"As of right now there is no arrest and no anticipated arrest"

Here's a tragic story hitting headlines everywhere -- however, no stories I've found have seriously discussed the surveillance technology at play nor the length of time this investigation has taken.

Late last week, a Yale pharmacology grad student's body was found hidden in a wall in the basement of a Yale medical research building after she had been missing for almost a week.

However, due to the access control restrictions on the building, investigating officers believe this not to be a random act, but rather one committed by someone in the Yale community. Yale University President Richard Levin was quoted on Monday as saying, "We know everyone that was in the basement. There were limited number of people in the basement and we passed that on to police. There is an abundance of evidence."

And as CNN has reported, security cameras registered Le entering the building, but after searching hours of surveillance tapes, had been unable to find images of her leaving the building. The NY Daily News even reported that more than 100 FBI investigators and three police departments spent over six days pouring through building blueprints and surveillance footage -- and even used bloodhounds to search the building. Six days is a long time.

What does this tragic event teach us? While we await the murder details (expected to be revealed today), the value of using analytics and more sophisticated surveillance tools to search and comb through footage may have reduced the time needed to come to the conclusions we reached in seven days to maybe only a couple of hours. While even the tightest access control restrictions and clearest surveillance cameras cannot prevent a human from taking another's life, technology has the ability to hasten investigations and also equips security personnel with the eyes and ears needed when the human equivalent is not an option.

Using a variety of facial recognition, color tracking and other analytics, we may have been able to identify the student upon entering the building and followed her whenever she appeared on camera. We also could have also identified each person's face that entered and exited the building that evening, as well as tracked articles of clothing by color. We might not have an answer for the cause of such a brutal and senseless attack, but we do know that more stringent access control and surveillance technology may have helped in the investigation process.

I Can't Help It -- More iPhone MacRumors

MacRumors is back at it. Today, they're reporting additional patent filings around object recognition and facial detection extensions, continuing to push forward some of these technologies that I've posted about recently. While these take time to come to fruition, I can't help being excited -- the possible adaptations of these ideas are endless. Let's take a look.

The object recognition capability in which an iPhone would be able to "detect an object via camera, RFID sensor or other means and have their device automatically identify and provide additional information on the object" looks to be potentially quite useful. In the patent background, Apple used the example of an art museum:

"...a user might take a photo of a piece of art and wish to have it automatically identified and additional information on it provided, or engage in an audio tour or podcast and wish to access additional content beyond that provided in the audio files."

Think of all the possible ways to leverage this technology -- other than trying to distinguish between two pieces of art, maybe you can use it to uncover the name of that actress in the recent blockbuster movie that you can't recall but swear looks familiar. Or perhaps you will be able to identify the name of a certain wallpaper color swatch -- and be able to access its brand, serial number and all retail locations withing a five mile radius. Well, both of those might be a bit far off -- not sure the iPhone camera can yet detect the subtle difference between eggshell and off-white or has facial recognition capabilities on par with those of 3VR, but you catch my drift. ZDNet also noted using the technology for price comparisons between retail products.

As far as facial detection developments, it seems that iPhone engineers are indirectly attempting to remedy the device's often woefully poor battery life. New patents look to "determine whether a user is passively interacting with the device" -- meaning not watching the TV show they've downloaded or listening to a song on iTunes -- and if so, turn on a screensaver of some type (similar to the setting on a normal laptop or desktop) to save energy. The iPhone would use its internal camera to detect a user's presence, and while the idea may be antiquated, bringing this technology to a mobile device will be welcomed with open arms.

Computer Vision Resarch Goes Virtual

Sometimes the real world just isn’t real enough. That’s often the case in computer vision application development where super smart PhDs seek to create algorithms and technologies to track and classify people or objects within a video stream. Believe it or not, some of the same neural networks that catch bad guys today got their start by tracking frantic scientists running around their labs, offices, and dorm rooms.

But ObjectVideo thinks there is a better way…at least to start. Using technology from the videogame Half Life 2 , they have built a Virtual Video Tool that can be used to create “virtual surveillance” cameras.

The ObjectVideo Virtual Video (OVVV) Tool generates realistic video from simulated cameras in an interactive virtual world. This tool is free and is based on a modification (aka 'mod') of Half-Life 2, a commercially available game from Valve Software. Our hope in distributing this tool is to stimulate computer vision research in areas that cannot rely on canned video (eg. active tracking) or when large quantities of ground truthed video is unavailable or impractical (multi-camera installations, public spaces, the list goes on!).

The fact that virtual cameras are generally thought to lack the video noise and other artifacts found in real-world cameras, doesn’t prevent this tool from providing real benefits to students and researchers. Today gaming engines are so realistic and of such high quality that the line between real and virtual is being blurred. And, as OV points out, virtual cameras provide another benefit that’s impossible to achieve with real world footage: ground truth data that can be incorporated into the training process. Because virtual cameras are built on models of scenes where ever person and object and color and angle are actually known, a researcher always knows, without guess or estimation, just how well their computer vision algorithms are deciphering a particular video stream.

Beyond that, ObjectVideo has created most of the environments, models, and camera option necessary to test every conceivable surveillance variation during the testing process. Even blur, noise, and even lens and PTZ effects can be simulated with relative ease.

Virtual surveillance video is not just a great tool for computer vision researchers, it’s also an incredibly interesting area of research in itself. The folks at Valve Software have my appreciation for opening their platform enough to enable this kind of work. But believe it or not, Valve’s Half Life 2 is already almost 4 years old. Maybe ObjectVideo’s next endeavor can be a Crysis mod. That would be something. And next year there will be something else…even better.

Video surveillance gets smarter in Verbania, Italy

Verbania, the capital of the province of Verbano-Cusio-Ossola, Italy, was created when the towns of Intra and Pallanza merged. As one of the most idyllic and famous tourist destinations on Lake Maggiore, the town relies heavily on holidaymakers to fill its streets and generate income. To ensure the safety of visitors and citizens, the town council decided to launch a community surveillance project based on a system of network cameras.

Monitors linked to the ten Sony SSNC-RX550 network cameras are installed in the Verbania Municipal Police control room, which is currently undergoing restructuring. Even so, the system does not require the intervention of dedicated security operatives. The human element only comes into play when real-time monitoring is needed (for example during a major event), or when an automatic alarm is triggered.

Today the Municipality of Verbania can be assured that those who commit crime will be identified, thanks to technology which directly recognizes objects and reads vehicle registration plates. In fact, the town's network cameras have been positioned so that they can monitor all arrival and escape points in every area of the town. Intelligent image analysis functions now enable allow the city to keep special areas such as no-stopping zones under control. Using these features, live images can be monitored in unattended mode until suspicious activity occurs, at which point the operator is proactively alerted to the threat by means of an appropriate alarm.