Skip to main content

Li, Wanqing Associate Professor

Associate Professor

  • Advanced Multimedia Research Laboratory
  • Faculty of Engineering and Information Sciences
  • School of Computing & Information Technology
  • Coordinator - ICT Research Institute

Research Overview


  • Research Interests:
    Multimodal based image/video semantic analysis for annotation and retrieval

    Object tracking and behavior analysis

    Multimodal biometrics and crypto-biometrics

    Multimedia security and forensics

    Future Research Interests:
    MUVIDA project employs multimodal video analysis to develop technology to correlate and fuse audio and visual information. In particular, the spoken dialogue is analyzed and correlated with associated text extracted from the video; the identity and number of speakers in the scenes is established by using speaker recognition and face tracking algorithms.

    HARR (Human Activity Representation and Recognition) project has developed robust algorithms for human detection, tracking and motion direction estimation and, is currently developing "motion units" and grammar based activity representation and recognition algorithms.

    AISS (Autonomous Intelligent Surveillance System) Research Program aims to develop an adaptive and reconfigurable security surveillance system capable of exploiting environmental information and knowledge base. The system provides continuous detection, tracking and recognition of all human activities within the scene to generate person-specific surveillance report. The program consists of several key enabling projects: multi-modal biometrics, human activity representation and recognition, semantic scene description and representation.

    MUMOBIO (Multi-modal Biometric) Program is developing a continuous human recognition system using gait, face, voice and fingerprint modalities. The system is integrated with the HARR project to enable person-specific surveillance. In addition, the project is addressing the security issues of traditional pattern recognition based biometric systems by developing schemes to bind effectively and efficiently multimodal biometrics with cryptographic keys to form crypto-biometrics systems.

    The Multimedia "Search n Retrieve" Research Program aims to develop methods and tools that can be used in a rapid application development (RAD) environment for multimedia browse, search, and retrieve systems. The systems will employ a multi-modal approach involving, voice, image and video features, text and human cognition.

    RIWD (Robust Image Watermarking Decoding) Project aims to develop a robust decoding method for commonly adopted image watermarking schemes such as Spread Spectrum (SS) and Quantization Index Modulation (QIM). The method  models and estimates the possible attacks that the watermarked images have suffered and incorporates prior knowledge in a maximum posterior probability (MAP) decoding framework.

Available as Research Supervisor

Selected Publications


Available as Research Supervisor

Advisees


  • Graduate Advising Relationship

    Degree Research Title Advisee
    Doctor of Philosophy (Integrated) Computer Visionen-Based Postural Assessment Ding, Zewei
    Doctor of Philosophy Self-mixing interferometric sensing and its applications Ruan, Yuxi
    Doctor of Philosophy Computer Vision and Machine Learning in Disaster Management and Monitoring Process Iqbal, Umair
    Doctor of Philosophy (Integrated) Human Activity Recognition Yatanwala, Yatanwala Withanamalage Thilini Merian
    Doctor of Philosophy Light Field Acquisition for Free-viewpoint Video. FU, Shichao

Teaching Overview


  • Dr Li was a Lecturer from 1987 to 1990 and Associate Professor from 1991 to 1992, both with the Department of Computer Science and Technology, Zhejiang University of China. From 1992 to 1993, he was a visiting Research Fellow with the Computer Science Department, Murdoch University, Australia.  From 1997 to 1998, he worked as an Information Technology Officer with the Bureau of Meteorology, Australia. He joined Motorola Australian Research Centre in 1998 as a Senior Research Engineer and later a Principal Research Engineer. Since 2004, he has been a Senior Lecturer with the School of Information Technology and Computer Science, University of Wollongong.

    Dr. Li is a co-founder of the Centre for Multimedia Signal Processing and Content Management at University of Wollongong. He has 17 years combined industrial and academic research experience in multimedia. He has initiated, led and contributed to a number of successful R&D projects funded by government and industry. He received Motorola CTO's Award in 2003 due to his significant contribution in the area of video analysis. Dr Li has filed four US patents.  He has authored and co-authored over 50 refereed papers in the field of multimedia signal processing. His current research interests are human motion analysis, multimodal biometric cryptosystems, automatic annotation and intelligent retrieval and adaptation of multimedia content and image/video watermarking. Dr. Li regularly serves  as a committee member and session chair in international conferences and a reviewer of IEEE Transactions.


Keywords


  • Machine Learning (Deep Learning) and 3D Computer Vision - Human activity understanding, human detection, gait recognition, 3D sensing and reconstruction from RGB-D data

    3D Multimedia Signal Processing and Understanding – scene analysis and event detection

    Free Viewpoint Video (FVV) – Acquisition, processing, understanding and compression

    Medical Image Processing and Understanding – Image reconstruction for low-dose X-ray and fast MR imaging, segmentation of medical images

Fax


  • +61 2 4221 4170

Research Overview


  • Research Interests:
    Multimodal based image/video semantic analysis for annotation and retrieval

    Object tracking and behavior analysis

    Multimodal biometrics and crypto-biometrics

    Multimedia security and forensics

    Future Research Interests:
    MUVIDA project employs multimodal video analysis to develop technology to correlate and fuse audio and visual information. In particular, the spoken dialogue is analyzed and correlated with associated text extracted from the video; the identity and number of speakers in the scenes is established by using speaker recognition and face tracking algorithms.

    HARR (Human Activity Representation and Recognition) project has developed robust algorithms for human detection, tracking and motion direction estimation and, is currently developing "motion units" and grammar based activity representation and recognition algorithms.

    AISS (Autonomous Intelligent Surveillance System) Research Program aims to develop an adaptive and reconfigurable security surveillance system capable of exploiting environmental information and knowledge base. The system provides continuous detection, tracking and recognition of all human activities within the scene to generate person-specific surveillance report. The program consists of several key enabling projects: multi-modal biometrics, human activity representation and recognition, semantic scene description and representation.

    MUMOBIO (Multi-modal Biometric) Program is developing a continuous human recognition system using gait, face, voice and fingerprint modalities. The system is integrated with the HARR project to enable person-specific surveillance. In addition, the project is addressing the security issues of traditional pattern recognition based biometric systems by developing schemes to bind effectively and efficiently multimodal biometrics with cryptographic keys to form crypto-biometrics systems.

    The Multimedia "Search n Retrieve" Research Program aims to develop methods and tools that can be used in a rapid application development (RAD) environment for multimedia browse, search, and retrieve systems. The systems will employ a multi-modal approach involving, voice, image and video features, text and human cognition.

    RIWD (Robust Image Watermarking Decoding) Project aims to develop a robust decoding method for commonly adopted image watermarking schemes such as Spread Spectrum (SS) and Quantization Index Modulation (QIM). The method  models and estimates the possible attacks that the watermarked images have suffered and incorporates prior knowledge in a maximum posterior probability (MAP) decoding framework.

Selected Publications


Advisees


  • Graduate Advising Relationship

    Degree Research Title Advisee
    Doctor of Philosophy (Integrated) Computer Visionen-Based Postural Assessment Ding, Zewei
    Doctor of Philosophy Self-mixing interferometric sensing and its applications Ruan, Yuxi
    Doctor of Philosophy Computer Vision and Machine Learning in Disaster Management and Monitoring Process Iqbal, Umair
    Doctor of Philosophy (Integrated) Human Activity Recognition Yatanwala, Yatanwala Withanamalage Thilini Merian
    Doctor of Philosophy Light Field Acquisition for Free-viewpoint Video. FU, Shichao

Teaching Overview


  • Dr Li was a Lecturer from 1987 to 1990 and Associate Professor from 1991 to 1992, both with the Department of Computer Science and Technology, Zhejiang University of China. From 1992 to 1993, he was a visiting Research Fellow with the Computer Science Department, Murdoch University, Australia.  From 1997 to 1998, he worked as an Information Technology Officer with the Bureau of Meteorology, Australia. He joined Motorola Australian Research Centre in 1998 as a Senior Research Engineer and later a Principal Research Engineer. Since 2004, he has been a Senior Lecturer with the School of Information Technology and Computer Science, University of Wollongong.

    Dr. Li is a co-founder of the Centre for Multimedia Signal Processing and Content Management at University of Wollongong. He has 17 years combined industrial and academic research experience in multimedia. He has initiated, led and contributed to a number of successful R&D projects funded by government and industry. He received Motorola CTO's Award in 2003 due to his significant contribution in the area of video analysis. Dr Li has filed four US patents.  He has authored and co-authored over 50 refereed papers in the field of multimedia signal processing. His current research interests are human motion analysis, multimodal biometric cryptosystems, automatic annotation and intelligent retrieval and adaptation of multimedia content and image/video watermarking. Dr. Li regularly serves  as a committee member and session chair in international conferences and a reviewer of IEEE Transactions.


Keywords


  • Machine Learning (Deep Learning) and 3D Computer Vision - Human activity understanding, human detection, gait recognition, 3D sensing and reconstruction from RGB-D data

    3D Multimedia Signal Processing and Understanding – scene analysis and event detection

    Free Viewpoint Video (FVV) – Acquisition, processing, understanding and compression

    Medical Image Processing and Understanding – Image reconstruction for low-dose X-ray and fast MR imaging, segmentation of medical images

Fax


  • +61 2 4221 4170
uri icon