Scientists from the University of Cambridge (U.S.) and the National Institute of Technology and the Institute of Science (India) have published research revealing that drones (or unmanned aerial vehicles) can use artificial intelligence to detect violence in a crowd.
"The proposed method first uses the feature pyramid network (FPN) is used to detect the humans from the aerial image. Next, the proposed ScatterNet Hybrid Deep Learning (SHDL) network is used to estimate the pose for each detected human."
"Finally, the orientations between the limbs of the estimated pose are used by the support vector machine (SVM) to identify individuals engaged in violent activities,” according to the report.
Although the system experienced a decrease in the rate of accuracy as the number of violent individuals in test scenarios increased, and the system identified some innocent actions as violent ones, the research team expects improvement to the technology with both time and continued testing.
The study, called “Eye in the Sky: Real-Time DroneSurveillance System (DSS) for Violent Individuals Identification usingScatterNet Hybrid Deep Learning Network,” will be presented at the IEEE Computer Vision and Pattern Recognition (CVPR) Workshops 2018.