Detection of Fights in Crowd Video

Detection of fights and anomalous behavior of individuals in a crowd is a common problem in computer vision. Some tools that currently exist rely on optical flow of tracked features is a sequence of video frames. These motion algorithms are sensitive to independently moving objects in the frame. What constitutes an “anomaly” is context (eg. […]

Read More
AI based Pointing and Tracking for Satcom Terminals

Aimed at maximizing the antenna signal of the satellite communication (Satcom) terminal in a satellite system, positioning and tracking methods based on AI are studied in this project. This proposal focuses on the issue of a satellite’s pointing and tracking for a stationary Satcom terminal. The detailed methods includes the following four functional components: 1) […]

Read More
Characterisation of Millimeter-Wave Power Amplifiers and Application of Novel Digital Predistortion Techniques

To pave the road towards the upcoming 5th Generation of telecommunication standards (5G), we aim to develop a fully integrated solution satisfying the increasing requirements in terms of wide bandwidth, small footprint, and high-power efficiency. Initially, we prepare a fully automated setup to characterize the Gallium Nitride (GaN) Power Amplifiers (PA) considered as key components […]

Read More
Drive Continuous Innovation Growth in Canada

Many reports have indicated that with the current state of Canada’s science and technology, Canada is not globally competitive in business innovation, and the current state of growth is not sustainable. How to drive continuous innovation growth in Canada? This proposal centers on three areas: (1) continuous innovation growth in large incumbents, (2) viable business […]

Read More
Data Pipeline of Artificial Intelligence Applications

The overarching goal of this project is to research the feasibility of a low-cost, general purpose data pipeline that can learn and adapt to large, varied and dynamic data sets. Specifically, we will utilize a large sample of 3D gait and motion data captured from a cohort of research participants with dementia or mild cognitive […]

Read More
To analyze and identify White Box techniques that can be used to protect cryptographic operations of various ciphers, starting with SM4 Symmetric Block Cipher

White-box cryptography seeks to maintain the secrecy of cryptographic keys used by software, despite an attacker having full control over the software. This project extends the work by Dr. Lin on the Chinese cipher SM4, as well as its application to a further cipher. The goal of this project is: 1) To implement a complete […]

Read More
Condition assessment of infrastructure facilities using combined image processing and sensing technologies

As Canada’s infrastructure grow older every year, the inspection and maintenance of these capital intensive assets becomes more challenging. Most deterioration mechanism occur over a long period of time. Certain defects remain unnoticed during regular inspection until it is too late. Unfortunately, delayed diagnosis of defects can significantly increase the annual cost of maintenance. Inspectors […]

Read More
End-of-line Testing for Safety and Quality with Machine Learning

Safety-critical systems are pervasive throughout our society with everyday objects such as airplanes, cars, trains, or medical devices. The requested functionality and expectations from these systems are growing rapidly and consequently, they become more complex. The complexity is usually handled by breaking the system into manageable smaller components and parts. Factories then integrate these parts […]

Read More