For years , regime agencies have furrow technologies that would make it easier to insure that vehicles in carpool lanes are actually carrying multiple passenger . Perhaps the only reason these organisation have n’t garner much attending is that they have n’t been specially in effect or exact , as UC Berkeley researcher noted ina 2011 report . Now , an agency in San Diego , Calif. believes it may have found the answer : the Automated Vehicle Passenger Detection organization developed by Xerox .
TheSan Diego Association of Governments(SANDAG ) , a government umbrella chemical group that develops transportation and public safe initiatives across the San Diego County region , estimates that 15 % of driver in High Occupancy Vehicle ( HOV ) lanes are n’t theorise to be there . After coming up short with earlier data-based projects , the office is now testing a brand unexampled technology to snap down on carpool - lane scofflaw on the I-15 freeway .
Documentsobtained byCBS 8 newsman David Gotfredsonshow that Xerox ’s system apply two camera to capture the front and side purview of a car ’s interior . Then “ video analytics ” and “ geometric algorithms ” are used to detect whether the seats are occupied .
When the detection system ’s computer determines a machine driver is improperly traveling in the carpool lane , the cameras instantly broadcast photos of the auto ’s interior and its license denture to the California Highway Patrol .
In short : the technology is attend at your trope , the image of the people you ’re with , your location , and your license plate . ( SANDAG told CBS the systems will not be store licence plateful data during the tryout phase and the system will , at least for now , automatically redact image of driver and passengers . Xerox ’s software program , however , allows police the option of using a fallible form of editing that can be annul on request . )
Xerox ’s Automated Vehicle Passenger Detection system can be mounted in permanent locations , such as freeway gantries , or attached to roving trailers that “ can be move around , to keep potential violators honest . “
Xerox claims that the systems have a 95 - 99 % accuracy rate , even with vehicles traveling as rapidly as 100 mph . That map a significant leap in capability compared to the 14 - 20 % truth recorded by similar technology tested by SANDAG four year earlier .
So far , Xerox ’s technology has only had one other visitation run : a 2013 test on the Mackay Bridge in Halifax , Nova Scotia , where the detective work system captured 250,000 images of drivers in just under two weeks . Xerox claims the technology successfully determined front can passengers 98.9 % of the time and rearward place passenger 96.2 % of the time .
That winner rate may seem impressive , but it still means that , in aggregate , thousands of citizenry could have been affected by machine misplay . Automated Vehicle Passenger Detection system also raises the usual questions and business concern about concealment and mass surveillance , peculiarly without principle yet in position defining the limits of how this engineering science collects data and how that information will be lay in , accessed , and destroyed .
If this run is successful , it may only be a matter of time before Xerox begins marketing this fresh engineering to other jurisdictions . As Xerox told its investors in November , its Automated Vehicle Passenger Detection arrangement is “ aim at revolutionizing the bm of masses and goods worldwide . ”
Whether you ’re a local journalist or citizen watchdog , add Automated Vehicle Occupancy / Passenger Detection to your lexicon . In the coming months and years , look for it in procurement documents and citizens committee agenda . Ask for related documents in your routine public records request . As with all street - level surveillance technology , citizen have more power to determine policy when they key the tech in its infancy , rather than fighting to dial back its use after it has been integrated into daily constabulary surgical procedure .
This postfirst come along on Electronic Frontier Foundationand is republished here under Creative Commons licence . Image byRichunder Creative Common license .
CarsPrivacyroads
Daily Newsletter
Get the good technical school , science , and polish intelligence in your inbox daily .
tidings from the time to come , delivered to your present .
You May Also Like
