Dr. Sajid Javed
Dr. sajid javed Assistant Professor Electrical Engineering And Computer Science

Contact Information
sajid.javed@ku.ac.ae (02) 312 4353


Dr. Sajid is an assistant professor of computer vision at Khalifa University of Science and Technology, UAE. He is affiliated with Khalifa University Centre of Autonomous Robotics Systems (KUCARS), and the University of Warwick, United Kingdom. Dr. Sajid received his Ph.D. degree in Computer Science and Engineering from the Kyungpook National University, Republic of Korea, and his B.Sc. (Hons) degree in Computer Science from the University of Hertfordshire, United Kingdom. Previously, he has worked as a research fellow at the University of Warwick, University Hospitals Coventry and Warwickshire, United Kingdom, and KUCARS, UAE.

He leads the computer vision group in KUCARS and has extensive experience working on computer vision, machine learning, and artificial intelligence research projects. He has published many high-quality and high-impact factor papers in leading computer vision journals and conferences (e.g., Transactions on Pattern Analysis and Machine Intelligence, Transactions on Image Processing, Transactions on Cybernetics, Medical Image Analysis). His current research interests span the field of computer vision and computational pathology. This includes visual tracking from video sequences, multi-object tracking, object detection, background-foreground modeling, background subtraction, video object segmentation, histology image classification, tissue phenotyping, nucleus detection, and nucleus classification from routine Hematoxylin and Eosin Whole Slide Images. He is also a member of IEEE and ACM.

  • PhD. in Computer Science and Engineering, Republic of Korea
  • B.Sc. (Hons) in Computer Science, U.K.

  • Advanced Computer Vision Paradigms (ECCE630)
  • Artificial Intelligence (COSC604)
  • Deep Learning System Design (ECCE635)
  • Introduction to Human Computer Interfaces (HSEG601)
  • Operating Systems (ECCE354)

Affiliated Research Institutes/Centers
  • KU Center for Autonomous Robotic Systems

Research Interests
  • Computer Vision, Machine Learning, Artificial Interest, Medical Imaging, Computational Pathology, Cancer Imaging
  • Visual Tracking, Object Detection, Video Segmentation, Underwater Video Tracking, Underwater Image Analysis, Cancer Diagnosis, Tissue Classification, Histology Image Analysis

Research Projects

Underwater Image/Video Analysis

More than 70% of our planet is covered by oceans and about half of the earth's surface lies beyond 1000m depth. Deeper waters are inaccessible to divers to explore more about underwater lives that are deprived of natural lighting conditions. Artificial intelligence can assist ocean scientists in discovering interconnected activities related to underwater creatures or species. However, the deployment of current artificial intelligence paradigms still faces difficulty in understanding low-visibility environment scenes. This difficulty manifests particularly in underwater monitoring, a task of capital importance in many underwater technological sectors. This project addresses the main challenges faced by computer vision algorithms for underwater image analysis applications. The lack of publicly available underwater data is the major challenge to train very deep neural networks for different tasks such as object tracking, generic object detection, and segmentation. We are developing a large-scale underwater video analysis dataset for addressing fundamental computer vision applications. In this project, 01 Postdoc, 01 Ph.D. student, and 02 Ms.c. students are working on developing novel computer vision solutions.

Detecting Cancerous Footprintps in Histopathological Landscape

According to the WGO reports, in 2020, there are 18.1 million new cases of cancer, where 2.1 million of them are related to breast. Furthermore, there are 9.6 million deaths caused by malignancy, while 6.6% of them are breast cancer patients. More importantly, 24.2% of new cancer cases and 15% of deaths caused by cancer among women are breast cancer patients. Although the cause of this disease is not clear, early recognition and diagnosis contribute to keeping ladies from death. The earlier the diagnosis is made, the more likely it is to treat the patients effectively, saving lives and cutting down costs in medical care. Nevertheless, the clinical image examination is labor-intensive and time-consuming for experts. Fortunately, with the improvement of machine learning and clinical imaging innovation, computer-assisted diagnosis has given impressive help to pathologists. In light of this, the computer-assisted diagnosis of breast malignant growth using histology images has received extensive attention in the realm of computer vision and clinical image handling. This project addresses the main challenges faced by computer vision/machine learning methods in computational or digital pathology. We are developing novel AI-driven computation vision solutions for pathologists to diagnose cancer at an early stage and prepare the treatment plan. In this project, 01 Ph.D. student and 01 Ms.c. students are working on developing novel machine learning solutions.

Visual Object Tracking in the Wild

Visual Object Tracking (VOT) is one of the fundamental open problems in computer vision. The task is to estimate the trajectory and state of a target in an image sequence. VOT has a wide range of applications, including autonomous driving, robotics, intelligent video surveillance, sports analytics, and medical imaging, where it typically plays an important role within large intelligent systems. Given the initial state of any arbitrary target object, the main challenge in VOT is to learn an appearance model to be used when searching for the target object in subsequent frames. In recent years, VOT has received considerable attention, many thanks to the introduction of a variety of tracking benchmarks such as TrackingNet, VOT2018, and GOT-10K. Despite the recent progress, VOT is still an open research problem and is perhaps more active than ever. In this project, we are developing novel trackers to address the core tracking problems including target scale variation and lighting conditions etc.  

Muhammad Bin Zayed International Robotics Challenge-2023

MBZIRC-2023 is the flagship robotics competition hosted by ASPIRE. The competition aims to be one of the world's largest and most prestigious international robotics competitions. Held every two years in Abu Dhabi, UAE, as a real-world challenge for universities, research centers, companies, and individual innovators from all over the world. This competition inspires the development of solutions in autonomous robotic aerial and surface vehicle technologies. At the forefront of exploration and experimentation, MBZIRC-2023 set out to find novel technological successes that are resilient in an ever-changing market, reinforcing the UAE's role as an emerging hub for advanced technological innovations.  I

In this project, we are developing novel computer vision and robotics solutions for UAVs and USVs autonomy. MBZIRC-2023 grand challenge is a maritime domain challenge and winners will get an award of $3,250,000 USD. We are happy to see that Khalifa University is the only university that obtained a significant position among the top 10 teams around the world.

Research Staff and Graduate Students:

Dr. Fayaz Ali Postdoctoral Research Fellow
Dr. Farah Deeba Memon Postdoctoral Research Fellow
Basit Alawode Ph.D. candidate
Mehnaz Umar M.Sc. candidate
Yuhang Guo M.Sc. candidate
Additional Info

Dr. Sajid is currently working on three different projects including Artificial Intelligence for Oceans Surveillance, Detecting Cancerous footprints from the histopathological landscape, and the flagship competition/project Muhammad Bin Zayed International Robotics Challenge-2023. Dr. Javed is supervising is also supervising several PhD., Ms.c., and Postdocs candidates in those projects. Dr. Javed is also the area chair of the Asian Conference on Computer Vision (ACCV-2022) and the Internation Conference on Robotics and Automation (ICRA) 2023.


I am actively looking for a research associate/research engineer and postdocs to join projects related to computer vision and machine learning problems. Interested applicants with a strong track record of publications in computer vision venues are encouraged to contact me.