A novel infrared video surveillance system using deep learning based techniques
Multimedia Tools and Applications
Springer Verlag (Germany)
© The Author(s) 2018. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
This paper presents a new, practical infrared video based surveillance system, consisting of a resolution-enhanced, automatic target detection/recognition (ATD/R) system that is widely applicable in civilian and military applications. To deal with the issue of small numbers of pixel on target in the developed ATD/R system, as are encountered in long range imagery, a super-resolution method is employed to increase target signature resolution and optimise the baseline quality of inputs for object recognition. To tackle the challenge of detecting extremely low-resolution targets, we train a sophisticated and powerful convolutional neural network (CNN) based faster-RCNN using long wave infrared imagery datasets that were prepared and marked in-house. The system was tested under different weather conditions, using two datasets featuring target types comprising pedestrians and 6 different types of ground vehicles. The developed ATD/R system can detect extremely low-resolution targets with superior performance by effectively addressing the low small number of pixels on target, encountered in long range applications. A comparison with traditional methods confirms this superiority both qualitatively and quantitatively
This work was funded by Thales UK, the Centre of Excellence for Sensor and Imaging System (CENSIS), and the Scottish Funding Council under the project “AALART. Thales-Challenge Low-pixel Automatic Target Detection and Recognition (ATD/ATR)”, ref. CAF-0036. Thanks are also given to the Digital Health and Care Institute (DHI, project Smartcough-MacMasters), which partially supported Mr. Monge-Alvarez’s contribution, and to the Royal Society of Edinburgh and National Science Foundation of China for the funding associated to the project “Flood Detection and Monitoring using Hyperspectral Remote Sensing from Unmanned Aerial Vehicles”, which partially covered Dr. Casaseca-de-la-Higuera’s, Dr. Luo’s, and Prof. Wang’s contribution. Dr. Casaseca-de-la-Higuera would also like to acknowledge the Royal Society of Edinburgh for the funding associated to project “HIVE”.
This is the author accepted manuscript. The final version is available from Springer via the DOI in this record.
Published online 11 April 2018.