If It's Broken, Fix It

Just caught this article (via @abc7newsBayArea) that surveillance cameras on more than half of MUNI buses were broken or only "partially operational" as of September 2009.

According to documents that the ABC I-Team received, 22 percent of buses and light rail had no working cameras on board, while 30 percent were listed as only "partially operational."

Yes, MUNI is facing a $129 million deficit heading into the new fiscal year that began July 1, much to do with the many fare cheats costing it $19 million annually, but the buses must have working cameras in order to deal with the violence and fights that break out, like this one on the 20-Columbus. It's obvious just having an empty, inoperable box in buses is just not doing the trick these days.

Underground Trolley Cameras Coming to Beantown, SweeperCams In Nation's Capital

Some interesting municipal surveillance initiatives over on the East Coast caught my eye recently:

First off, saw a Boston Globe article that the MBTA will begin testing cameras on the underground trolleys as part of a pilot program funded by DHS.

This is an ongoing effort that has already seen success. Three hundred buses and most of the T-subway stations are already equipped with cameras, and transit police have used video in almost 500 investigations, more than 240 of which have resulted in charges. This new program only will enhance the system and add more high-resolution cameras to improve video quality. (These cameras are facial recognition software-friendly and may be used to track people as well).

The video will be streamed in real-time to the Transit Police's operation control center in downtown Boston. According to the article:

"Our hope is that the cameras will be able to be viewed in a police cruiser, so that an officer responding to a call will have real-time viewing of what is happening on the scene," MacMillan said.

While station footage will be stored for almost a month, surveillance video from buses will only be kept for 72 hours. Not sure it's an issue with storage capacity due to high video quality, but a three-day limit severely restricts the video from being used in ongoing investigations, many of which last long past that time frame. However, this is a great effort on the part of the MBTA to take a proactive approach to increase transit security and identify repeat offenders.

Also interesting, I caught an article about D.C.'s Sweepercam implementation, a ticketing camera system installed on the city’s street sweepers to fine cars parked in designated-cleaning areas. The cameras are equipped with license plate recognition software so, should a car be parked in a designated spot, the cameras will note the plate number and the system will send the owners a ticket in the mail.

The system has already had a few hiccups and angered some folks with malfunctioning equipment and/or human error. Many operators have forgotten to turn off the cameras in places not slated for cleaning and thus, photographed legally-parked cars. In an email, DPW spokesperson Nancee Lyons responded to the mishaps:

“The camera may have captured the wrong vehicle, a duplicate ticket may have been issued, the camera may have been triggered accidentally and a ticket may have been issued during a day and hours when there was no street sweeping..."

With possible plans to extend parking meter hours to raise an estimated $9 million in extra funds for the transit system, I'm surprised San Francisco has not picked up on this one yet. DC has already dispensed 22,000 tickets from Sweepercam thus far -- that's good chunk of change that more than covers the investment.

South Korean Study Delivers a Face Rec First (90%+ Accuracy Using Surveillance Video)

Those following the South Korean government’s most recent biometric initiative know it to be one of the most ambitious facial recognition testing and deployment projects ever conceived. The project, in its various phases, has been featured quite extensively on Korean television here and here.

Under the project, the Korean National Police (NPA) sought to deploy facial recognition technology against Seoul’s plentiful video surveillance cameras, both to generate alerts to the presence of targeted individuals, as well as provide a mechanism to quickly search city surveillance archives for persons identified after the fact.

Though the NPA has been quite public on its facial recognition project in general, details regarding the specific technologies and testing results have been closely guarded. However, today after much anticipation, the NPA has finally made its initial findings public. According to the NPA and SK Networks spokesmen, 3VR's facial recognition platform demonstrated the highest percentage of accuracy of any of the eight tested technologies in trials run by the NPA and its testing partner, South Korea's IT giant SK Networks.

Indeed the results, at around 90% accuracy, would seem far better than those achieved in any previous public video facial recognition study. After a grueling multi-year testing process, in 3VR SmartRecorders and SmartCams provided between 85 percent and 92 percent accuracy in recognizing and matching faces in a few crowded, highly-trafficked public train stations in Seoul. In each case, the images analyzed were of fast-moving groups of commuters entering or exiting various transit areas en masse.

Said Sung-Ho Kong of SK Networks:

“In 2008, we performed a live, uncontrolled test of 3VR's facial recognition technology in Seoul subway stations, where the solution was an impressive 85-92 percent accurate, depending on conditions. No other solution approached this level of accuracy, vastly improving our ability to track, find and thwart crime in subways and other highly populated areas, which had previously proven extremely difficult to monitor.”

To better appreciate just how impressive the NPA’s results are, we need to compare them to the best previous facial recognition study. In 2006-2007, a similar facial recognition-use case was evaluated by the German Federal Police. After months of testing in a German subway with lighting and traffic much more controlled than in South Korea, a mediocre 60 percent accuracy rating was achieved.

The improvements in accuracy afforded by 3VR are the result of a unique approach to video facial recognition. While most face rec vendors offer technologies optimized for the comparison of flat, normally lit, passport-style photos, only 3VR's software was built from the ground up to address many of the unique challenges presented by real-time surveillance video.

According to Tim Frederick, director of engineering at 3VR:

“This study demonstrates the breakthrough power of 3VR’s patented facial surveillance technology. Unlike other attempts at high-volume face surveillance, which re-purposed still-image face recognition algorithms, the South Korean study benefited from 3VR’s end-to-end video analysis system, specifically designed for this type of demanding video application.”

Expect more details from 3VR and the NPA shortly, but in the meantime, please check out SDN's Rhianna Daniels' feature story on the announcement, as well as a quick diagram of how the technology works and even some up-close and personal screen grabs of the UI.

UPDATE June 22, 2009:

Here is a translation of the South Korean National Police's Phase 1 testing results: