Lahore University of Management Sciences Lahore University of Management Sciences

Computer Vision

Computer Vision focuses upon the theories behind and the practical applications of machines that can 'see', that is, extract useful information from an image or video, to carry out certain functions or tasks. Current research in the Computer Vision Lab at LUMS focuses on applications of this field for developing countries. In this context, recent projects include the development of a crawler for Google Earth that allows for segmentation of nucleated villages in satellite imagery, as well as the development of a low-cost ultrasound training simulator that will allow trainee doctors to practice without relying on real patients, and innovative ways to map socio-economic parameters for Pakistan.

Research Publications

  • Hands-on Experience in Image Processing: The Automated Lecture Cameraman
    A. Cavallaro, R. Chandrasekera, and M. Taj
    Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Honolulu, USA, 15–20 April 2007
  • Multiview Structure from Motion in Trajectory Space
    Aamer Zaheer, Ijaz Akhter, Mohammad Haris Baig, Shabbir Marzban, Sohaib Khan
    International Conference on Computer Vision (ICCV), 2011
  • Correlation Coefficient Based Fast Template Matching Through Partial Elimination
    Arif Mahmood, Sohaib Khan
    IEEE Transactions on Image Processing, Vol. 21, No. 4, April 2012
  • Efficient Multi-target Visual Tracking Using Random Finite Sets
    E. Maggio, M. Taj and A. Cavallaro
    IEEE Trans. Circuits Syst. Video Technol., vol. 18, no. 8, pp. 1016–1027, August 2008
  • Content and Task-based View Selection from Multiple Video Streams
    F. Daniyal, M. Taj and A. Cavallaro
    Data Semantics from Multi-media Systems, Special Issue: Semantic Multimedia, Vol. 46, No. 2-3, pp. 235-258, January 2010
  • Content-aware Ranking of Video Segments
    F. Daniyal, M. Taj and A. Cavallaro
    ACM/IEEE Int. Conf. on Dist. Smart Cameras, Stanford, CA, USA, 07–11 September 2008
  • Distributed Visual Sensing for Virtual Top-view Trajectory Generation in Football Videos
    G. Kayumbi, P. Mazzeo, P. Spagnolo, M. Taj and A. Cavallaro
    Proc. of ACM Int. Conf. on Image and Video Retrieval, Niagara Falls, CA, 7–9 July 2008
  • Target Detection and Tracking with Heterogeneous Sensors
    H. Zhou, M. Taj and A. Cavallaro
    IEEE Journal of Selected Topics in Signal Processing, vol. 2, no. 4, pp. 503–513, August 2008
  • Audiovisual Tracking using STAC Sensors
    H. Zhou, M. Taj, and A. Cavallaro
    ACM/IEEE Int. Conf. on Dist. Smart Cameras, Vienna, AT, 25–28 September 2007
  • Bilinear Spatiotemporal Basis Models
    Ijaz Akhter, Tomas Simon, Sohaib Khan, Iain Matthews, Yaser Sheikh
    ACM Transactions on Graphics, Vol. 31, No. 2, April 2012
  • Trajectory Space: A Dual Representation for Nonrigid Structure from Motion
    Ijaz Akhter, Yaser Sheikh, Sohaib Khan, Takeo Kanade
    IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 33, No. 7, July 2011
  • Multi-modal Particle Filtering Tracking Using Appearance, Motion and Audio Likelihoods
    M. Bregonzio, M. Taj, and A. Cavallaro
    Proc. of IEEE Int. Conf. on Image Processing, San Antonio, TX, USA, 16–19 September 2007
  • Multi-view Multi-object Detection and Tracking, Computer Vision: Detection, Recognition and Reconstruction
    M. Taj and A. Cavallaro
    Springer Verlag GmbH, July 2010
  • Recognizing Interactions in Video. Intelligent Multimedia Analysis for Security Applications
    M. Taj and A. Cavallaro
    Springer Verlag GmbH, April 2010
  • Distributed and Decentralized Multi-camera Tracking: A Survey
    M. Taj and A. Cavallaro
    IEEE Signal Processing Magazine, Special issue: Distributed Image Processing and Communications, vol. 28, issue 3, pg. 46-58, May 2011
  • Multi-Camera Track-Before-Detect
    M. Taj and A. Cavallaro
    ACM/IEEE Int. Conf. on Dist. Smart Cameras, Como, IT, 30 August–02 September 2009
  • Audio-Assisted Trajectory Estimation in Non-overlapping Multi-camera Networks
    M. Taj and A. Cavallaro
    IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Taipei, TW, 19–24 April 2009
  • Object and Scene-centric Activity Detection Using State Occupancy Duration Modeling
    M. Taj and A. Cavallaro
    IEEE Int. Conf. on Advanced Video and Signal Based Surveillance, Santa Fe, NM, USA, 1–3 September 2008
  • Multi-camera Scene Analysis Using an Object-Centric Continuous Distribution Hidden Markov Model
    M. Taj and A. Cavallaro
    Proc. of IEEE Int. Conf. on Image Processing, San Antonio, TX, USA, 16–19 September 2007
  • Simultaneous Detection and Tracking with Multiple Cameras, Computer Vision and Machine Learning for Image and Video Analysis
    M. Taj and A. Cavallaro
    Springer Verlag GmbH, 2013
  • Interaction recognition in wide areas using audiovisual sensors
    M. Taj, and A. Cavallaro
    IEEE Int. Conf. on Image Processing, Orlando, FL, USA, 30 September 2012.
  • Objective Evaluation of Pedestrian and Vehicle Tracking on the CLEAR Surveillance Dataset
    M. Taj, E. Maggio, and A. Cavallaro
    Classification of Events, Activities and Relationships Workshop, Springer LNCS 4625, Baltimore, MD, USA, 8–11 May 2007
  • Multi-feature Graph-based Object Tracking
    M. Taj, E. Maggio, and A. Cavallaro
    Classification of Events, Activities and Relationships Workshop, Springer LNCS 4122, pp. 190–199, Southampton, UK, 6–7 April 2006
  • Event Analysis on TRECVid 2008 London Gatwick Dataset
    M. Taj, F. Daniyal, and A. Cavallaro
    TREC Video Retrieval Workshop, Gaithersburg, MD, USA, 17–18 November 2008
  • Multi-camera Calibration and Event Recognition with Outlier Behaviour Detection
    M. Taj, N. Anjum, and A. Cavallaro
    Proc. of Int. Crime Science Conf, London, UK, 16–17 July 2007
  • Relative Position Estimation of Non-overlapping Cameras
    N. Anjum, M. Taj, and A. Cavallaro
    Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Honolulu, HI, USA, 15–20 April 2007
  • Detection and Tracking of Humans and Faces
    S. Karlsson, M. Taj and A. Cavallaro
    EURASIP Journal on Image and Video Processing, vol. 2008, no. 1, 2008
  • Geodetic Alignment of Aerial Video Frames
    Sheikh, Y.A., Khan, S.A., Shah, M., Cannatta, R.
    Video Registration, Kluwer Academic Publishers, Boston, May 2003