Kevin Cannons
Department of Computer Science and Engineering
York University
4700 Keele Street
Toronto, Ontario
M3J 1P3
Canada

E-mail:


My CV

About me

Hi, my name is Kevin Cannons. I am currently a Ph.D. candidate at the Department of Computer Science and Engineering at York University in Toronto. I am a member of the Vision Lab and my supervisor is Dr. Rick Wildes.

I received my B.Sc. from (Honours with Distinction) degree in computer engineering from the University of Manitoba, Winnipeg, Canada, in 2003, and my M.A.Sc. degree in computer engineering from the University of Toronto, Canada, in 2005. I also spent the summer of 2007 at Academia Sinica in Taipei, Taiwan as a computer vision research intern developing systems.

Research

My major field of interest is computer vision and my thesis dissertation focuses on the problem of visual tracking. I am highly interested in a number of related computer vision problems including surveillance and action/activity recognition.

Publications

Refereed Journal Publications

• Derpanis, K., Sizintsev, M., Cannons, K., Wildes, R.: Action spotting and recognition based on a spatiotemporal orientation analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI). (Submitted and Under Review).
• Chen, D., Cannons, K., Tyan, H., Shih, S., Liao, H.: Spatiotemporal motion analysis for the detection and classification of moving targets. IEEE Transactions on Multimedia (TMM) 10(8), 1578-1591 (2008). pdf
• Kinsner, W., Cheung, V., Cannons, K., Pear, J., Martin, T.: Signal classification through multifractal analysis and complex domain neural networks. IEEE Transactions on Systems, Man, and Cybernetics, Part C (SMC) 36(2), 196-203 (2006). pdf

Refereed Conference Publications

• Cannons, K., Gryn, J., Wildes, R.: Visual tracking using a pixelwise spatiotemporal oriented energy representation. In: European Conference on Computer Vision (ECCV), pp. 511-524 (2010). pdf supplemental video (requires DIVX, 50 megs) project webpage
• Derpanis, K., Sizintsev, M., Cannons, K., Wildes, R.: Efficient action spotting based on a spacetime oriented structure representation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1990-1997 (2010). pdf supplemental video (requires DIVX, 22 megs) project webpage
• Chen, D., Cannons, K., Tyan, H., Shih, S., Liao, H.: A framework of spatio-temporal analysis for video surveillance. In: IEEE International Symposium on Circuits and Systems (ISCAS), pp. 2745-2748 (2008). pdf
• Cannons, K., Wildes, R.: Spatiotemporal oriented energy features for visual tracking. In: Asian Conference on Computer Vision (ACCV), pp. 532-543 (2007). pdf project webpage
• Barillas, Y., Bressmann, T., Gu, J., Wong, W., Cannons, K., Carmichael, B., Heng, C., Ciccia, M.: Routine clinical ultrasound data acquisition and analysis with the CHASE head anchor and the Ultra-CATS software. In: Third Ultrasound Roundtable, (2005).
• Kinsner, W., Cheung, V., Cannons, K., Pear, J., Martin, T.: Signal classification through multifractal analysis and complex domain neural networks. In: IEEE International Conference on Cognitive Informatics (ICCI), pp. 41-46 (2003). pdf

Technical Reports

• Cannons, K.: A review of visual tracking. Technical Report CSE-2008-07, York University, Department of Computer Science and Engineering, (2008). pdf
• Cannons, K., Wildes, R.: Spatiotemporal oriented energy features for visual tracking. Technical Report CSE-2007-02, York University, Department of Computer Science and Engineering, (2007). pdf

Non-Refereed Presentations

• Cannons, K., Gryn, J., Sizintsev, M., Wildes, R.: Recent advances in spatiotemporal stereo and tracking. MacDonald, Dettwiler and Associates Ltd. Space Vision and Advanced Robotics Workshop, (2009).
• Cannons, K., Elder, J., Estrada, F., Hou, B.: Real-time visual surveillance for search and rescue and other security applications. Ontario Centres of Excellence Centre for Earth and Environmental Technologies Project Review Symposium, (2006).
• Cannons, K.: A biologically inspired gait recognition system using the Hough transform. York University Computer Vision Seminar, (2006).

Teaching and TAing

This semester (Fall, 2010), I am a TA for CSE1019: Discrete Mathematics in the Department of Computer Science and Engineering.

In the past, I have TAed a wide range of courses across the computer science and engineering curriculum at York University, including:

• CSE4210: Architecture and Hardware for DSP
• CSE3221: Operating System Design
• CSE3215: Embedded Systems
• CSE3201: Digital Logic Design
• CSE2001: Introduction to Theory of Computation

In the Winter 2005 semester, I was a guest lecturer for CSC190: Computer Algorithms, Data Structures and Languages in the Department of Electrical and Computer Engineering at the University of Toronto.

In 2004, I also acted as a supervisor for an undergraduate summer researcher while completing my M.A.Sc. at the University of Toronto. The summer student ported an active contour model-based tracker that I had developed and enhanced its ease of use by creating a GUI. The tracker, called Ultra-CATS, can delineate the outline of a human tongue in noisy ultrasound videos. It is available as a free download and has has proven to be very useful for speech-language pathologists internationally because it helps to automate the time-consuming, manual delineation process.