surveillance
EFF condemns Apple's "traitorware" technology
The Electronic Frontier Foundation, a watchdog group for digital privacy issues, has issued a statement condemning Apple's exploration of what EFF calls "traitorware." According to the EFF statement, Apple has filed a patent application on technology that would allow Apple to take pictures of an iPhone user without the knowledge of the user and send them back to Apple.
Computer vision scientist wins People's Choice prize
Australian computer vision researcher Clinton Fookes has won one of the Austrialian Museum's Eureka Prizes, which are considered among the most prestigious in Australia. Dr. Fookes, of the Queensland University of Technology, does research on 3-D face recognition, with applications to security in public spaces such as airports.
Government scientists investigating nonverbal cues to detect terrorists
Submitted by Sek Chai
Scientists at the Homeland Security Advanced Research Project Agency are investigating methods to detect people with malicious intent using nonverbal cues. High resolution cameras, low power laser scanners, and other devices can be used to measure fidgeting, heart rate, pupil dilation, and skin temperature. These sensors could be placed in a security line, record travelers bio signs, and alert the guard if necessary. More information is available in a Los Angeles Times article
Surveillance systems detect insurgents' behavior patterns
Submitted by Sek Chai
Researchers at the Defense Science and Technology Laboratory (DSTL) in the United Kingdom are developing a surveillance system that finds insurgents or terrorists. The system would detect unsual behavior patterns that are characteristic of insurgents, such as "two vehicles meeting in a concealed location". It uses high resolution cameras (128 Megapixel)and hyperspectral cameras with large area coverage. More information is available in a BBC News article.
Camera provides real-time text description of surveillance feed
Submitted by Sek Chai
Researchers at UCLA (University of California, Los Angeles) have developed a prototype system to generate real-time text descriptions from surveillance cameras. The system, named I2T (Image to Text), parses each image, separates the background from objects, and then describes the movement of objects in successive frames. More information is available in a MIT Technology Review article.
Arizona to discontinue speed camera program
Submitted by Boaz Super
The state of Arizona is discontinuing its speed camera program. Redflex, the company providing the speed cameras, announced that its current contract will not be renewed. Although the contract runs through early 2011, Arizona will turn off the cameras on July 15th. Speed cameras and red-light cameras continue to be used in many other states and municipalities, including municipalities in Arizona.
Video analytics software learns crowd behavior
Researchers at Curtin University of Technology have developed vision based software to detect unusual behavior in crowds. The software could learn typical behavior in different environments and then report on unusual activities. The project is supported by venture capital firm Yuuwa Capital and Curtin University pre-seed funding. The software is being commercialized for use in video surveillance by iCetana Pty Ltd. More details are available in a press release.
Computer vision system for air traffic control to be built by MIT
Submitted by Boaz Super
The US Federal Aviation Administration (FAA) has commissioned MIT to build a Staffed NextGen Tower (SNT) for airport ground control. Currently air traffic controllers perform out-the-window visual surveillance. With SNT, the controllers will instead use video from a network of cameras throughout the airport. A press release states that computer vision techniques will be used, but does not give details.
BRS Labs announces new version of its visual surveillance analytics system
BRS Labs has announced the release of AISight 2.1, a computer vision system that classifies and tracks objects. According to the company's press release, the system's classifiers are automatically trained on particular scenes on a camera-by-camera basis, and can distinguish between humans, cars, and animals.
UK researchers develop biometrics tunnel for gait analysis
Professor Mark Nixon of the University of Southampton is leading a research project on gait analysis. A tunnel with four cameras on each side records the 3D motion of a person walking through the tunnel. On future traverals of the tunnel, a person's gait can be compared with the recorded representation. The tunnel's background consists of colored squares to aid the analysis. More information is available in a janes.com article.
