Top of page

Student/Staff Portal
Global Site Navigation

School of Science

Local Section Navigation
You are here: Main Content
  • Malik Muhammad Asim

    Malik Muhammad Asim

Related Contents

  • See Also
  • ORCiD profile
    https://orcid.org/0009-0005-3980-9370
  • ORCiD profile
  • LinkedIn profile
    https://www.linkedin.com/in/malik-muhammad-asim-a441471b1/
  • LinkedIn profile

Malik Muhammad Asim

Overview of thesis

Maritime activities have gained significant attention due to their growing contribution to global socio-economic growth. The expanding volume and complexity of maritime operations necessitate advanced technology for effective monitoring and management. Remote cameras, deployed across the extensive maritime landscape, provide continuous coverage but generate vast amounts of video data that require labour-intensive manual analysis. There is a growing need for automatic analysis of maritime activities for efficient monitoring and management while overcoming the limitations of manual video data analysis. Given the critical role of maritime vessels in maritime activities, recent research has concentrated on developing techniques for their detection, classification, and tracking. These tasks are challenging due to the dynamic nature of maritime traffic and environmental factors such as variable light, glare, waves, high illumination, occlusion, low resolution, and extreme weather conditions.

The advent of deep learning has led to substantial progress in video surveillance systems for automatically detecting larger vessels like cargo ships, ferries, military ships, and cruise ships. However, computer vision-based solutions for smaller vessels are still underdeveloped. State-of-the-art object detection algorithms often perform poorly in this context due to insufficient data. Additionally, accurately extracting features of smaller vessels is challenging due to their size and the low signal-to-noise ratio caused by environmental artifacts.

This research addresses these challenges by developing a computer vision-based techniques that enhances spatio-temporal features for the successful detection and classification of vessels in dynamic maritime scenarios. It also aims at developing an algorithm for multi-vessel tracking to enable automatic traffic analysis in remote camera footage.

Qualifications

  • 2009: Master of Science in Computer Engineering, University of Engineering and Technology, Taxila.
  • 2005: Bachelor of Science in Computer Engineering, University of Engineering and Technology, Taxila.

Research

Research Interests

  • Computer Vision
  • Object detection and classification
  • Artificial Intelligence / Machine Learning

Past Research employment history

  • 2021 – 2023: Research Fellow – SWARM Robotics Lab

Past Teaching

  • 2011: Assistant Professor, University of Engineering and Technology, Taxila
  • 2005 – 2011: Lecturer, University of Engineering and Technology, Taxila

Scholarships and Awards

  • 2024: Department Of Primary Industries & Regional Development Scholarship

Supervisors

  • Dr Syed Zulqarnain Gilani, Edith Cowan University
  • Dr Johnny Lo, Edith Cowan University
  • Dr Claire Smallwood, Department of Primary Industries & Regional Development
  • Professor Dr Mohamed Sedky, Staffordshire University

Contact

Malik Muhammad Asim
PhD Student
School of Science
Skip to top of page