Shafiq Ahmad

Shafiq Ahmad
Istituto Italiano di Tecnologia | IIT · Department of Pattern Analysis and Computer Vision

PhD

About

2
Publications
21,476
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
12
Citations
Introduction
Shafiq Ahmad is PhD Research Fellow at Pattern Analysis & Computer Vision (PAVIS) research group at Italian Institute of Technology (iit). Shafiq does research in Computer Vision and Deep Learning.
Additional affiliations
November 2019 - present
Istituto Italiano di Tecnologia
Position
  • PhD Student
May 2019 - November 2019
COMSATS University Islamabad
Position
  • Research Associate
Description
  • National Center of Artificial Intelligence (NCAI)
February 2019 - May 2019
University of Engineering and Technology, Peshawar
Position
  • Research Associate
Description
  • National Center of Artificial Intelligence (NCAI)
Education
November 2019 - October 2022
Università degli Studi di Genova
Field of study
  • COMPUTATIONAL VISION & AUTOMATIC RECOGNITION
January 2013 - September 2016
Institute of Space Technology
Field of study
  • Electrical Engineering
September 2007 - February 2011
COMSATS University Islamabad
Field of study
  • Electronics Engineering

Publications

Publications (2)
Conference Paper
The large-scale use of surveillance cameras in public spaces raised severe concerns about an individual privacy breach. Introducing privacy and security in video surveillance systems, primarily in person re-identification (re-id), is quite challenging. Event cameras are novel sensors, which only respond to brightness changes in the scene. This char...
Article
Full-text available
In this article, we propose two kinds of improvements to a baseline tracker that employs the tracking-by-detection framework. First, we explore different feature spaces by employing features commonly used in object detection to improve the performance of detector in feature space. Second, we propose a robust scale estimation algorithm that estimate...

Questions

Questions (12)
Question
1) I find corner (Harris Corner) on 1st frame. then
2) Compute Optical Flow and find moition vector (Ux,Vy) between two frames, at corners.
3)then update Coordinates of Corners by adding Ux and Vy. (Cx+Ux, Cy+Vy).
But it fail to track corners. If any one have KLT Simple Tracker Matlab code kindly share with me. 
Question
I have 50 images, want to read them one by one in Matlab.
Question
In the Attached Paper, I have a problem in Mean Shift Vector Equation 10.
Does M(X) => Mean Shift Vector are contain both Vx and Vy or single value ?
Question
I have only problem in how to calculate Target Model & Target Candidates Kernel density from histograms (for gray scale images.)
Let suppose we have histograms H1 and H2 of Target Model & Target Candidates respectively. I want to compute Gaussian kernel Density.
Question
I want to warp frame2 by the reverse motion between the two frames (frame1 and frame2)
Question
Suppose, We have Optical Flow [u v]=[6 6] (only for one Pixel) between two frames (frame1 and frame2).
I want to remove [u' , v']=[4 , 4] motion from frame2 so that when I measure Optical Flow again betw Frame1 and Frame2, motion is [2 , 2]. 
Question
I need a test video for object tracking.
Question
I have series of frames and want to track harris corner using Lucas Kanade. After detecting corner how to track these corners?
Question
I want to track an object using the lucas kanade algorithm, and for features I want to use harris corner.
Question
What are some ongoing challenges in face recognition? I want to do my MS research in this area.

Network

Cited By

Projects

Projects (2)
Project
The aim is to design algorithm for brain tumor detection and segmentation in MRI images using deep learning.
Archived project
First, we explore different feature spaces for object detection to improve the performance of detector in feature space. Second, we propose a robust scale estimation algorithm that estimates the accurate size of the object in the current frame.