Architecture for a 3D-Vision FPGA-based System for Real-Time Object Tracking

Object tracking using stereo video is a field of research applicable to a large number of applications. However, most proposed methods are complex, and require significant computing resources to be implemented. As a result, the number of applications and environments where object tracking systems can be realistically deployed is limited. The proposed research project aims to alleviate this problem, by researching and developing a real-time stereo video-based moving object detection and tracking method and architecture utilizing minimal hardware and power resources; the anticipated result of the proposed research will be the developed architecture of the system implemented and tested using a Field-Programmable Gate Array (FPGA) platform. Through this project, the intern will further develop technical skills, as well as obtain a better understanding of industrial R&D procedures. Likewise, the industrial partner will be able to diversify their product range using the developed method and architecture for this novel technology enabling further commercialization.

Faculty Supervisor:

Lev Kirischian

Student:

Victor Dumitriu

Partner:

Soft-R US

Discipline:

Engineering - computer / electrical

Sector:

Information and communications technologies

University:

Ryerson University