Smart Cameras Blog

[From Boeing's 'virtual fence' on Mexican border is full of holes, critics say -- chicagotribune.com]

An update on the Secure Border Initiative that is contracted out to Boeing. (See here for past coverage).

The program so far has been a failure. Nevertheless the government decided to give Boeing a second chance, because they thought it would be even harder to start with a new contractor. While Boeing is mum on how they will fix the project, a recent hearing has some details, starting with problems of the first version:

Flash rainstorms would trip the radar accidentally. Satellite communications — initially thought to be more efficient in terrain where cell towers are sparse — took too long to transmit instructions from cameras to control centers to agents in the field. By the time the agents reached locations minutes later where the cameras had registered a hit, the illegal immigrants had moved on.

. . .

The network of cameras and sensors was scheduled to be fully operational by this year. Now, the government’s new projection for full operation has been pushed back to 2016.

. . .

He said the government has simplified the project, removing in-vehicle monitors that didn’t work well. The project also has switched from satellite to microwave communication signals. The goal is to give agents a system that merges data from ground sensors, video cameras and radar.

The government already has installed 17 towers to watch over a 23-mile stretch south of Tucson, Ariz. The project managers are finishing a new round of testing and plan to turn the network over to the Border Patrol in January.

Borkowski said the future of the project depends on that field testing. Some lawmakers complain that the government has lowered expectations too much: The new system has to detect only seven of 10 incursions to be considered acceptable.

rshah Uncategorized

From heise online:

Here is a quote:

In April 2006, a pilot project was launched in Berlin, in which train operators on three lines of the Berlin underground aimed to test the extent to which 24-hour video surveillance could reduce criminality. The pilot project included the U2, U6 and U8 lines. The Social Democratic Party, which strongly supported the project in the state parliament, anticipated a “general preventive effect.”

An evaluation of the project commissioned from the Büro für angewandte Statistik was unexpectedly cancelled after receipt of an interim report. BVG, the company responsible for public transport in Berlin, stated that the pilot project had proved its worth in the detection of assaults and criminal damage and decided to extend the project to all 170 underground stations in Berlin by the end of the year.

Civil rights group The Humanist Union has now forced the BVG, which had previously declined to do so, to release the report (PDF file). According to the report, video surveillance and recording on the three underground lines did not reduce the incidence of criminality, but in fact led to a small increase.

Of a total of many thousands of criminal incidents, video material was available in only 78 cases. In only a third of these was the recording of sufficient quality to allow suspects to be identified. In particular, the cameras were not able to contribute to a higher detection rate regarding prevention of vandalism. The report suggests that in this case the reason no usable video recordings were obtained was that criminals were taking the cameras into account in planning their malfeasance. (anw/c’t)

The report is here, but it is in German

rshah Uncategorized

From USATODAY.com:

Another article with anecdotes of how cameras reduce crime. There really is a need for some good empirical research in the US. The article notes:

Jose Cordero, police director in East Orange (NJ), said the sensors and cameras have helped reduce crime 38% and shootings 30% so far this year compared to 2006. The city has nearly halved its murders from 17 in 2004 to nine last year, Cordero said.

rshah Uncategorized

From New York Times:

A 25 year blueprint for NYC includes a role for smart cameras in several areas. For example, incorporating congestion pricing (ala London) for Manhattan below 86th Street from 6 a.m. to 6 p.m. on weekdays.

In Manhattan, cameras and other equipment at intersections would deduct money from a driver’s E-ZPass account or photograph a car’s license plate, with the driver given two days to pay the fee through the mail, online or at certain stores.

The city said yesterday that it intended to seek state approval for a three-year test of congestion pricing and would need to spend $225 million to buy and install traffic-recording equipment. Officials said the city and state could jointly apply for grants from the United States Department of Transportation to cover those costs.

”The federal government really does want to be helpful,” Mr. Bloomberg said, in a rare departure from his prepared text.

According to thenewspaper, there are also proposals for:

plans to expand the use of multi-space parking meters designed to double-charge for parking. Bloomberg is counting on a windfall from traffic ticket revenue to further boost revenue from his plan. . . . Finally, Bloomberg wants to introduce speed cameras and massively expand the city’s existing red light camera program.

rshah Uncategorized

From Wired 15.04: Shot Spotter:

A great article on the shot spotter technology (gunshot detection system). It covers how the system works, the history of the technology, and how it is currently being deployed. Its a nice long article with lots of detail. Here are some snippets:

In October, the department spent $350,000 to install 84 ShotSpotter sensors on rooftops, utility poles, and other inconspicuous places over 6 square miles of urban blight. Since then, dispatchers have received roughly a dozen automatic alerts every day, each one an opportunity to get officers to the scene of a shooting while the gun is still smoking. [Oakland, CA]

“In the past, the best information the police could hope for was a neighbor calling to say, ‘Sorry to bother you, but there may have been a shooting somewhere in my neighborhood,’” says ShotSpotter CEO James Beldock. “Our system can immediately tell them that, say, 11 rounds were fired from a car going 9 miles an hour, northbound, in front of a specific address on Main Street. In some situations, ShotSpotter could get someone on the scene within a minute. That’s a level of situational knowledge police have never had.”

This kind of coverage requires an array of 12 to 20 specialized sensors per square mile. Roughly the size of a medium pizza and designed to look like a rooftop fan, each sensor contains up to four small microphones. If one of these units detects a loud noise, it forwards a recording to a server at police headquarters along with three pieces of information: location, time, and general direction the sound came from. If a sound is detected by only one sensor, it’s probably too quiet to be gunfire, and in any case, the system needs data from three sensors to pinpoint the location of a noise. If several sensors report an event at the same time, the server gets to work. First, the software performs an analysis to categorize the noise as gunfire, firecrackers, bottle rockets, helicopters, or other. If it determines the event was a gunshot, the program makes a simple calculation to triangulate the sound’s origin to within 80 feet or less.

The upgrade caught on fast. Chicago, Gary, and Washington, DC, bought systems in 2005 and 2006. . . . Meanwhile, ShotSpotter expanded from the mean streets of the US to the blast zones in Iraq. In 2006, the Army deployed a specialized battlefield version. The user interface is mobile, and so are the sensors themselves; soldiers carry units roughly the size of a Tom Clancy paperback. The sensors pinpoint enemy fire while a camera on an unmanned Boeing scan Eagle aircraft overhead targets the threat.

The improved sensor arrays deployed in US cities show even more promising results. Two days after Rochester, New York, activated 6 square miles in July 2006, local police arrived on the scene of a shooting in time to make an arrest. Since then, the array has been solely responsible for roughly one gun-related arrest per month.

The 2-square-mile grid in Gary recorded 10 to 15 incidents a day when it was installed in 2005. Police used the system to confiscate 45 illegal weapons on New Year’s Eve of that year, and shooters began to think twice. Now the system picks up one or two hits a day.

rshah Uncategorized

From Informationweek:

Smart cameras being used in retail setting to improve operational efficiency, merchandising, and market research. The article focuses on the use of IBM’s Smart Surveillance system by Pathmark supermarkets.

For example, it might provide better data on what percentage of shoppers make purchases and why the rate differs by store. Analyzing how customers move through stores might also let Pathmark tailor the layout based on traffic and place promotion material better.

Its pretty thin on details, but another example of how smart cameras are beginning to be considered for applications outside security.

rshah Uncategorized

From NYTimes:

A new x-ray body scanning machine is being tested at the Phoenix Sky Harbor International Airport. It is a millimeter wave machine and is able to provide a “virtual strip search” for airport security.

The machine beams a low-energy X-ray at the passenger, which after it bounces off the surface of the skin is processed by computer software that highlights metals or elements like nitrogen that are found in explosives or weapons. The X-ray is not strong enough to penetrate much beyond the skin, so it cannot find weapons that may be hidden in body cavities.

The interesting part for me is the privacy software that “intentionally blurs the image, creating an outline of a body that is clear enough to see a collarbone, bellybutton or weapon, but flattens details of revealing contours.” Its nice to see a smart sensor/camera system that considers privacy. This is an improvement over earlier systems that have been discussed here and here.

rshah Uncategorized

I thought I would highlight two interesting articles on privacy with smart cameras.

The first comes from Reason and is titled Is Privacy Overrated?

Its key insight is the gains that come from a transparent society ala Brin.

My credit card company has long known where I buy underwear, but I don’t lay awake nights worried that prosecutors might demand knowledge of my preferences in skivvies. The ways in which that information can be accessed by the state are circumscribed by decades of legal precedent. We should remain vigilant that those precedents aren’t eroded, and we should work to strengthen protections where necessary, but the collection of the information in itself is an unstoppable force, mostly for good–I like that I can sift thorough records ofeverything I have purchased in the last three years.

As this hints at, the article still notes that abuse of cameras by public officials is a reasonable fear and one that should be punished.

The second is by Bruce Schneier, the renowned security expert. He wrote an op ed for the Arizona Star. In the article, which discusses the use of ANPR, he points out how “technology is fundamentally changing the nature of surveillance.” He uses the term “wholesale surveillance.” He argues this switch is not a mater of degree, but fundamentally different than our previous notions of surveillance and privacy. He argues:

Wholesale surveillance is fast becoming the norm. Automatic toll-collection systems record when individual cars pass through toll booths. We can all be tracked by our cell phones. Our purchases are tracked by banks and credit-card companies, our telephone calls by phone companies, our Internet surfing habits by Web site operators.

The effects of wholesale surveillance on privacy and civil liberties are profound; but, unfortunately, the debate often gets mischaracterized as a question about how much privacy we need to give up in order to be secure. This is wrong. It’s obvious that we are all safer when the police can use all techniques at their disposal. What we need are corresponding mechanisms to prevent abuse and that don’t place an unreasonable burden on the innocent.

As a practical example, he suggests that ANPR systems should erase the data on innocent car owners and not save it. Furthermore, he argues that with automatic detection, think red-light cameras, we need to realign the detection and enforcement actions. He suggests removing criminal penalties for both red-light cameras and speed-trap cameras. Instead, the the cameras should issue citations without any “points” assessed against the driver.

rshah Uncategorized

From Chicago Tribune:

A story describing 3VR’s search technology for camera footage. I noted this technology about a year ago when it received quite a bit of press. Here is a bit more detail on how it works:

We discard everything except the best two or three frames,” he said. The system looks for images that are similar to each other, Ross said, and this produces many results that aren’t right on target. “But if you get 100 images to look at and 10 of them are what you want, that’s good enough,” he said.

A system costs $4,000 to $16,000, depending on its analytical ability, according to 3VR. The company, which has financial backing from an arm of the Central Intelligence Agency, collects information associated with video images, Ross said.

It notes if there is motion, if a human appears to be moving and which way. It notices if something in a scene changes and when. All of this information can be reduced to bytes in a database that’s quickly searchable. That serves as a sort of index to the video images associated with each observation. And the system becomes better with practice.

After being told that 10 different images are all of the same hotel employee, Strand said his system can locate that employee viewed on any of the Talbott’s cameras with about 80 percent accuracy.

rshah Uncategorized

From the Baltimoresun.com:

Some useful information on the smart camera system at John Hopkins University. Back in May 2005, I noted this camera system. The system relies on 89 cameras. The software is by Cernium and displays 19 scenes on a large screen in the command center. It is also sends alerts from 18 different behaviors including “people moving very fast or loitering; cars that stop suddenly or drive too fast; crowds that gather or disperse; unattended objects and people who fall”. The article provides a number of examples of how these alerts have proved useful, such as detecting loitering:

A lone man is looking up and down the street, apparently waiting for someone. A pickup truck drives up. The man says something to the driver, gets in and they drive off. Minutes later, a block away, a woman is robbed at gunpoint by two men who speed off in a pickup. No one at the scene can describe the truck to campus security officers or to Baltimore police.

Hopkins’ security system caught the robbery suspects on a video camera on Lovegrove Street. The software registered the man’s behavior and the late hour, and alerted the security officer on duty in the command center. The view down Lovegrove was singled out by the computer amid the incoming imagery from 89 campus security cameras. It popped automatically onto the officer’s screen, with the man’s image highlighted in a yellow box. She quickly zoomed in and recorded images of the suspect, the truck and its license plate.

After the victim reported the robbery, the tag number led police within hours to a borrowed truck and the suspect, who had a police record. The victim picked him out of a photo lineup. He was arrested a few days later, linked to a second crime and charged with both.

“If we didn’t have this video system, or she didn’t focus on him, he would have gotten away,” said Edmund Skrodzki, executive director for security for Hopkins’ Homewood campus. “One person can’t monitor 89 screens. You need help with it, and behavioral recognition provides that assistance.”

• In addition to the Lovegrove loiterer, the system has alerted security to a juvenile as he attempted to steal a motorbike, leading to an arrest.
• Another youth was spotted, tracked by cameras and arrested after spray-painting graffiti on campus buildings.
• A nighttime bicycle thief was confronted after another alert brought nearby security officers to the scene. The crook dropped his bolt cutters and ran off, but the bike was recovered, Skrodzki said.
• Other potential criminals were warned off because of automated alerts as they cased a sorority house, or tried doorknobs and car handles near campus.
• Campus bike thefts dropped from 25 during the 2005 fall semester to three last fall. Overall crime was down 20 percent in 2006. And Skrodzki credits the behavioral recognition software for providing a critical assist.

rshah Uncategorized