Vision and Machine Learning (VML) Research Group

Introduction

The Vision and Machine Learning (VML) Group is dedicated to conducting highly impactful research on the cutting edge of computer vision, machine learning, their application areas as well as real-time software and hardware implementations. Both fundamental and applied research is carried out. The group consists of experts in object tracking, detection, recognition and segmentation, scene understanding (recognition, layout estimation), stereo and multi-view vision, structure from motion, shape from texture, unsupervised and supervised learning methods, and augmented reality.

Team

Publications

1. Farkhanda Aziz, Azhar Ul-Haq, Shahzor Ahmad, Yousef Mahmoud, Marium Jalal and Usman Ali, “A Novel Convolutional Neural Network-Based Approach for Fault Classification in Photovoltaic Arrays”. IEEE Access, 2020.
2. Shahzor Ahmad and Loong-Fah Cheong: Robust Detection and Affine Rectification of Planar Homogeneous Texture for Scene Understanding. International Journal of Computer Vision, 2018.
3. Shahzor Ahmad and Loong-Fah Cheong. Facilitating and Exploring Planar Homogeneous Texture for Indoor Scene Understanding. In Proc. 14th European Conference on Computer Vision (ECCV), Amsterdam, the Netherlands, October 2016.
4. Mohammad Bilal Malik and Usman Ali, “Adaptive Thresholding using Particle Filter for Tracking Small and Low Contrast Objects”, IEEE 10th International Conference on Information Sciences, Signal Processing and their Applications, 2010.
5. Usman Ali, Mohammad Bilal Malik and Khalid Munawar, “FPGA/Soft-Processor Based Real-Time Object Tracking System”, IEEE 5th Southern Programmable Logic Conference, pp. 33-37, 2009.

MS Thesis Alumni

Funded Projects

Contact Person

Dr Shahzor Ahmad

Head VML Research Group

Email: [email protected]