UCF Researchers Perform World's First Automated Mass-Crowd Count (ucf.edu)
subh_arya writes: Automatic crowd counting has been an extremely challenging computer vision problem. However, researchers from UCF, seem to have found a reasonably accurate solution using sophisticated probabilistic models. Although there has been several previous efforts in this direction, this is the first time the technology has been put to use on a realistic scenario where around 550,000 protesters participated for Catalunyan Independence. A freely available technical paper published in IEEE Trans. on Pattern Analysis and Machine Intelligence, 2015 is available here.
We learned years ago that people from Florida don't know how to count.
Damn_registrars has no butt-hole. Damn_registrars has no use for a butt-hole.
"Food riot in progress. Approximately 1500 civilians. No weapons evident."
When there's no provable number involved, everybody uses the number that suits their own interests. How else can you explain estimates that vary by 3x?
Police? If the issue isn't police malfeasance, they like the higher number. If there was a riot, the large number supports their "need" for more police officers, weapons and expanded powers (greater leniency on the use of violence, more intelligence gathering, etc). If the protest was non-violent, they get to claim the credit for successfully managing it and keeping it peaceful.
Government? They usually like the lower number, as it allows them to claim the organizers or issues lack political support so they can keep doing whatever it is they want.
Protesters? They like the bigger number, it shows how much support they have.