A new audio surveillance system could help fight crime in the city and protect kilometers of unmanned borders. Software developed by Ted Berger, director of the University of Southern California Center for Neural Engineering, can be trained to recognize and distinguish sounds that are indicators of a security breach or a safety hazard, such as a gunshot or the rattle of someone climbing a chain-link fence. The software is based on mathematical models that mimic the way the brain interprets sound, but it can distinguish between two similar sounds far more precisely than the human ear. This fall, Oak Brook, IL-based Safety Dynamics plans to implement the software in surveillance devices that monitor urban activity. Mounted on streetlight poles, the devices will listen for gunshots, then guide surveillance cameras toward the source of the sounds. Berger says the technology can also be used for large-scale security; an array of detectors placed along a deserted border, for example, could listen for footfalls or whispers, painting a scene solely on the basis of acoustic information. The detectors could then notify a central location of any suspicious activity.
Embracing CX in the metaverse
More than just meeting customers where they are, the metaverse offers opportunities to transform customer experience.
Identity protection is key to metaverse innovation
As immersive experiences in the metaverse become more sophisticated, so does the threat landscape.
The modern enterprise imaging and data value chain
For both patients and providers, intelligent, interoperable, and open workflow solutions will make all the difference.
Scientists have created synthetic mouse embryos with developed brains
The stem-cell-derived embryos could shed new light on the earliest stages of human pregnancy.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.