Does Deep Super-Resolution Enhance UAV Detection? – IEEE paper

ALADDIN partner, CERTH has produced a publication to the 16-th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS) conference with regards to the ALADDIN project. The title of the paper is “Does Deep Super-Resolution Enhance UAV Detection?” and it is published by IEEE, the issue release date is 2019-11-25 and the abstract is presented below. More information regarding this paper could be found here (https://ieeexplore.ieee.org/abstract/document/8909865/). For more public reports and publications follow this link.

Abstract: The popularity of Unmanned Aerial Vehicles (UAVs) is increasing year by year and reportedly their applications hold great shares in global technology market. Yet, since UAVs can be also used for illegal actions, this raises various security issues that needs to be encountered. Towards this end, UAV detection systems have emerged to detect and further anticipate inimical drones. A very significant factor is the maximum detection range in which the system’s senses can “see” an upcoming UAV. For those systems that employ optical cameras for detecting UAVs, the main issue is the accurate drone detection when it fades away into sky. This work proposes the incorporation of Super-Resolution (SR) techniques in the detection pipeline, to increase its recall capabilities. A deep SR model is utilized prior to the UAV detector to enlarge the image by a factor of 2. Both models are trained in an end-to-end manner to fully exploit the joint optimization effects. Extensive experiments demonstrate the validity of the proposed method, where potential gains in the detector’s recall performance can reach up to 32.4%.