Feng Shi
Computer Vision Researcher at SPORTLOGiQ
Ottawa, Ontario, Canada
Summary
👤
Senior🎓
Top SchoolFeng Shi is a computer vision researcher with 13 years of experience combining deep academic foundations and practical industry impact, currently building real-time player detection and tracking systems for 4K sports video at SPORTLOGiQ. He holds a PhD in Electrical Engineering from the University of Ottawa and has a strong publication record including papers at CVPR and WACV. Feng specializes in object detection, multi-object tracking, and human action recognition, and has delivered production-grade algorithms in C++ that achieved mAP >99% and 10x speedups on legacy methods. His background includes UAV and satellite image analysis at MDA and novel spatio-temporal descriptors and local part models developed during his doctoral research. Comfortable moving ideas from theory to deployed systems, he blends probabilistic methods (Bayesian inference, Markov chains) with efficient deep learning to solve real-world video analytics problems. An interesting detail: he improved classic HOG-based action recognition substantially and pioneered face-skin heart-rate analysis for emotion and anomaly detection in surveillance video.
13 years of coding experience
6 years of employment as a software developer
Master's degree, Electrical Engineering, Master's degree, Electrical Engineering at University of OttawaGithub contributions (3)
fshi/actionMBH
Mar 2014 - Jun 2014
Contributions:4 commits in 2 months
beahacker/actionMBH
May 2013 - Jul 2013
Contributions:10 commits in 1 month
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.