Skip to main content
Faisal Qureshi

Faisal Qureshi
PhD

Professor

Faculty of Science

Advancing theory and models for intelligent visual systems—spanning hyperspectral analysis, video understanding, industrial anomaly detection, and networks of smart cameras—that perceive, interpret, and act in dynamic environments.

@faisalzqureshi

Contact information

Science Building - Room UA4071
North Oshawa
2000 Simcoe Street North
Oshawa, ON L1G 0C5

905.721.8668 ext. 3626

faisal.qureshi@ontariotechu.ca
https://vclab.ca/

Research topics

  • Visual Sensor Networks
  • Multicamera Tracking
  • Visual Anomaly Detection
  • Video Summarization
  • Stereo Depth Estimation
  • Optical Flow Estimation
  • Hyperspectral Image Analysis
  • Deep Networks for Computer Vision
  • Activity Analysis
  • Action Recognition
  • Image Inpainting
  • Video Surveillance

Areas of expertise

  • Computer Vision
  • Hyperspectral Image Analysis
  • Deep Learning
  • Smart Camera Networks
  • Computer Science

Background

Dr. Qureshi is a Professor of Computer Science at Ontario Tech University, where he leads the Visual Computing Lab. His research explores computational models of visual perception to support intelligent behavior in dynamic environments, with applications in hyperspectral imaging, video understanding, anomaly detection, and networks of smart cameras. He received his Ph.D. and M.Sc. degrees in Computer Science from the University of Toronto in 2007 and 2000, respectively; an M.Sc. in Electronics from Quaid-e-Azam University, Islamabad, in 1995; and a B.Sc. in Mathematics and Physics from Punjab University, Lahore, in 1993. Dr. Qureshi is also a Guest Professor at Mid Sweden University.

Education

  • PhD Computer Science University of Toronto 2007
  • MSc Computer Science University of Toronto 2001
  • MSc Electronics Quaid-e-Azam University 1995
  • BSc Mathematics and Physics (Minor) Punjab University 1992

Courses taught

  • CSCI 1061U - Programming Workshop II
  • CSCI 2050U - Computer Architecture
  • CSCI 3050U - Computer Architecture II
  • CSCI 3070U - Design and Analysis of Algorithms
  • CSCI 3010U - Simulation and Modeling
  • CSCI 3090U - Computer Graphics
  • CSCI 4110U - Advanced Computer Graphics
  • CSCI 4220U - Computer Vision
  • Graduate courses in Computer Vision, Deep Learning, and Machine Learning

Involvement

  • Selected publications
    • TLAC: Two-stage LMM Augmented CLIP for Zero-Shot Classification. Munir, A.; Qureshi, F. Z.; Khan, M. H.; and Ali, M. In Proc. 8th Multimodel Learning and Applications Workshop (co-located with CVPR 2025), pages 11pp, Nashville, TN, June 2025.
    • Hyperspectral Image Compression Using Sampling and Implicit Neural Representations. Rezasoltani, S.; and Qureshi, F. Z. IEEE Transactions on Geoscience and Remote Sensing, 63: 12pp. December 2024.
    • Hyperspectral Pixel Unmixing with Latent Dirichlet Variational Autoencoder. Mantripragada, K.; and Qureshi, F. Z. IEEE Transactions on Geoscience and Remote Sensing, 62: 13pp. January 2024.
    • The Effects of Spectral Dimensionality Reduction on Hyperspectral Pixel Classification: A Case Study. Mantripragada, K.; Dao, P. D.; He, Y.; and Qureshi, F. Z. PLOS ONE, 17(7): 24pp. July 2022.
    • Improving hyperspectral image segmentation by applying inverse noise weighting and outlier removal for optimal scale selection. Dao, P. D.; Mantripragada, K.; He, Y.; and Qureshi, F. Z. ISPRS Journal of Photogrammetry and Remote Sensing, 171: 348 - 366. 2021.
    • “A Residual-Dyad Encoder Discriminator Network for Remote Sensing Image Matching,” Khurshid, N.; Mohbat; Taj, M.; and Qureshi, F. IEEE Transactions on Geoscience and Remote Sensing, 14pp., 2019. In press
    • “Joint Spatial and Layer Attention for Convolutional Networks,” Joseph, T.; Derpanis, K.; and Qureshi, F. In 30th British Machine Vision Conference (BMVC19), 14pp, Cardiff, Sep 2019.
    • “Neural Networks Trained to Solve Differential Equations Learn General Representations,” Magill, M.; Qureshi, F.; and de Haan, H. In The Thirty-second Annual Conference on Neural Information Processing Systems (NuerIPS 18), 11pp, Montreal, Dec 2018.
    • “Fast Estimation of Large Displacement Optical Flow Using Dominant Motion Patterns & Sub-Volume PatchMatch Filtering,” Helala, M.; and Qureshi, F. In 14th Conference on Computer and Robot Vision (CRV 17), 8pp, Edmonton, May 2017. Best Computer Vision Paper
    • “Stereo Reconstruction of Droplet Flight Trajectories,” L.A. Zarrabitia; F.Z. Qureshi; and D.A. Aruliah. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(4), April, 2015, 847–861.
    • “Smart Camera Networks in Virtual Reality,” F.Z. Qureshi; and D. Terzopoulos. Proceedings of the IEEE, 96(10), October, 2008, 1640–1656, (Special Issue on “Smart Cameras”).
    • “Intelligent Perception and Control for Space Robotics: Autonomous Satellite Rendezvous and Docking,” F.Z. Qureshi; and D. Terzopoulos. Journal of Machine Vision Applications, 19(3), February, 2008, 141–161.