Computer vision system for ice detection on power cables

In northern countries, ice storms can cause major power disruptions such as the one that occurred in the Toronto area on December 2013 that left more than 300,000 customers with no electricity immediately after the storm. Prediction of ice formation on power cables can help on taking actions for removing the ice before a major problem occurs. Currently Manitoba Hydro HVDC Research Centre has a vision based ice detection system that uses digital images taken from the overhead line conductors. The system, as it is currently implemented, yields a number of misclassification such as an alarm indicating ice formation in a cable that does not present an ice formation problem, no alarm when there is ice, etc. With state of the art digital image processing techniques the project aims to improve the current performance of this system.

Faculty Supervisor:

Gabriel Thomas

Student:

Binglin Li

Partner:

Manitoba Hydro

Discipline:

Engineering - computer / electrical

Sector:

Information and communications technologies

University:

University of Manitoba