Hicham Sekkati

Short biography

I am currently a postdoc at VIP lab, University of Waterloo, ON. I recieved both my M.Sc. and Ph.D in computer sciences at Institut National de la Recherche Scientifique, Montreal, QC, in 2003 and 2005, respectively. I was a postdoc in computer science/computer engineering at University of Miami, FL, University of Ottawa, ON, and Ecole Polytechnique de Montreal, QC, in 2005, 2011, and 2012, respectively. From 2007 to 2010, I filled a key position in a startup company (SPGDATA 3D) as computer vision researcher/Technical Director. I also filled an R&D position in game industry as computer vision scientist between 2012 and 2015. 

Supervisors

Alexander Wong, David A. Clausi

Research interests

My primary research interests lie in visual scene understanding. I am mainly concerned with solving problems arising in visual perception and action recognition, which are key components in many vision applications such as surveillance, robot guidance, multi-modal image interpretation, remote sensing, and visual field monitoring. I also focus my attention on the processing of optical/sonar images for underwater vision applications. Recently I’ve had a chance to explore many aspects falling at the edges between computer vision, computer graphics, and machine learning, such as performance-based animation, procedural animation, shape descriptors and spectral geometry for shape analysis.

Research topics

Computer Vision

Image Segmentation/Classification

Scientific Imaging

Stochastic Models

Video Analysis

Publications

Journal papers

• H. Sekkati and S. Negahdaripour, “Opti-Acoustic Stereo Imaging: On System Calibration and 3-D Target Reconstruction”, IEEE Transactions on Image Processing, vol. 18, issue 6, pp. 1203-1214, 2009.
• H. Sekkati and A. Mitiche, “Concurrent 3D-motion segmentation and 3D interpretation of temporal sequences of monocular images”, IEEE Trans. on Image Processing, vol. 15, n_◦ 3, pp. 641-653, 2006.
• H. Sekkati and A. Mitiche, “Dense 3D Interpretation of Monocular Image Sequences: A Boundary Preserving Variational Approach Using Anisotropic Diffusion”, International Journal of Au­tomation, Robotics and Autonomous Systems, vol. 55, n 7, 597-607, 2007.
• Mitiche and H. Sekkati, “Optical flow 3D segmentation and interpretation: A variational method with active curve evolution and level sets”, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 28., n_◦ 11, pp. 1818-1829, 2006.
• H. Sekkati and A. Mitiche, “Join optical flow estimation, segmentation, and 3D interpretation with level sets”, Special issue of CVIU commemorating the career of Prof. Azriel Rosenfeld. vol. 103., n_◦ 2, pp. 89-100, 2006.

Conferences with committee

• H.Sekkati, R.Laganiere, and A. Mitiche "Robust background subtraction using geodesic active contours in ICA Subspace for video surveillance applications", Ninth Conference on Computer and Robot Vision (CRV 2012).
• A. S. Montero, H.Sekkati, J. Lang, and R.Laganiere "Framework for Natural Landmark-based Robot Localization", Ninth Conference on Computer and Robot Vision (CRV 2012).
• S. Negahdaripour and H. Sekkati and H. Pirsiavash, “Opti-Acoustic Stereo Imaging, System Calibration and 3-D Reconstruction”, IEEE International Workshop on: Beyond Multiview Geometry: Robust Estimation and Organization of Shapes from Multiple Cues 2007, Minneapolis, USA.
• H. Sekkati and S. Negahdaripour, “3-D Motion Estimation for Positioning with 2-D Acoustic Video Imaging Systems”, The third Iberian Conference on Pattern Recognition and Image Analysis, 2007, Girona, Spain.
• H. Pirsiavash, H. Sekkati and S. Negahdaripour, “Integration of Motion Cues in Optical and Acoustic Videos for 3-D Positioning”, the second international ISPRS workshop, held with IEEE CVPR 2007, Minneapolis, USA.
• H. Sekkati and S. Negahdaripour, “Direct and Indirect 3-D Reconstruction from Opti-Acoustic Stereo Imaging”, Third International Symposium on 3D Data Processing, Visualization and Transmission, Chapel Hill, USA, June 14-16, 2006.
• H. Sekkati and A. Mitiche, “Joint Dense 3D Interpretation and Multiple Motion Segmentation of Temporal Image Sequences: A Variational Framework with Active Curve Evolution and Level Sets”, IEEE International Conference on Image Processing (special issue ICIP 2004), Singapour, 2004.
• H. Sekkati and A. Mitiche, “Dense 3D Interpretation of Image Sequences: A variational approach using anisotropic diffusion”, IEEE Computer Society Press in the proceedings of the 12th International Conference on Image Analysis and Processing (ICIAP 2003), Mantova, Italy, 2003.