Smart Cameras Blog

I have been very busy (and will probably continued to be), so the blog won’t be updated as often. But I will try to keep up on all the major stories related to smart cameras and the Chicago surveillance system.

CBS News ran a story that provides a basic overview of the Chicago camera network.

The CPD is using predictive profiling as a new technique, from the Sun-Times and Government Technology:

The Chicago Police Department is working with the Illinois Institute of Technology and the Rand Corp. on an innovative project that will help pinpoint hot spots of criminal activity. The process — called predictive analytics — is to analyze every violent incident and gang interaction with police to extrapolate and identify future problems. The numbers will be analyzed by experts at ITT. . . . Weis explained how the information pinpoints the time of day and location of violent crimes. In the past, gang data were compiled on a yearly basis, Weis said. Now any police interaction with a gang member will be fed into the system for a “real time, ongoing” account of where gangs operate.

For a different angle, the folks at Second City Cop have also weighed in on this technique.

rshah Applications, Chicago

[From Surveillance with privacy in mind - Security Systems News]

To make surveillance more palatable, Brookline Massachusetts has installed Situcam cameras with a “physical lens cover that opens when the system is in use and closes in an obvious way when the cameras are not operational.” It is a very interesting idea, especially to convince people the cameras will not be used outside of defined times. In this case, the camera policy “mandates that the cameras only be on between 10 p.m. and 6 a.m., or during an emergency situation.”

Here is some detail on the covers:

“The covers are reassuring,” DeWitt said. “You can see the cameras are not on, and that alleviates concerns that the cameras could be remotely controlled and that the operator might manipulate them into residents’ windows or something. So having the covers makes it abundantly clear that they can’t be used for other than safety purposes.”

Are the lens covers as much for public relations as anything else? “They’re redundant,” he admitted, as the software alone can control when the cameras are on or off and who has access, “but they’re crystal clear. The teachers or town workers know there’s no chance they’re being monitored.

The lens covers and software work with many camera types (it was a Bosch system here in Brookline), and while SituCon did the integration here as one of its first big customers, Cirker said the company is looking for dealers and partners to help make the technology more widely available and known.

I am a fan of this idea and want to point out it came out of citizen involvement in polices for the use of the cameras:

How has Brookline come so far in its willingness to accept public surveillance? A lot of hard work by a citizen oversight committee that developed policies for the use of the surveillance system that made sense for the community, with a helping hand from the Constitution Project and technology provided by SituCon.

rshah Applications, Other Cities

[From YouTube - HP computers are racist ]

A video demonstration showing how HP’s photo tracking software doesn’t work with an African American. The video is pretty funny and a nice example of how technology is far from neutral (but instead can treat particular groups of people differently). Another similar example was how a voice recognition technology, developed in Massachusetts, wouldn’t work for people with a southern accent.

Here is the part of the response from HP:

We are working with our partners to learn more. The technology we use is built on standard algorithms that measure the difference in intensity of contrast between the eyes and the upper cheek and nose. We believe that the camera might have difficulty “seeing” contrast in conditions where there is insufficient foreground lighting

rshah Applications, Policy

[From Why Baggage-Left-Behind has Been Such a Failure « Spot On Security]

A great analysis of a smart camera technology by Doug Marman. Lets start with this teaser:

It continues to amaze me that people list Baggage-Left-Behind detection as one of the shining examples of the power of video analytics. In fact, it has to be the biggest disappointment in the market. However, the reason it has failed so often is not a reflection on bad technology, but the dangers of complex systems. It is a good lesson in knowing where and when to use new technologies.

Marman goes on to show that while the technology works (detect bags left behind), it is not useful in real life situations. He notes:

IBM made a study of baggage-left-behind years ago. I don’t see a public posting of the study that I can link to, but they went back over the last decade to study terrorist bombings. The question they asked was how much benefit would baggage-left-behind have delivered if it were installed at the sites that were bombed. Their conclusion: Baggage-left-behind would not have helped a single one of the cases. No benefit at all. It wouldn’t have helped even prevent a single bombing or saved any lives.

He then shows the problem of baggage left behind is more nuanced. Its a great analysis of the problem as it actually occurs in real life. I urge you to read this complete post. Here are some of his parting thoughts:

It’s such a tempting use of analytics, especially when it is so easy to demonstrate. It really isn’t that difficult to detect a bag being left in the middle of an empty platform. But when you start looking at the overall complexity of the application, how difficult it is to reduce false alarms, the problems with recognizing bags in crowded areas, and how easy it is for people to defeat the system by not leaving bombs in open areas, then you start to realize that this really isn’t such a great application for video analytics.

rshah Applications

[From With New System, Digital Eyes Will Chart Baseball’s Unseen Skills - NYTimes.com]

A new camera and software system in its final testing phases will record the exact speed and location of the ball and every player on the field, allowing the most digitized of sports to be overrun anew by hundreds of innovative statistics that will rate players more accurately, almost certainly affect their compensation and perhaps alter how the game itself is played.

. . .

In San Francisco, four high-resolution cameras sit on light towers 162 feet up, capturing everything that happens on the field in three dimensions and wiring it to a control room below. Software tools determine which movements are the ball, which are fielders and runners, and which are passing seagulls. More than two million meaningful location points are recorded per game.

rshah Applications

[From colorblind | blogOV]

Bob Cuttings on over on blogOV has a bit of a rant on color detection in smart camera systems. I can’t judge the merit of his comments, but I think it is well worth repeating (It was so good, I copied most of his post):

The next time I attend a conference where that same company gives the same presentation showing how video analytics with color detection could have been used to search for vehicles and prevent events such as the Washington DC sniper killings, I’ll call them out. Using video analytics for color detection is viable in certain applications. But the way this “solution” is presented is just plain careless.

With any video analytic solution, it’s never just about the analytics. It’s about camera coverage…AND the manner in which cameras adjust to light changes…AND the lack of lighting for nighttime applications…AND the blue cast that seems to overlay many objects under certain lighting conditions…AND the sheer fact that customers underestimate the challenge of separating the white/grey/silver/light blue cars that make up 75% of cars on the road! Who has actually sold this and made it work?

This type of non-consultative, haphazard positioning of a solution does a great disservice to our market. Why do vendors continue to compromise our huge collective investment in R&D by making claims based on concept? Would you set up your company for such a customer support nightmare just to win a deal?

rshah Applications

Lucas D. Introna and Helen Nissenbaum have put together a comprehensive look at facial recognition. The title of the report is Facial Recognition Technology: A Survey of Policy and Implementation Issues.

The report:

highlights the potential and limitations of the technology, noting those tasks for which it seems ready for deployment, those areas where performance obstacles may be overcome by future technological developments or sound operating procedures, and still other issues which appear intractable. Its concern with efficacy extends to ethical considerations.

For the purposes of this summary, the main findings and recommendations of the report are broken down into five broad categories: performance, evaluation, operation, policy concerns, and moral and political considerations.

Introna also wrote a more scholarly paper a few years ago on facial recognition titled, Picturing Algorithmic Surveillance: The Politics of Facial Recognition Systems.

rshah Applications, Facial Recognition, Policy

[From In Hard Focus: Manchester Airport Downgrades Matching Threshold on Facial Scanners]

Here is the money quote from the Telegraph article that was posted:

Airport face scanners designed to verify travellers’ identity against their passport photographs are working at such a low level that they would be unable to tell the difference between Osama bin Laden and the actress Winona Ryder, it has been claimed.

Here is more detail:

In a leaked memo, an official says the machines have been recalibrated to an “unacceptable” level meaning travellers whose faces are shown to have only a 30 per cent likeness to their passport photographs can pass through.

The machines, undergoing trials at Manchester airport, have apparently been questioning so many passengers’ identities that they were creating huge queues. The technology was designed to help immigration officials spot people traveling under false passports, particularly terrorists, but the multi-million pound scheme now appears to be in jeopardy.

Rob Jenkins, an expert in facial recognition at Glasgow University’s psychology department, said lowering the match level to 30 per cent would make the system almost worthless. Using facial recognition software from Sydney airport in Australia set at 30 per cent, he found the machines could not tell the difference between Osama bin Laden and the actors Kevin Spacey or even the actress Winona Ryder while Gordon Brown was indistinguishable from Mel Gibson.

Stephen Russell adds a comment:

I’ll be interested to see if an official response to this “leaked memo” is released that explains the drastic drop in standards and their reason for the large number of false-positives. It could be the result of their technology choice, or just the result of poor, old, and varied photos common to passports. Likely both.

rshah Applications, Facial Recognition

['Smart' ads: targeted to who's watching the screen -- Newsday.com]

Cameras and televisions can be combined to customize smart advertisements. The cameras identify gender (with around a 85% accuracy) and then show the appropriate advertising – “That could mean razor ads for men, cosmetics ads for women and video-game ads for teens.”

This technology relies on facial recognition / face tracking software. The vendors mentioned are TruMedia and Quividi.

Here is a snippet about how the technology works:

In general, the tracking systems work like this: A sensor or camera in or near the screen identifies viewers’ faces by picking up shapes, colors and the relative speed of movement. The concept is similar to the way consumer cameras now can automatically make sure faces are in focus.
When the ad system pinpoints a face, it compares shapes and patterns to faces that are already identified in a database as male or female. That lets the system predict the person’s gender almost immediately.
The most important features seem to be cheekbones, fullness of lips and the gap between the eyebrows,” said Paolo Prandoni, chief scientific officer of Quividi, a French company that is another player in face-tracking technology. Others include Studio IMC Inc. in New York.
The companies say their systems have become adept at determining a viewer’s gender, but age is trickier: The software can categorize age only in broad ranges – teens, younger to middle-aged folks and seniors. There’s moderate demand for ads based on ethnic information, but the companies acknowledge that determining ethnicity is more challenging than figuring out gender and age range.

rshah Applications

[From Philips camera pill easy to swallow | Crave - CNET and Pillcam from CNET]

Two interesting pill size cameras/sensors for use inside the body. The Pillcam Colon Capsule Endoscope is a large pill with a camera inside it. It can generate up to 144,000 images over a 10-hour period.

The other pill size sensor is from Philips. It can be programmed to deliver targeted doses of medicine to patients with digestive disorders. Besides delivering medicine to multiple locations, the pill can measure data such as local temperature, and report measurements wirelessly to an external receiver unit.

rshah Applications