Continuous Traffic Detection

Team New Perspective is attempting to implement image processing algorithms on an FPGA that will detect cars moving in traffic and output their position and speed. Current traffic controllers have no way of getting this information quickly enough to affect the flow of traffic in real time. When all the processing is done at the camera, real time traffic control is possible.

Project Specifics
To detect traffic flow without the privacy issues that many current systems have, we have decided to use a method we have termed the “tripwire” method. Certain rows in the camera sensor pixel array will be monitored by the FPGA. When an object significantly different than the background passes across this “tripwire”, the row will “fire” and we will know that the leading edge of an object was at the tripwire. When it hits subsequent tripwires, we will know the same thing. If we know the length between the tripwires, gleaning speed information is easy. We are using the method of background subtraction to detect vehicles. This involves generating a background frame, reading the pixel array for a current frame, and subtracting the current frame from the background frame (resulting in a foreground frame) to see moving objects.

Project Description and Goals
Design a high-speed trapezoidal image sensor and control system for continuous traffic monitoring at signalized intersection approaches

Problem Definition
Currently, obtaining position, speed, and acceleration information on cars in an intersection is a very costly process. It involves actual loops in the the road itself, radar, or the recently invented lidar. Additionally these applications require a lot of computing power and are thus slow. To monitor and control traffic in real time then, a solution that is faster and less expensive is needed. Additional info can be found on the Problem Definition Page.

Project Sponsors
National Institute for Advanced Transportation Technology (NIATT) Tranlive Program

VSRG (VLSI Sensors Research Group)

Dr. Ay is Associate Professor of Electrical and Computer Engineering at University of Idaho. He received his MS and PhD Degrees in Electrical Engineering-Electrophysics from the University of Southern California (USC), Los Angeles, CA, in 1997 and 2004. From September 1997 to July 2007, he was working in the industry as VLSI Design Engineer specializing in the area of mixed-signal VLSI design and CMOS image sensors. He was with Photobit Corporation which later became the Micron Technology Inc.’s Imaging Division in 2001 and Aptina Imaging in 2008. He joined the Department of Electrical and Computer Engineering of University of Idaho on August 2007 as assistant professor and promoted to associate professor in 2013.

His research focuses on VLSI analog and mixed-signal integrated circuit (IC) design techniques for new class of baseband and RF circuits and systems, on intelligent sensor systems with emphasis of reconfigurable, secure, flexible electro-optical circuit and devices, and on self sustained and smart CMOS sensors for remote wireless network and systems. He is a member of IEEE Solid State Circuits, IEEE Circuit and Systems, IEEE Electron Devices, and SPIE societies.

He has a research group called VLSI Sensors Research Group (VSRG)

Glossary of Terms
Rows -  Pixels that run from one side of the street to another perpendicular to the flow of traffic.

Columns -  Pixels that run up and down the street parallel to the flow of traffic.

Background -  A frame recording the unmoving parts of the scene.

Current Frame -  The frame being used to extract foreground objects.

Pixel Fill -  The portion of a pixels shade that can be attributed to a foreground object.

Delta Cap -  The maximum amount of change than can be applied to the background due to a new frame.

Delta Breach -  When a current frame pixel is more than one Delta Cap away from the corresponding background pixel.

Foreground Threshold -  The minimum difference between background and current frame pixels to register a foreground pixel.

Tripwire -  A row of pixels that is being monitored for foreground pixels.

The Team
All senior design teams have different members. Clients, faculty mentors, student mentors, undergraduate, graduates, and even high-school students work together to solve real world problems. More information can be found on Team New Perspectives Team Member Page.

Project Documents
Team Documents Page