HomeAbout
Research
chevron icon
Current ProjectsPast Projects
PeopleTeachingDatabasesPublicationsNews

Human Activity Recognition

Computer Vision & Pattern Recognition

Most video surveillance systems can only provide simple event alarms such as Virtual Perimeter Breach, in which a person crosses an imaginary line (Left), or Abandoned Object Detection. Our goal is to detect more complex multi-persons’ actions such as two people interacting (e.g., shaking hands) or a person interacting with an object (e.g., gun-shooting). This is useful for online surveillance or video database indexing.

Related Publications

  • S. Althloothi, M.H. Mahoor, X. Zhang, R. M. Voyles, “Human Activity Recognition Using Multi-Features and Multiple Kernel Learning”, Journal of Pattern Recognition, Volume 47, Issue 5, Pages 1800–1812, May 2014.
  • Wu, G., Mahoor, M.H., Althloothi, S., Voyles, R., “SIFT-Motion Estimation (SIFT-ME): A New Feature for Human Activity Recognition”, The 2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, Los Vegas, July 2010.
  • Althloothi, S., Voyles, R., Mahoor, M.H., Wu, G., “2D Human Skeleton Model from Monocular Video for Human Activity Recognition”, The 2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, Los Vegas, July 2010.
  • Salah Althloothi, Mohammad H. Mahoor, Richard M. Voyles, “A Robust Method for Rotation Estimation Using Spherical Harmonics Representation”, IEEE Transactions on Image Processing. pp. 2306-2316, Vol. 22, No.6 June 2013.
  • S. Althloothi, M. H. Mahoor, and R. M. Voyles, “Fitting distal limb segments for accurate skeletonization in human action recognition”, Journal of Ambient Intelligence and Smart Environments, Volume 4 (2) IOS Press – Jan 1, 2012.