Skip to main content

Software could determine where a video was shot, based on scenery and ambient sound

Sometimes, a posted video is the only clue to the whereabouts of a missing person, or a terrorist group. Unfortunately, unless that video has already been geo-tagged, it can often be very difficult to tell where it was shot. Now, however, scientists have created algorithms that can determine a video's location by comparing its background imagery and audio to that of thousands of other videos.
The researchers, from Spain's Ramón Llull University, utilized the existing MediaEval Placing Task database. It's a collection of videos and photos from known locations, used for developing geolocation software.
Given that the videos being scrutinized presumably wouldn't show well-known landmarks, the algorithms instead look for distinct images in seemingly generic scenes (such as streets or wilderness areas) that have a match in the database.
Random ambient audio also plays a key role. "The acoustic information can be as valid as the visual and, on occasions, even more so when it comes to geolocating a video," said researcher Xavier Sevillano. "In this field we use some physics and mathematical vectors taken from the field of recognition of acoustic sources, because they have already demonstrated positive results."
So far, the system has been tested by comparing sample videos to approximately 10,000 other clips already in the MediaEval database. It was able to geolocate three percent of those samples to within a 10-km (6.2-mile) radius of where they were actually shot, and one percent to within one kilometer (0.6 mile).
While those figures obviously leave a lot of videos still unlocated, the scientists believe that the success rate should be much higher if the database is expanded to include many more clips. Additionally, even in its present form, the technology is claimed to be more accurate than other approaches used on the database.
Source: FECYT

Comments

Popular posts from this blog

Solar car hits U.S. in round-the-world jaunt

Last October, the SolarWorld GT solar-powered car set out from Darwin, Australia on a drive around the world. It has since driven 3,001 kilometers (1,865 miles) across Australia, logged 1,947 km (1,210 miles) crossing New Zealand and been shipped across the Pacific Ocean. This Friday, it will embark on the U.S. leg of its journey, as it sets out across America from the University of California, Santa Barbara.   The SolarWorld GT is the result of a collaboration between solar panel manufacturer SolarWorld, and Bochum University of Applied Sciences in Germany. The four-wheeled, two-door, two-seat car gathers solar energy through photovoltaic panels built into its roof, with its solar generator offering a peak performance of 823 watts. Custom hub motors are located in both of the front wheels. The vehicle manages an average speed of 50 km/h (31 mph), with a claimed top speed of 100 km/h (62 mph). In order to demonstrate that solar powered cars needn't be a radical...

Biocomputer, Alternative To Quantum Computers

A team of international scientists from Canada, the U.K., Germany, the Netherlands and Sweden announced Friday that they had developed a model biological supercomputer capable of solving complex mathematical problems using far less energy than standard electronic supercomputers. The model “biocomputer,” which is roughly the size of a book, is powered by Adenosine triphosphate (ATP) — dubbed the “molecular unit of currency.” According to description of the device, published in the  Proceedings of the National Academy of Sciences , the biocomputer uses proteins present in all living cells to function. It uses a strategy similar to that of quantum computers, which use qubits — the quantum computing equivalents of bits — to perform “parallel computation,” wherein  computers are able to process information quickly and accurately by performing several calculations simultaneously, rather than sequentially. In the case of the biocomputer, the qubits are replaced with ...

Qualcomm showcases the Snapdragon S4 ahead of Mobile World Congress

We’ve already heard about Qualcomm’s latest processor, the Snapdragon S4 , which will be quad-core and utilize LTE. Qualcomm took the time to give us some details ahead of Mobile World Congress. The new SoC now supports up to three cameras (two in the back for 3D and one front-facing), 20-megapixels, and recording video at 1080p (30fps). We can also expect zero shutter lag, 3A processing (autofocus, auto exposure and auto white balance), and improved blink/smile detection, gaze estimation, range finding and image stabilization. Last but not least, it supports gesture detection/control, augmented reality , and computer vision (via Qualcomm’s FastCV). Hit the break for a couple of videos featuring image stabilization and gestures.