Various research video demos with links to available open access manuscripts, open source software and datasets.
ENHANCED THREAT DETECTION
Autonomous Baggage Security Systems
Issue
Potential threats concealed within the baggage has become one of the prime security concern all over the world. Manual recognition of these threats is time-consuming and subject to human errors caused by fatigue due to intensive work schedules or less experienced operators.
Approach:
In this research, we aim to develop intelligent frameworks which can autonomously detect and recognize such threats, especially under extreme occlusion, clutter, and concealment.
Application:
Demonstrable real-time BCI teleoperation of a humanoid robot, based on the use of naturally occurring in-scene stimuli.
Successful use of a novel variable SSVEP BCI (varying: pixel pattern + region size,/shape).
CNN based real-time decoding of dry-EEG bio-signals for interactive BCI applications.
DEMO
BRAIN-COMPUTER INTERFACE FOR REAL-TIME HUMANOID ROBOT NAVIGATION
Issue
Variable position and size SSVEP stimuli for real-time teleoperation BCI application.
Approach:
Variable position and size SSVEP stimuli, based on real-time object detection pixel regions, within the live video stream from a teleoperated humanoid robot traversing a natural environment. CNN architecture for scene object detection and dry-EEG bio-signal decoding.
DEMO
REAL-TIME MONOCULAR DEPTH ESTIMATION
Issue
Synthetic images captured from a graphically-rendered virtual environment primarily designed for gaming can be employed to train a monocular depth estimation model. However, this will not generalize well to real-world images as the supervised model easily overfits to local features present within the training domain.
Approach:
1) Train a primary model to estimate monocular depth based on synthetic images. 2) use a secondary model to transform real-world images to the synthetic style before their depth is estimated.
Application:
At run-time only requires two forward passes required during inference – once through the style transfer network and once through the depth estimation model.
DEMO
REAL-TIME VEHICLE DETECTION AND TRACKING IN THERMAL IMAGERY
Issue
Siverra lectus mauris ultrices eros in. Eget egestas purus viverra accumsan in nisl nulla nisi scelerisque euvestibulum sed risus ultricies. Fermentum posuere urna nec tincidunt. Quis imperdiet massa tincidunt nunc pulvinar sapien et ligula ullamcorper.
Approach
We investigate the accuracy of a number of real-time object classification approaches for this task within the wider context of an existing initial object detection and tracking frame-work.
Application
Based on photogrammetric estimation of target position, we then illustrate the use of regular Kalman filter based tracking operating on actual 3D vehicle trajectories. Results are presented using a conventional thermal-band infra-red (IR) sensor arrangement where targets are tracked over a range of evaluation scenarios.
Real-time Classification of Vehicle Types within Infra-red Imagery (M.E. Kundegorski, S. Akcay, G. Payen de La Garanderie, T.P. Breckon), In Proc. SPIE Optics and Photonics for Counterterrorism, Crime Fighting and Defence, SPIE, Volume 9995, pp. 1-16, 2016.