Skip to main content

Dr Tardi Tjahjadi

Video surveillance for human activity recognition

A key objective of video surveillance is to detect abnormal behaviour patterns and recognise the normal ones. To achieve this objective, previously observed behaviour patterns need to be analyzed and profiled, upon which a criterion on what is normal/abnormal is drawn and applied to newly captured patterns for anomaly detection. Most of the approaches for recognizing and detecting activities are based on the premise that the activity has already occurred. Reasoning about the intentions of humans and inferring what is going to happen present interesting challenges. I am interested in supervising PhD research in human activities to predict an intentional activity that may pose a threat to a critical infrastructure (e.g., an intruder entering a restricted site of a building) or pose a danger to the human performing the activity (e.g., a person swaying unsteadily).

Gait analysis for human identification

Biometrics has emerged as a reliable means of identifying a human subject based on the subject's distinctive biological features. Behavioural biometrics examines human behaviour and the most promising example is gait that exploits a subject's distinctive way of walking to perform identification. Gait analysis has a wide range of applications in surveillance for security, forensics and biometric authentication. Silhouette-based gait recognition methods do not assume an explicit model of the human body, but analyse the spatio-temporal shape and motion characteristics of silhouettes. I am interested in supervising a PhD research in silhouette-based 3D gait analysis (for view invariance).

Other research topics

I am also interested in supervising PhD research in the following topics: enhancement of video sequences; 3-dimensional object reconstruction from images via shape from silhouettes (SfS) or via structure from motion (SfM); autonomous navigation in a multiscale framework; real-time hand tracking; digital sculpturing; and face verification.

Note: Should your application for admission be accepted you should be aware that this does not constitute an offer of financial support. Please refer to the scholarships & funding pages.