PhD student Rachel Abbott wins prestigious SPIE best paper award

PhD student Rachel Abbott from Queen’s University Belfast associated with the UDRC project and working as an industrial CASE student with Thales UK has recently won the best student paper award at the SPIE Security and Defence conference held in Strasbourg, France where a panel of experts evaluated her paper for quality, content and novelty.

The paper was entitled “Multi-modal object detection using unsupervised transfer learning and adaptation techniques” and it presented a method for multi-modal object detection using unsupervised transfer learning and adaptation techniques. The novelty of this work includes; the use of the IR imagery, modality adaption from RGB to IR for object detection and the ability to use real-life imagery in uncontrolled environments. The practical impact of this work to the defence and security community is an increase in performance and the saving of time and money in data collection and annotation. The abstract and paper can be viewed here.

Extract from the paper, Figure 1. Detections in long wavelength IR imagery after training faster RCNN with RGB data with (left image) and without (right image) our extra mean squared error loss term.
Extract from the paper, Figure 1. Detections in long wavelength IR imagery after training faster RCNN with RGB data with (left image) and without (right image) our extra mean squared error loss term.