Student research opportunities
Rapid Road Sign Detection
Project Code: CECS_173
This project is available at the following levels:
Engn4200, Honours, Summer Scholar, Masters, PhD
Keywords:
Computer Vision, Object Detection, Boosting, Machine Learning, Intelligent Vehicles
Supervisors:
Dr Lars PeterssonDr Gary Overett
Outline:
The AutoMap Project is building robust, high bandwidth road sign detectors for applications in map building for various applications including GPS navigation and road asset management.
This project allows for various avenues of investigation, including novel features for object detection and new learning methodologies for combining existing features.
Goals of this project
To advance the capabilities of the NICTA Automap object detection engine to allow for more robust or more rapid detection of various objects.
To extend the learning capabilities of the existing system to allow the detection of object types which are currently difficult to detect using the pre-existing state-of-the-art approach.
Requirements/Prerequisites
Basic knowledge of digital image processing.
Good knowledge of C/C++, Matlab
Student Gain
Excellent opportunity for students interested in computer vision, image processing and pattern recognition.
Students will have the opportunity to participate in genuine fundamental research with a commercial focus. Students who discover improved object detection methods will have the opportunity to see their research rapidly deployed on object detection systems used regularly on 1000's of kilometres of georeferenced video data.
Links
Automap Project PageProject Video
