CAMBRIDGE, England (CelebrityAccess) A drone surveillance system is in the works to detect if violence is occurring at an event but, to be clear, it’s still a long way off.
The idea is great: a drone can detect at an event if someone is becoming violent toward another person. The technology was first considered during the Boston Marathon bombing, according to IEEE Spectrum, and then became accelerated after the bombing near the Manchester Arena after the Ariana Grande concert. The technology would be able to recognize the actions of choking, punching, kicking, stabbing and shooting. However, it’s still in the pupae stage.
“This time we were able to do a relatively better job, because the software was able to run in realtime and does a relatively good job of detecting violent individuals,” Amarjot Singh, a Ph.D. student in deep learning at the University of Cambridge, told IEEE Spectrum.
The distance between theory and reality can be marked by one of the many convoluted paragraphs that use terms like “neural network layers” and “supervised learning” in the report:
“The research team also needed to sit down and manually mark 18 coordinates on each person’s body in the video frames. That would have quickly become a labor-intensive and exhausting process for 10,000 or 20,000 images normally needed to train deep learning algorithms. The researchers wanted to cut down the amount of necessary training data to just 2,000 annotated images that included about 5,000 individuals performing violent actions.”
There is a lot of “deep learning” to still be considered, but Cambridge University is is apparently deep into making this a reality.
