• Home
  
  
• Übersicht
• Forschung
• Lehre
• Mitarbeitende
• Publikationen
• Auszeichnungen
• Sonstiges
  
  
• Aktuelles
• Kontakt

GET-Forschungsseminar Abstracts

Visual Object Tracking

Dr. Faisal Khan, Military College of Signals, National University of Science and Technology, Rawalpindi, Pakistan

Vortrag: Mi. 27.06.2012, 10:45, Raum P 1.4.08.1

Summary: Object tracking has various applications in daily routine and scientific areas.The problem of traking despite varying appearances due to different reasons is adressed in this talk.Powell's method is applied to find normalized cross correlation between the template and the candidates. The occluded objects the tracker starts predicting the location of object using Kalman Filter. For objects that may undergo changes in their acceleration during occlusion, a proximity search is performed to increase the reliability of tracker.The performance of the proposed tracker was better or equivalent to the best existing methods.

Bio: Muhammad Faisal Khan got his PhD and MS degree in Electrical and Computer Engineering from Georgia Institute of Technology, USA in 2004 and 2008 respectively. He did his BS from University of Engineering and Technology, Lahore, Pakistan in 1994. He is working as an Assistant Professor at College of Telecommunication Engineering (MCS), a constituent college of National University of Sciences and Technology (NUST), since Feb 2009. He has setup Broadband and Wireless Networks (BaWN) Lab, Next Generation Networks (NGN) Lab and Video and Image processing (VIP) Lab at MCS. His research interests include broadband access networks, wireless networks, NGN, video processing and image processing. He works on MAC layer, routing layer and transport layer of broadband and wireless networks. He has also worked on the architectural and MAC protocol design of dense wavelength division multiplexing (DWDM) based passive optical networks (PONS).