Skip to main content

Bouzerdoum, Salim Prof.

Snr Professor of Computer Engineering

  • Faculty of Engineering and Information Sciences
  • School of Electrical, Computer and Telecommunications Engineering
  • Signals, Information and Communications Research Institute (SICOM)
  • Director - Centre for Signal and Information Processing (CSIP)

Overview


Graduated with MSEE and Ph.D. degrees from the University of Washington, Seattle, USA. In 1991, he joined Adelaide University, South Australian, and in 1998 he moved to Edith Cowan University, Perth, as an Associate Professor. He was appointed Professor of Computer Engineering and Head of School of Electrical, Computer & Telecommunications Engineering at the University of Wollongong in 2004, before moving on to become Associate Dean (Research), Faculty of Informatics, in 2007. Professor Bouzerdoum held several Visiting Professor Appointments at Institut Galilée, Université Paris-13 (2004, 2005, 2007, 2008, 2010, 2013, and 2014), LAAS/CNRS, Toulouse, France (2001), Villanova University, USA (2010 and 2013), and the Hong Kong University of Science and Technology (2007). From 2009 to 2011, he was a member of the ARC College of Experts and Deputy Chair of the EMI panel (2010–2011). He served as Associate Editor for 4 International journals, including IEEE! Trans. Systems, Man, and Cybernetics (1999–2006). He has published over 300 technical articles and graduated 36 Ph.D. and Research Masters students.  Professor Bouzerdoum is the recipient of the Eureka Prize for Outstanding Science in Support of Defence or National Security in 2011, the Chester Sall Award of IEEE Trans. Consumer Electronics in 2005, and a Distinguished Researcher Award (Chercheur de Haut Niveau) from the French Ministry in 2001.

Selected Publications


Investigator On


Impact Story


  • <p>Underwater mines are a cost-effective tool in asymmetric warfare and are commonly used to block shipping lanes and restrict naval operations. The aim of this research is develop an automatic system based on sonar imaging for locating naval mines and then recognizing their various types. It involves investigating the latest advances in deep learning and artificial intelligence for object detection, image segmentation, and image classification.<br /><br />This on-going research, supported by the <em>NSW Defence Innovation Network </em>(DIN), is conducted in collaboration with <em>Defence and Science Technology Group</em> (DSTG) and a defence software company. The research team includes Assoc. Prof. Son Lam Phung (<em>CI, Technical Lead, Principal Supervisor</em>), Mr Hoang Thanh Le (PhD Student), Mr Luca Russo (PhD student), Dr. Thi N. A. Nguyen (Associate Research Fellow), Senior Prof. Salim Bouzerdoum (CI), Prof. Christian Ritz (CI), and Dr. Le Chung Tran (CI).<br /><br />In this project, we have developed a deep learning-based tool for underwater mine detection. Further discussions are in progress to apply the project outcomes. </p><p><strong>Publication</strong>: H. T. Le, S. L. Phung, P. B. Chapple, A. Bouzerdoum, C. H. Ritz, L. C. Tran, "Deep Gabor neural network for automatic detection of mine-like objects in sonar imagery," <em>IEEE Access</em>, vol. 8, no. 1, pp. 94126-94139, 2020.</p>
  • <p>Over 250 million people worldwide and 380,000 people in Australia suffer from visual impairment. The aim of the project is to develop, based on deep learning and artificial intelligence technologies, a portable electronic tool that enables a vision-impaired user to perform micro-navigation tasks. The targeted tasks include locating the pedestrian path in crowded scenes, evading obstacles and hazards, and recognising relevant landmarks. The technologies developed in this project can be adopted for road safety, self-driving vehicles, and autonomous robots.<br /><br />This project is funded by an ARC Discovery Project DP190100607, titled "<em>Assistive Micro-Navigation for Project for Vision Impaired People"</em> (2019-2021). It is one of five national projects highlighted in the Ministerial Media Release on 27 Nov 2018 <a href="https://www.arc.gov.au/news-publications/media/media-releases/funding-world-leading-research" target="_blank" rel="noopener">(link)</a>. The research team includes blind volunteers, Assoc. Prof. Son Lam Phung (CI), Senior Prof. Salim Bouzerdoum (CI), Dr Thi N. A. Nguyen (Associate Research Fellow), and a number of PhD/MPhil students.</p><p>This on-going research has received the <strong><em>Best Recognition Paper Award</em></strong> at the International Conference on Digital Image Computing: Techniques and Applications (DICTA) in 2014, and the <em><strong>Highly Commended Award</strong></em> at the Canon Extreme Imaging Competition in 2012. Recently, we have reached a project milestone by successfully developing a deep learning-based tool to locate the pedestrian path for the blind. This tool is published in <em>IEEE TNNLS</em> which has an impact factor of 8.793 (top 10% in 136 computer science and AI journals, and top 5% in 266 electrical/electronic engineering journals).</p><p><strong>Publication</strong>: T. N. A. Nguyen, S. L. Phung, and A. Bouzerdoum, "Hybrid deep learning-Gaussian process network for pedestrian lane detection in unstructured scenes," <em>IEEE Transactions on Neural Networks and Learning Systems, </em>2020. <a href="https://ieeexplore.ieee.org/document/8998354" target="_blank" rel="noopener">(URL)</a></p>

Advisees


  • Graduate Advising Relationship

    Degree Research Title Advisee
    Doctor of Philosophy Deep Learning Algorithms for Image and Signal Processing Applications Le Hoang, Thanh
    Doctor of Philosophy Depth Perception from a Single Colour Image Thompson, Joshua
    Doctor of Philosophy Depth Estimation with Deep Learning for Assistive Navigation Phan, Steve
    Doctor of Philosophy Scene Perception and 3D Sound Synthesis for Assistive Navigation of Blind People Lei, Yunjia
    Master of Philosophy - EIS Deep Learning for Hyperspectral Image Processing Bui, Ly

Selected Publications


Investigator On


Impact Story


  • <p>Underwater mines are a cost-effective tool in asymmetric warfare and are commonly used to block shipping lanes and restrict naval operations. The aim of this research is develop an automatic system based on sonar imaging for locating naval mines and then recognizing their various types. It involves investigating the latest advances in deep learning and artificial intelligence for object detection, image segmentation, and image classification.<br /><br />This on-going research, supported by the <em>NSW Defence Innovation Network </em>(DIN), is conducted in collaboration with <em>Defence and Science Technology Group</em> (DSTG) and a defence software company. The research team includes Assoc. Prof. Son Lam Phung (<em>CI, Technical Lead, Principal Supervisor</em>), Mr Hoang Thanh Le (PhD Student), Mr Luca Russo (PhD student), Dr. Thi N. A. Nguyen (Associate Research Fellow), Senior Prof. Salim Bouzerdoum (CI), Prof. Christian Ritz (CI), and Dr. Le Chung Tran (CI).<br /><br />In this project, we have developed a deep learning-based tool for underwater mine detection. Further discussions are in progress to apply the project outcomes. </p><p><strong>Publication</strong>: H. T. Le, S. L. Phung, P. B. Chapple, A. Bouzerdoum, C. H. Ritz, L. C. Tran, "Deep Gabor neural network for automatic detection of mine-like objects in sonar imagery," <em>IEEE Access</em>, vol. 8, no. 1, pp. 94126-94139, 2020.</p>
  • <p>Over 250 million people worldwide and 380,000 people in Australia suffer from visual impairment. The aim of the project is to develop, based on deep learning and artificial intelligence technologies, a portable electronic tool that enables a vision-impaired user to perform micro-navigation tasks. The targeted tasks include locating the pedestrian path in crowded scenes, evading obstacles and hazards, and recognising relevant landmarks. The technologies developed in this project can be adopted for road safety, self-driving vehicles, and autonomous robots.<br /><br />This project is funded by an ARC Discovery Project DP190100607, titled "<em>Assistive Micro-Navigation for Project for Vision Impaired People"</em> (2019-2021). It is one of five national projects highlighted in the Ministerial Media Release on 27 Nov 2018 <a href="https://www.arc.gov.au/news-publications/media/media-releases/funding-world-leading-research" target="_blank" rel="noopener">(link)</a>. The research team includes blind volunteers, Assoc. Prof. Son Lam Phung (CI), Senior Prof. Salim Bouzerdoum (CI), Dr Thi N. A. Nguyen (Associate Research Fellow), and a number of PhD/MPhil students.</p><p>This on-going research has received the <strong><em>Best Recognition Paper Award</em></strong> at the International Conference on Digital Image Computing: Techniques and Applications (DICTA) in 2014, and the <em><strong>Highly Commended Award</strong></em> at the Canon Extreme Imaging Competition in 2012. Recently, we have reached a project milestone by successfully developing a deep learning-based tool to locate the pedestrian path for the blind. This tool is published in <em>IEEE TNNLS</em> which has an impact factor of 8.793 (top 10% in 136 computer science and AI journals, and top 5% in 266 electrical/electronic engineering journals).</p><p><strong>Publication</strong>: T. N. A. Nguyen, S. L. Phung, and A. Bouzerdoum, "Hybrid deep learning-Gaussian process network for pedestrian lane detection in unstructured scenes," <em>IEEE Transactions on Neural Networks and Learning Systems, </em>2020. <a href="https://ieeexplore.ieee.org/document/8998354" target="_blank" rel="noopener">(URL)</a></p>

Advisees


  • Graduate Advising Relationship

    Degree Research Title Advisee
    Doctor of Philosophy Deep Learning Algorithms for Image and Signal Processing Applications Le Hoang, Thanh
    Doctor of Philosophy Depth Perception from a Single Colour Image Thompson, Joshua
    Doctor of Philosophy Depth Estimation with Deep Learning for Assistive Navigation Phan, Steve
    Doctor of Philosophy Scene Perception and 3D Sound Synthesis for Assistive Navigation of Blind People Lei, Yunjia
    Master of Philosophy - EIS Deep Learning for Hyperspectral Image Processing Bui, Ly
uri icon