JProfiler and DTrace) can provide detailed information on the internal system behavior, it is not feasible to run them with the field systems due to their high overhead. Binary instrumentation is a program analysis technique, which can add additional monitoring points without modifying or restarting the system. This project aims to explore the feasibility of leveraging binary instrumentation to automatically monitor and debug the behavior of these field systems. The student(s) will first evaluate the pros and cons on various binary instrumentation libraries (e.g., ASM and PIN). Then he/she will implement a monitoring/debugging framework using the selected instrumentation library. **Short Description:** Many large scale software systems ranging from e-commerce websites (e.g., eBay) to telecommunication infrastructures (e.g., AT&T) are required to be available and ready to service by millions of users all the time. It is essential to monitor the behavior of these systems in the field and troubleshoot problems whenever they arise. On one hand, many existing monitoring tools (e.g., PerfMon and pidstat) mainly focus on the high level resource usage data (e.g., CPU and memory). On other hand, although profilers (e.g., JProfiler and DTrace) can provide detailed information on the internal system behavior, it is not feasible to run them with the field systems due to their high overhead. Binary instrumentation is a program analysis technique, which can add additional monitoring points without modifying or restarting the system. This project aims to explore the feasibility of leveraging binary instrumentation to automatically monitor and debug the behavior of these field systems. The student(s) will first evaluate the pros and cons on various binary instrumentation libraries (e.g., ASM and PIN). Then he/she will implement a monitoring/debugging framework using the selected instrumentation library.
- \\  
------------- 
-\\  
  
 +
 +\\ 
 ====== Mining Software Repositories Data====== ====== Mining Software Repositories Data======
  
Line 110: Line 153:
  
 \\  \\ 
------------------- 
-\\  
- 
 ======Reliably tracking horizontal eye movements====== ======Reliably tracking horizontal eye movements======
  
Line 120: Line 160:
  
 **Description:** The Intel Perceptual Computing SDK includes support for head tracking and facial analysis. The project will use the Creative Interactive Gesture Camera, a depth camera designed to work with the SDK. Based on these technologies, the project implements an eye tracking system that detects the horizontal eye position and consequently, if the user is looking at the left, center, or right portion of the screen. Based on this, the project will implement a simple media browsing browsing system, e.g., for TV channels, music, or videos. **Description:** The Intel Perceptual Computing SDK includes support for head tracking and facial analysis. The project will use the Creative Interactive Gesture Camera, a depth camera designed to work with the SDK. Based on these technologies, the project implements an eye tracking system that detects the horizontal eye position and consequently, if the user is looking at the left, center, or right portion of the screen. Based on this, the project will implement a simple media browsing browsing system, e.g., for TV channels, music, or videos.
-----------------------------------+ 
 + 
 +\\  
 +======Model-based Design and Development of Embedded Systems with Code Generation Tools====== 
 + 
 +**Supervisor:** Jia Xu 
 + 
 +**Required Background:** At least a B+ in Embedded Systems (CSE3215), MATLAB, C programming skills, solid experience in using a microcontroller 
 +such as Arduino. 
 + 
 +**Project Description:** 
 + 
 +Model-based design with code generation tools can be used for simulation, rapid prototyping, and hardware-in-the-loop testing of embedded systems. This project explores model-based design and development of embedded systems on various hardware platforms with code generation tools. The selected student will develop and test embedded systems using model-based design and code generation tools such as MathWorks MATLAB /Simulink Coder. 
 + 
 + 
 +\\  
 +======C2000 Concerto Microcontrollers====== 
 + 
 +**Supervisor:** Jia Xu 
 + 
 +**Required Background:** At least a B+ in Embedded Systems (CSE3215), 
 +strong C programming skills, solid knowledge of microcontrollers 
 + 
 +**Description:** The C2000 Concerto family of microcontrollers combines 
 +two cores on a single-chip with on-chip low latency interprocessor communication between the two cores: a C28x 32-bit control core for 
 +real-time control with faster/more loops and small sampling window; 
 +and an ARM 32-bit Cortex-M3 host core for communications and general purpose. The selected student will evaluate the capabilities of the 
 +C2000 Concerto family of microcontrollers through testing and investigating open source software for real-time control applications 
 +that runs on C2000 Concerto Microcontrollers. 
 + 
 + 
 +\\  
 +======Real-Time Bidding Platform====== 
 + 
 +**Supervisor:** Jia Xu 
 + 
 +**Required Background:** At least a B+ in Operating System Fundamentals 
 +(CSE3221), strong Ubuntu/Linux, C++ programming, GCC, TCP/IP skills 
 + 
 +**Description:** Real-time bidding (RTB) is a new method of selling and buying online display advertising in real-time one ad impression at a time. Once a bid request has been sent out, all bids must be received within a strict deadline - generally under 100 milliseconds, including network latency. This project explores RTBkit, an open source SDK allowing developers to create customized real time ad bidding systems (for Media Buyers/Bidders). 
 + 
 + 
 +\\  
 +======Circuit and Board Design for a Pulsed Ground Penetrating Radar====== 
 + 
 +**Supervisor:**Sebastian Magierowski 
 + 
 +**Description:** The project requires the construction of components for a ground penetrating radar.  The students would have to design microwave boards for the high-frequency components of this unit, on both the transmitter and the receiver.  On the transmitter side the board would take a 5-MHz input clock, run it through a series of off-the-shelf amplifiers and then through a shaping circuit that would convert the input into an outgoing series of pulses (still at 5-MHz repetition rate) less than 400-ps in duration each.  The bandwidth of the signal is roughly 2-8 GHz and hence requires very careful board layout.  The receiver would be a time-shifted sampler, used to sample the returning pulses in progressive periods.  This radar circuit is ultimately intended to be positioned on a rover doing ground analysis. 
 + 
 +**Required Background** A background in undergraduate-level electronics is very important.  Experience with board level implementations and knowledge of microstrip lines would be helpful, otherwise the basics would have to be picked up during the project. 
 \\  \\ 
 ------------------ ------------------
 \\  \\ 
-More project proposals may be added here in the first week of fall term.+More project proposals may be added here in the first week of the summer term.
 \\  \\ 
 ------------------ ------------------
 \\  \\ 
 \\  \\ 
projects.1378688113.txt.gz · Last modified: 2013/09/09 00:55 by pd
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki