TY - JOUR
T1 - A novel infrared video surveillance system using deep learning based techniques
AU - Zhang, Huaizhong
AU - Luo, Chunbo
AU - Wang, Qi
AU - Kitchin, Matthew
AU - Parmley, Andrew
AU - Monge-Alvarez, Jesus
AU - Casaseca-de-la-Higuera, Pablo
PY - 2018/10/1
Y1 - 2018/10/1
N2 - 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.
AB - 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.
KW - ATD/R
KW - CNN
KW - Object detection
KW - Super-resolution
KW - Video surveillance
UR - http://www.scopus.com/inward/record.url?scp=85052735138&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85052735138&partnerID=8YFLogxK
UR - http://www.mendeley.com/catalogue/novel-infrared-video-surveillance-system-using-deep-learning-based-techniques
U2 - 10.1007/s11042-018-5883-y
DO - 10.1007/s11042-018-5883-y
M3 - Article (journal)
SN - 1380-7501
VL - 77
SP - 26657
EP - 26676
JO - Multimedia Tools and Applications
JF - Multimedia Tools and Applications
ER -