John Honovich points out the importance of false positives. A false positive arises when a smart camera system warns operators of a situation, when the situation is normal. This problem arises when cameras move out of laboratories into real world conditions where weather and external stimuli, such as birds, make video analytics difficult.

Here are some interesting snippets:

Making sure you only trigger when someone is violating is hard because there are so many factors that might set off the analytic besides a valid adversary. To a computer, rain, dust and snow can all generate a similar form to a human being. Quick changes in light or the movement of water (waves) can also generate such forms. A camera that shakes because of the wind or issues with the mounting or installation also can trigger such alerts. The hard part in such analytics is to make sure that these alerts can be eliminated. This is a key metric in testing and differentiating between analytics.

False positives drive up the cost of systems. . . . While it is better operationally to centrally manage alerts, if the system generates dozens or hundreds of false alerts per day, the costs can become prohibitive. Let's say an 'intelligent' camera generates 5 false alerts a day at the cost of $1 per alert (the unit cost to pay a monitor to assess). That's $5 per day, over $1,800 per year and about $10,000 for a projected 5 year lifecycle. If you dozens or hundreds of cameras, this hidden operational cost can be in the millions. And this is not theoretical. This is the feedback you will hear time and again from real world deployments. It's widely accepted that this is improving but it is still the major factor in duing your due diligence in analytics.

The network is expanding by 5000 cameras. It will include 3 to 5 operators watching images in real time. Analytic software is expected to be added by the end of the year. The cameras come from existing networks:

In its start-up phase, the system will include the public schools, the D.C. Housing Authority, the Office of Property Management and the Transportation Department. By year's end, it will expand to homeland security and the departments of Parks and Recreation, Corrections, Health and Fire and Emergency Medical Services. The schools have the largest number of cameras, about 3,600.

Right now DC is still looking for funding and privacy advocates are not happy that the department is rushing ahead without applying prior safeguards. Until now, DC had been the model for the best privacy safeguards. See the article for more or read this nice opinion piece by John Podesta and William Sessions.

Developed by Karl Martin and Kostas Plataniotis, researchers at the faculty of engineering, their secure visual object coding application uses cryptography techniques to encrypt "objects of interest" within video frames -B faces or other features that may be used to identify a person - and store them separately. In order to view the original complete image, a decryption key is needed to restore the object of interest.

The project web site by Karl Martin shows a number of pictures of the process at work. The idea here is to encrypt either faces or complete bodies as a way to protect privacy. For example, surveillance could be monitored in real-time but faces would be obscured. However, this is reversible if a decryption key is used.

The PET application is an add-on designed to work with a front-end video surveillance system that has object detection capabilities. "Facial detection has been around for a long time to varying degrees of performance. Many vendors already offer it in consumer applications like digital cameras so you can focus on faces when taking photos."

An interesting article on the use of small cheap motion detectors within buildings. They can be used as an alternative to cameras in some areas, because they are cheaper and less invasive from a privacy standpoint. It is suggested that this technique could be used for security monitoring.

Here is a nice video of the system, Ambient Intelligence for Better Buildings (link to Journal article)

Preliminary results are being released on a study of the effectiveness of cameras in San Francisco. The cameras have slightly reduced nonviolent threats, otherwise they have had no effect on crime.

The city contracted with the UC Berkeley's Center for Information Technology Research in the Interest of Society to evaluate the cameras. The final report won't be available for a few months. I am glad San Francisco is doing this and I wish other cities (ahem . . Chicago) would allow researchers to evaluate the effectiveness of cameras. An important factor to consider is that the cameras in San Francisco are not monitored in real-time (lowering costs, but also lowering effectiveness).

Researchers examined data from the San Francisco Police Department detailing the 59,706 crimes committed within 1,000 feet of the camera locations between Jan. 1, 2005, and Jan. 28, 2008. . . . The only positive deterrent effect was the reduction of larcenies within 100 feet of the cameras. No other crimes were affected - except for homicides, which had an interesting pattern. Murders went down within 250 feet of the cameras, but the reduction was completely offset by an increase 250 to 500 feet away, suggesting people moved down the block before killing each other.

I enjoy as much as the next person television shows such as 24 and the BBC's excellent equivalent MI-5, but I am under no illusion that super agents using super computers are able to monitor terrorists in real time as they make their way through city streets and malls so they can be interdicted before they carry out their plots. The best that can be hoped for from cameras is that they deter would-be terrorists. But cameras cannot actually prevent terrorism, unless a perpetrator is very dumb and slow and authorities are extraordinarily lucky.

Another useful observation:

In the 1990s, New York City made great strides in cleaning up its subway system and streets. But it did so by putting more officers on platforms and trains. Police can see what cameras cannot, and they can respond immediately, rather than waiting to be summoned by those monitoring cameras. Cameras are a sop, a symbolic reaction that merely enables timid politicians to say, "Look. See? We're doing something."

A second column I found interest is by Julian Sanchez on wiretapping. This is an issue of great contemporary political import. The core of this debate has implications for the use of surveillance cameras by government. Read the column, but here are some key insights:

Without meaningful oversight, presidents and intelligence agencies can -- and repeatedly have -- abused their surveillance authority to spy on political enemies and dissenters. The original FISA law was passed in 1978 after a thorough congressional investigation headed by Sen. Frank Church (D-Idaho) revealed that for decades, intelligence analysts -- and the presidents they served -- had spied on the letters and phone conversations of union chiefs, civil rights leaders, journalists, antiwar activists, lobbyists, members of Congress, Supreme Court justices -- even Eleanor Roosevelt and the Rev. Martin Luther King Jr. The Church Committee reports painstakingly documented how the information obtained was often "collected and disseminated in order to serve the purely political interests of an intelligence agency or the administration, and to influence social policy and political action."

. . .

In that light, the security-versus-privacy framing of the contemporary FISA debate seems oddly incomplete. Your personal phone calls and e-mails may be of limited interest to the spymasters of Langley and Ft. Meade. But if you think an executive branch unchecked by courts won't turn its "national security" surveillance powers to political ends -- well, it would be a first.

Thruvision offers a camera that relies upon Terahertz electromagnetic waves. The promise of terahertz is that these waves emit from people, but pass through solid materials. By passively collecting them, it is possible to identify if someone is concealing an object. The above story has lots of links for more information.

A nice article on the growing use of facial recognition. A couple of interesting points:

After a driver sits for a photo at the Illinois Secretary of State office to renew a license, officials use facial-recognition technology to give the resulting image a close look. First, state officials verify that the face matches the images portrayed on previous licenses issued under the driver’s name. The second, more extensive run-through determines if the same face appears on other Illinois driver’s licenses with different names.

Since starting the program in 1999, the state has uncovered more than 5,000 cases of multiple identity fraud, said Beth Langen, policy and program division administrator at the Illinois Secretary of State office. The state pays Digimarc Corp. about 25 cents per license for the service, she said. . . . About 40 percent of the nation’s drivers are set to undergo such facial-recognition database checks when they renew their licenses in 20 states. . . . .

Police departments, eager for more investigative tools, are pressing for access to the millions of photographs in the motor vehicle databases. A few states prohibit such sharing, but many allow it.

Chicago is going to link 4,500 school cameras to police districts, squad cars, and the 911 emergency center. This Sun-Times notes that the existing network includes more than 10,000 public and private cameras. So this means, the 911 center will be capable of monitoring 15,000 cameras. The half million dollar upgrade will be paid for with Homeland Security funds.

School cameras go from cameras viewable only by school security to cameras viewable by 911 dispatchers, squad cars, and police districts. The article notes that the cameras will be accessible only when needed (whatever that means).

15,000 cameras is enormous. I am really curious about the technical infrastructure to integrate those feed and archive them.

There are a whole host of issues with cameras in schools, a previous post on cameras in NYC schools considers some of them.

Update: I confirmed the 10,000 cameras with Fran Spielman, the Sun-Times reporter. "The 10,000 figure includes CTA, airport, city, Park District, McCormick Place cameras, as well as private cameras hooked up to the city network."

A very informative article on red-light cameras in Chicago. Here is a summary of many of the facts in the article:

69 intersections with red light cameras in Chicago, resulting in 800,000 tickets over the last four years, the tickets cost $90 each, the city has collected $19.8 million in 2006 and expects to collect $50 million this year. By my calculations, this means over the last four years, violators have paid $72 million in fines.

The city has signed a $52 million contract for 220 more red light cameras by 2012. (Plus there are more red light cameras going up in the suburbs because of a new state law.)

Part of the contract "requires technology that will allow motorists to see evidence of their violation online. Using their computer keyboards to enter a city code, license plate number and citation number, drivers will be able to view 12 seconds of video and still photos that officials expect will show the offending vehicles in the intersection with a visible red light."

I am still curious about the effectiveness of the cameras. A previous story claimed a 70 reduction in accidents, but this article states that early data indicates a 24 percent decline in accidents. Also the article notes that violations have dropped significantly at the sites where red light cameras are located:

On average, the number of red-light violations at camera-equipped spots so far has declined 59 percent, he said. At Halsted and 111th Streets, where the devices have been particularly effective, violations have dropped from 105 a day to 10, Bills said. At Ashland Avenue and 71st Street, the decline has been from 44 to about four, at LaSalle and Kinzie Streets, from 39 to four.

Gait analysis and recognition is another useful application of smart camera systems. There are several problems with reliable gait analysis including the collection of data and that the choice of footwear can affect how people walk. Plantiga offers a new shoe that can provide more gait and movement information and then transmit it wirelessly. As a result, it offers a unique method of biometric identification. For more, see this page on their web site.

I have no idea how well this works, but it is a novel and interesting approach.

A thoughtful opinion by Frank Baitman on whether it is time to regulate surveillance. Frank Baitman is president of Petards, the Baltimore-based subsidiary of Britain-based Petards Group. He has been obviously influenced by the laws in Britain and believes they can serve as a model of us. He points to three specifics areas:

Specifically, Congress should consider establishing laws to:

Ensure that surveillance technologies satisfy their mission for crime and terror control without the potential for misuse.

Reassure the public that their images are being collected for bona fide objectives, and that there are penalties for those who misuse surveillance recordings.

Promote the adoption of open standards to ensure interoperability, which in turn would promote the introduction of emerging technologies.

First, the Metro Nashville, TN school system is installing face-recognition technology, which is suppose to be operational by December 2007. Its a bit strange that this is installed in an elementary school, but I will be awaiting the results of the test.

Second, a facial recognition research group is online at http://www.face-rec.org/newsgroup/. There are lots of techie articles, but also an active google group (face-rec) discussing the issues.

Third, the National Institute of Standards and Technology has been evaluating and testing facial recognition technologies. The project is known as FRVT. Its too bad there haven't been other public tests for other features of smart cameras.

DARPA is supporting various smart camera technologies in a number of ways. Here are snippets from the story:

Dynamic Multisensor Exploitation, or "DYME," aims to combine cameras, radar, and acoustic sensors to better find bad guys as they move through urban canyons, and along coastal waters.

The goal of "Building Labels for Urban Environments," or "BLUE" (you gotta love these acronyms), is to automatically label the structures seen in surveillance video.

The Combat Video Analysis Engine (no acronym, alas) would use "computer vision, machine learning and probabilistic models to detect and recognize complex threats and suspicious activities without identification of specific individuals."