New AI Technology Detects Spy Cams in 5 Seconds for About 10,000 Won

The Korea Advanced Institute of Science and Technology (KAIST) announced that it has developed an artificial intelligence (AI) technology that can detect hidden illegal filming cameras using only a smartphone and a light-emitting diode (LED) device.

The SweepLED technology, developed by a research team led by Professor Han Jun from the School of Computing, involves analyzing reflection change patterns appearing on the surface of an object by changing only the direction of the LED light while fixing a smartphone camera.


While reflection points on general glossy objects change position or disappear depending on the lighting direction, camera lenses feature uniquely distorted reflection shapes due to their internal lens, aperture, and image sensor structures.

The research team trained a deep learning-based image analysis model on these time-dependent reflection change patterns to distinguish camera lenses.

Whereas conventional detection methods relied on the user's naked eye to simply look for "bright spots," SweepLED differentiates itself by having AI comprehensively analyze the movement and shape changes of reflections appearing across multiple lighting angles to identify hidden cameras.

Through this, it is possible to more reliably detect camera lenses hidden inside various objects commonly found in accommodation spaces, such as chargers, desk clocks, remote controls, and ornaments.

When the research team evaluated its performance on 30 objects found in real-world environments, it recorded a detection accuracy of about 94%.

It was also confirmed that inspecting a single object takes less than 5 seconds.

The research team explained that because the core components of the LED case that attaches to a smartphone cost less than $7 (approx. 10,000 won), the technology could potentially be commercialized in the future as a budget-friendly detector in the form of a smartphone accessory or a consumer product.

Professor Han Jun said, "Illegal filming cameras are a serious threat to personal safety and privacy in everyday spaces," adding, "This is significant in that it demonstrates the potential of a practical detection technology that allows non-experts to easily use it by combining smartphone-based low-cost hardware with artificial intelligence analysis."

(Photo courtesy of KAIST, Yonhap News)
※ Please note: This article was translated by AI and may contain errors.