Anyone who has watched CSI or any of the Law & Order franchises has no doubt witnessed a well groomed police technician magically clean up fuzzy security camera vision, thereby providing the detectives with the vital number plate or the face of a criminal at the push of a button. The truth is, of course, far removed from such TV fantasy – at least it has been until now. A new video “perfection tool” developed by researchers at Tel Aviv University (TAU) helps investigators enhance raw video images to improve the quality at which the images were originally recorded.

The new invention enhances the resolution of raw video images from security cameras, military binoculars, and standard personal-use video cameras, improving the quality of the originally recorded or transmitted images. It can also be used with live video or recordings, in both color and black-and-white.

To develop the new tool Prof. Leonid Yaroslavsky and his colleagues from TAU exploited the fact that most parts of a video scene remain still. Although this is true, a major challenge in video analysis is that images of objects become distorted over long distances due to variations in the air that can affect our sight and the "sight" of a camera. In the language of optical science, this is known as a "turbulent atmosphere" and can cause a critical image of a person or object to become unstable and almost impossible to identify with any amount of accuracy.

Using specially designed algorithms, the team built a software application that lets cameras and video analysis equipment stabilize images, allowing objects that are really moving to be distinguished from chaotic atmospheric changes. This can mean the difference between "seeing" trees blowing in the wind and finding a terrorist hiding in those trees.

Prof. Yaroslavsky believes the technology will not only increase the odds of identifying suspects in court, but could also save bandwidth and time in sending large video files over the Internet. Smaller and lower-resolution files could be sent to be enhanced at their destination. He went on the say that, once a commercial partner is found, the device can be integrated into existing technology within a matter of months.

Maybe someone should have told him that CSI and Law & Order have been using similar technology for years.

The TAU team’s findings were published in Optical Letters and the Journal of Real Time Image Processing.