Tag: arif mahmood

Statistically Correlated Multi-task Learning for  Autonomous Driving

Statistically Correlated Multi-task Learning for Autonomous Driving

| August 1, 2019 | 0 Comments

Waseem Abbas, M. Fakhir Khan, Murtaza Taj, and Arif Mahmood Abstract Autonomous driving research is an emerging domain in computer vision and machine learning areas. Most existing methods perform Single Task Learning (STL) from one or more images while Multi-Task Learning (MTL) is more efficient due to the leverage of shared information between different tasks. […]

Continue Reading

Arif Mahmood

Arif Mahmood

| August 6, 2012

Arif Mahmood successfully defended his Ph.D. at Lahore University of Management Sciences in May 2011. Dr. Mahmood’s research interests broadly span the areas of image processing and computer vision. More specifically, he is interested in optimization of image processing algorithms from computational perspective. He worked on fast image matching techniques and developed new bound based […]

Continue Reading

Correlation Coefficient Based Fast Template Matching Through Partial Elimination – Project Page

| April 21, 2012

Project page of our IEEE Transactions on Image Processing April 2012 paper on “Correlation Coefficient Based Fast Template Matching Through Partial Elimination”. Contains datasets and code.

Continue Reading

TIP 2012 – Correlation Coefficient Based Fast Template Matching Through Partial Elimination

TIP 2012 – Correlation Coefficient Based Fast Template Matching Through Partial Elimination

| April 1, 2012

Arif Mahmood, Sohaib Khan IEEE Transactions on Image Processing, Vol 21, No 4, April 2012 Abstract Partial computation elimination techniques are often used for fast template matching. At a particular search location, computations are prematurely terminated as soon as it is found that this location cannot compete already known best-match location. Due to non-monotonic growth […]

Continue Reading

PhD Dissertation Defense: Arif Mahmood

| May 1, 2011

Arif Mahmood successfully defended his Ph.D. thesis on May 27, 2011 at LUMS, Lahore. Thesis Abstract: Template matching is frequently used in Digital Image Processing, Machine Vision, Remote Sensing and Pattern Recognition, and a large number of template matching algorithms have been proposed in literature. The performance of these algorithms may be evaluated from the […]

Continue Reading

Exploiting Transitivity of Correlation for Fast Template Matching – Project Page

| August 21, 2010

Project page of our IEEE Transactions on Image Processing Aug 2010 paper, “Exploiting Transitivity of Correlation for Fast Template Matching”. Contains links to datasets and code.

Continue Reading

TIP 2010 – Exploiting Transitivity of Correlation for Fast Template Matching

TIP 2010 – Exploiting Transitivity of Correlation for Fast Template Matching

| August 8, 2010

Arif Mahmood, Sohaib Khan IEEE Transactions on Image Processing, Vol 19, N0. 8, Aug 2010 Abstract Elimination Algorithms are often used in template matching to provide a significant speed-up by skipping portions of the computation while guaranteeing the same best-match location as exhaustive search. In this work, we develop elimination algorithms for correlation-based match measures […]

Continue Reading

ICIP 2009 – Early Termination Algorithms for Adaboost Based Detectors

ICIP 2009 – Early Termination Algorithms for Adaboost Based Detectors

| November 8, 2009

Arif Mahmood, Sohaib Khan 16th International Conference on Image Processing, Cairo, Egypt, Nov 7-10, 2009 Abstract In this paper we propose an early termination algorithm for speeding up the detection phase of the Adaboost based de- tectors. In the basic algorithm, at a specific search location, the AdaBoost ensemble response is computed as monotonic decreasing […]

Continue Reading

ICIP 2008 – Exploiting Local Auto-Correlation Function for Fast Video-to-Reference Image Alignment

ICIP 2008 – Exploiting Local Auto-Correlation Function for Fast Video-to-Reference Image Alignment

| October 9, 2008

Arif Mahmood, Sohaib Khan 15th IEEE International Conference on Image Processing, ICIP 2008 Abstract Digital images of natural scenes are usually characterized by strong spatial correlation between adjacent pixels which has been successfully exploited in the coding of still and moving pictures. In this work we show that the strong spatial correlation of natural images […]

Continue Reading

Video Coding Using Linear Compensation (VCLC) – Project Page

Video Coding Using Linear Compensation (VCLC) – Project Page

| August 19, 2008 | 0 Comments

Arif Mahmood, Zartash Uzmi, Sohaib Khan Download our paper here. For a presentation on VCLC click here Abstract Block based motion compensation techniques are commonly used in video encoding to reduce the temporal redundancy of the signal. In these techniques, each block is matched with an other block in a previous frame. The match criteria, […]

Continue Reading