[From In Hard Focus: Sitting Down with Rajiv Shah]
Stephen Russell of 3VR Security recently gave me the chance to ask him some questions on smart cameras. He has posted his responses over at his blog, In Hard Focus. HIs responses are very informative and insightful. I urge all of you to read his full responses. Here are the questions I asked:
1. Privacy: What should the industry approach be towards privacy? Should they incorporate features that protect privacy? Should they have default settings that protect privacy or delete information? Or should we not worry about this? Is there a need for an industry-wide approach to this issue?
2. Comparing Vendor Solutions: What can be done to make it simpler for end users to compare and contrast different solutions? It’s very confusing now for end users to sort through claims by tens of companies on effectiveness, costs, technology, etc.
3. Connections to Academia: Explain if anything needs to be done to expand the connection between industry and academia. After all, much of the engineering talent has come directly from universities. Are there any suggestions you have for universities and their research?
4. Future Growth of Smart Cameras: Have cameras hit a period of steady growth or do you foresee a potential boom ahead? If so, what are the crucial factors that you see that are limiting growth of that will cause growth to increase? Do we need to improve technology, better end-user experience, etc.
rshah Policy, Vendors
[From Photo Enforced: License Plate Hunter Cameras]
A post describing ELSAG North America’s Automatic License Plate Recognition (ALPR) technology.
A network of fixed LPR systems, which can be mounted to structures such as bridges and overpasses, as well as mobile LPR systems, which are mounted to police vehicles that can capture up to 3,000 license plates per hour, help keep a tight watch on cities, ports, borders and other sensitive areas. The MPH-900® LPR technology is being used by hundreds of agencies all across the United States to assist with interdiction, the capturing criminal intelligence data.
rshah ALPR, Vendors
[From Vumii]
Vumii Sensorii software combines a static panoramic image with a live view at night. This allows users to easily navigate an area at night. See the video for a demonstration.
Vumii also has added a software module that enables communication between radar systems and its Discoverii day/night laser camera platform. This allows for a seamless transition between radar and cameras.
While I am sure other vendors offer similar capability, the point here is how software can integrate multiple systems and sensors. As a result, users have access to greater data, but in a very manageable way.
rshah Vendors
Here is a brief summary of some of the news regarding IBM and Chicago’s venture on smart cameras:
Here are the goals as laid out in the CNN story:
In the first phase, IBM helped the City experts and network engineers to design and implement a surveillance strategy infrastructure to capture, monitor and fully index video for real-time and forensic-related safety applications. This entailed building a unified fiber network throughout the downtown Chicago area, deploying a critical wireless infrastructure to offer flexibility as required, installing hundreds of new surveillance cameras, linking thousands of preexisting cameras to the network, and creating a fully redundant backend system to monitor the video, store the images and allow for business continuity and disaster recovery applications.
The Chicago OEMC and IBM are now teaming to expand the surveillance system and to add analytics that provide license plate recognition, trending projections and intelligent search capabilities to the existing infrastructure. Chicago’s security solution is designed to provide several benefits to both city officials and citizens including: real-time video surveillance intelligence for proactive homeland security monitoring; faster response time to emergencies; more effective deployment of emergency responders; and increased travel efficiency through traffic congestion tracking.
IBM is pushing their smart camera technology. I assume its based off the Smart Surveillance System that I previously noted. The system features some security cameras that can detect gunshot sounds that prompt the cameras to turn toward the sounds before automatically calling 911. The system can also read license plate numbers. They are hoping to roll this out to other cities, but Chicago is first.
IBM is collaborating with Firetide and Genetec.
Firetide has a mesh technology that “supports wireless public safety applications ranging from traffic control and VoIP communications to covert and overt video surveillance. The Firetide system allows Chicago’s first responders to access databases rapidly and is configured to allow the addition of thousands more video access points in the future.” – From InformationWeek
Firetide’s mesh network operates within the 2.4 GHz, 4.9 GHz public safety licensed band, or 5.0 GHz band. “Because the technology is radio-agnostic, any license-free or licensed spectrum (can) be meshed,” said Bo Larsson, Firetide CEO, in an e-mail. ‘Firetide is unique in that our nodes can be decoupled from access points. Sometimes the best location for an access point is not the best place for a mesh node.”
IBM chose Genetec’s Omnicast as the main video management platform for building the Operation Virtual Shield system.
rshah Chicago, Vendors
From Forbes.com:
A very nice short article on installations of smart cameras. The article mentions:
Port of Houston (Verint Systems)
The Eiffel Tower (Nice Systems)
New York City Subways (ObjectVideo)
Port of Corpus Christi, Texas (Vistascape)
O2 in London (Ipsotek)
Subway in Stockholm (Axis Communications)
rshah Vendors
From Government Technology:
I have noted before how cell phones can be used for traffic monitoring. Dust Networks is taking that capability to add smarts to traffic monitoring.
“The Dust Network compares current speeds with historical speeds, and when it sees a large variation in what’s expected, it trips an alarm,” said Szymkowski, adding that AirSage monitors calls to 911 and creates an alarm when it detects a spike. “We’re probably going to be working with the Wisconsin State Patrol to understand when an incident occurred and see if we can match up the alarms with the real incidents.”
Dust Networks web site also mentions another interesting technology that makes parking meters smart.
Streetline Meter Monitors provide two-way networking to standard single space parking meters, with no wiring and no modification to the meter housings. The patented technology is compatible with over 90% of installed meters, and in most cases will simply plug into existing meter data ports. The Monitors help cities track usage and vandalism, and provide a detailed audit of all meter operations in real-time. Streetline Vehicle Sensors deliver accurate real-time information about arrivals, departures and occupancy in on-street parking spaces.
rshah Vendors
From FCW.com:
A nice article on smart cameras. It discusses the role of video analysis software used by the Halifax Port Authority (vendor is PureTech Systems) and the San Francisco airport (vendor is Vidient). It also gives a sensible use for smart cameras:
The airport spent about $30,000 for software that sounds alarms if it detects someone trying to bypass security via the exit lane for arriving passengers. “Many airports use a person to watch this lane, but we felt it was the best use of our resources to simply automate the monitoring job,” Short said.
As well as spill-over benefits of cameras:
Video software can also assist with forensic analysis after an incident occurs. Of the three incidents that have triggered alarms since the Rapid City Regional Airport installed motion-detection software in 2006, one involved a passenger who ignored alarms and continued to the boarding area. The video record of the event was a major piece of evidence for the U.S. attorney who prosecuted the breach.
Dilip Sarangan of Frost and Sullivan chimes in:
the market faces challenges in reaching that size. For one thing, the accuracy of analytical algorithms must improve. “This is still very, very much an emerging technology,” Sarangan said. “Only in the last year or two have we started to see companies actually implementing these solutions so they could be used as a complete security solution.”
rshah General, Vendors
From the newspaper.com:
Redflex, a major developer of red light cameras, has developed a stop sign camera, read their announcement.
The stop sign devices are based on red light camera platforms, but they differ greatly in use. The more familiar stoplight cameras typically photograph a vehicle entering an intersection if a signal light changes to red as little as 0.1 seconds after the car crosses the stop bar line. In most cases, the resulting ticket photograph will show both the vehicle in the intersection and a visible red light, offering visual documentation of the technical violation. With the new Redflex stop sign cameras, a machine will make calculations to determine whether a vehicle did not come to a complete stop and deserves a ticket.
While I think this isn’t as important as red light cameras from a traffic safety perspective, it does show the growth in this industry. I am sure over the next several years, we will see lots of these ticketing devices. They appear effective at enforcing laws and generating revenue. Moreover, the public outcry over them hasn’t sufficiently coalesced to protest these devices.
rshah Applications, Red Light Cameras, Vendors
From San Jose Mercury News:
A number of anecdotes on 3VR’s technology, which was described here previously.
Consider what happens to criminals who write bad checks. Nowadays, a security camera can track someone who walks into a bank and take a sharp picture of the person’s face. It can then compare that face to a database of known fraudsters. By the time the person walks up to the teller, the system can warn the teller not to cash a check from that person.
This technology is available today thanks to San Francisco-based 3VR, which has applied its search technology to face recognition. Using off-the-shelf computers, the 3VR system captures an image of a face from a security camera and compares it to faces stored in a database. More than 90 percent of the time it comes up with an accurate match, according to the company.
Three of the nation’s top 10 banks as well as the Bank of Hawaii are using it. Other customers are in retailing, travel and national security.
The Drake Hotel in San Francisco discovered a case of employee fraud as a result of the 3VR system. It showed that one employee was clocking in and then disappearing for hours at a time. The system enabled hotel security to search through camera videos for the worker’s face quickly, said Lisa Kershner, director of operations at the Drake.
rshah Vendors
From CNN.com:
A nice interview with Sergio Velastin of Ipsotek out of the UK. Velastin is a leading scholar on developing smart camera systems. Some quotes from the article:
Industry experts suggest that after 12 minutes of continuous video monitoring an operator will miss up to 45 percent of screen activity. That rises to up to 95 percent after 22 minutes.
“Humans will always be better than machines at spotting real behavior, but most security guards have an almost impossible task to watch so many screens all the time that they can’t be used practically,” Velastin told CNN.
“Most people do things in a fairly straight forward way and we’re able to gain statistical knowledge of what they do. From that it follows that you can raise an alarm if something is deemed ‘infrequent’, which usually means abnormal or suspicious,” he said. It sounds simple enough, but the task of creating a computer program that can filter out all the normal background goings on of a situation, be it on a train station platform or high street, has proved to be extremely complex.
In three to five years we hope to have a program that would identify from your walk whether or not you are carrying a gun,” he told CNN.
rshah Vendors
Recent Comments