Tech for Cops: a Round Up
I’m going to kick off with a startup outfit called Broadcastr.
Broadcastr allows you, or anyone else for that matter, to record and upload audio clips and have them organised by geographic location. What this means is that people can listen to an audio clip that is tagged to a specific location. They can also choose to listen to a specific category of story. The highest rated stories are played first and people can share stories they like with their social networks or follow the person who submitted it.
For me this potentially provides yet another great opportunity for policing to move into an additional engagement channel. I have blogged before about how forces, and neighbourhood teams in particular, could take advantage of geo location services such as Gowalla and Foursquare to allow people to ‘check in’ with their neighbourhood policing teams and ‘earn’ badges and rewards by greater levels of engagement (Communication to Cooperation to Collaboration). Broadcastr opens an additional channel. Neighbourhood policing teams could for instance, record ‘about your neighbourhood team’ audio clips, or ‘team updates’ or ‘you said, we did’ updates, or crime appeals or or or! Public order commanders could have safety messages uploaded that were appropriate to the event and location and change them easily as the event progressed. Roads policing might use it to publicise an enforcement campaign in a specific area.
The site is in beta right now (and a bit on the slow side), but you can already listen to people talking about holiday visits to various parts of the UK.
Next up an interesting article that’s quite timely given the possible scale of protest in the near future, anti-surveillance camouflage, CV Dazzle (or how to hide from facial recognition software).
At the moment CV Dazzle is a New York University thesis project, but the website describes the concept as ‘camouflage from computer vision (CV)’
The site goes on ‘It is a form of expressive interference that combines makeup and hair styling (or other modifications) with face-detection thwarting designs. The name is derived from a type of camouflage used during WWI, called Dazzle, which was used to break apart the image of warships, making it hard to discern their directionality, size, and orientation. Likewise, the goal of CV Dazzle™ is to break apart the understanding of a face, or object, and make it undetectable to computer vision algorithms, in particular face detection.
And because face detection is the first step in automated facial recognition, CV Dazzle™ can be used in any environment where automated face recognition systems are in use, such as FaceBook, Google’s Picasa, or Flickr’
It may only be a thesis project at the moment, but next time you’re working a public order event and you see people wearing highly stylised make up designs, it just might be a Dazzle disguise.
Staying on the unmasking disguises theme, Fast Company magazine reports that ‘Researchers at Concordia University have discovered a way to mathematically uncover the unique (and often sub-conscious) writing style, or “write print,” of each individual. The most immediate application will help law enforcement identify the author of anonymous emails from a line of suspects. As of now, the program is roughly 85% accurate and confined to email sniffing, but it’s conceivable that the technology could eventually unearth the identities of spammers, trolls, or even terrorists.
The proving ground for the team’s sleuth algorithm was 200,000 real-life emails from 150 Enron employees. From a small sample of 10 subjects and 100 emails, the technique correctly identified between 80 to 90% of subjects. Thus, it’s not accurate enough for a court of law (because 20% of subjects would be falsely accused), but it is enormously beneficial to resource-strapped detectives’.
Just to add to the detectives joy, it was reported last week that a team led by an Indian scientist has developed new software that can, allegedly, automatically match hand-drawn facial sketches to mug shots stored in police databases.
The research is published in the journal IEEE Transactions on Pattern Analysis and Machine Intelligence. Good luck getting hold of that.
And finally, when they say that ‘a little bird told me’ they may just be telling the truth. Researchers have developed an unmanned aerial drone in the shape and form of a hummingbird.
With a 6.5-inch wing span, the remote-controlled bird weighs less than a AA battery and can fly at speeds of up to 11 mph, propelled only by the flapping of its two wings. A tiny video camera sits in its belly.
The bird can climb and descend vertically, fly sideways, forward and backward. It can rotate clockwise and counterclockwise. Most of all it can hover and perch on a window ledge while it gathers intelligence,
Just to really scare you, the researchers are apparently working on new drones that look like insects and the helicopter-like maple leaf seed.
Finally, don’t forget that only blog items are emailed to you. Check out the ‘interesting things’ category on the www.openeyecommunications.com web site for snippets that don’t make it to the blog email and the ‘agency reports’ section for the latest reports and publications from across the various agencies and government ministries.
This article was previously published on the OPen Eye Communications Blog.