When the police used ANPR data to study Khan and Uddin’s movements, they uncovered another surprise: the duo hadn’t travelled alone. Officers dug into the national database using a technique called “convoy analysis.” First, every record of Khan and Uddin’s car trip was recalled from the system. Then another set of plate numbers was generated: those of every car that had passed by those same cameras within a few seconds or minutes of the pair. By comparing this set with those at the next camera site, and the next, and the next, the police identified a second car that had travelled in convoy with them from Birmingham to Dewsbury. Within 48 hours, police arrested not only Khan and Uddin, but four further members of the group from the second car. All six men later plead guilty to preparing an act of terrorism, and were sentenced to a total of 111 years in prison.
Goodbye, anonymity: Latest surveillance tech can search up to 36 million faces per second
Welcome to the next generation in surveillance technology. A Japanese company, Hitachi Kokusai Electric, has unveiled a novel surveillance camera that is able to capture a face and search up to 36 million faces in one second for a similar match in its database.
While the same task would typically require manually sifting through hours upon hours of recordings, the company´s new technology searches algorithmically for a facial match. It enables any organization, from a retail outlet to the government, to monitor and identify pedestrians or customers from a database of faces.
Hitachi’s software is able to recognize a face with up to 30 degrees of deviation turned vertically and horizontally away from the camera, and requires faces to fill at least 40 pixels by 40 pixels for accurate recognition. Any image, whether captured on a mobile phone, handheld camera, or a video still, can be uploaded and searched against its database for matches.
“This high speed is achieved by detecting faces through image recognition when the footage from the camera is recorded, and also by grouping similar faces,” Seiichi Hirai, Hitachi Kokusai Electric researcher told DigInfo TV.
Photo Credit: (fastcompany.com)
Early mobile app for tracking surveillance cameras in NYC.
In fact, while much eﬀort has been expended on analysing video surveillance as a tool of social sorting, there is a current lack of research regarding the spatial logics and characteristics of CCTV. Before targeting speciﬁc social groups or individuals, the installation points of the cameras, their technical features (zoom, angle of vision, etc.), their direction while unattended and the active manipulations of their position by camera operators are ﬁrst and foremost related to speciﬁc portions of space. Individuals or social groups are monitored once they enter the cameras’ gaze. Social behaviour is of interest only within the cameras’ premises. As a limited window to the city, video surveillance must thus above all be considered as ‘surveillance of space’.
This video, a trailer for Faceless, a 2007 film by artist Manu Luksch, comes courtesy of a recent conversation with Darius Cuplinskas of OSF. It counterpoints Respectful Cameras, the Ken Goldberg one I posted a couple of weeks ago quite nicely, I think. Here’s a PDF and more details about the concept behind and making of the film, here’s the manifesto for CCTV filmmakers, and here’s a BBC report about it.
It feels somewhat (Egoyan + Marker) x von Trier… But that is, I admit, a bit reductive. I really, really want to see the whole thing…