Researchers from the National University of Singapore and Yonsei University in South Korea have devised a mobile application that uses smartphones’ time-of-flight (ToF) sensor to find tiny spy cameras hidden in everyday objects.
The app is more successful at detecting hidden cams than existing state-of-the-art commercial hidden camera detectors (CC308+, K18) and much more successful than the human eye/brain.
How the app works
Tiny cameras concealed in sensitive locations – hotel rooms, bathrooms, AirBnb rentals, etc. – are becoming a significant problem. They can be bought online for a pittance, and are so small that they are difficult to spot with the naked eye, especially in cluttered rooms.
The researchers’ quest to create a more effective method of detecting hidden spy cams has resulted in the creation of the LAPD (Laser-Assisted Photography Detection) app, which can work on any smartphone with a ToF sensor. They tested the app on Samsung Galaxy S20+, S20 Ultra 5G, and Note 10+ smartphones.
“During the scan process, the ToF sensor emits laser pulses and receives the reflected light off of the object – such as the water bottle – and its surroundings. Specifically, the hidden camera embedded in the object reflects the incoming laser pulses at a higher intensity than its surroundings due to an effect called lens-sensor retro-reflection,” they explained.
“This occurs when almost all light energy impacting an object is reflected directly back to the source. These unexpectedly high-intensity reflections from hidden cameras cause certain regions of the ToF sensor to be “saturated” and appear as black pixels. LAPD processes these saturated areas to automatically identify the hidden camera and its location and displays it on the user’s smartphone screen.”
To weed out false positives due to the different reflectivity of various objects, the different capabilities of ToF sensor hardware, and certain limitations of reflections’ optical properties, the researchers used augmented reality to guide the user to move closer and further away from the object and various filters (including deep-learning-based ones).
A promising solution
While this solution is definitely promising, current limitations to its widespread, easy use include factors such as the overall (un)availability of ToF sensors (which are expected to become ubiquitous in the next five years) and the fact that LAPD requires users to scan only one object at a time – and it takes approximately one minute to scan one object.
On the other hand, the solution’s accuracy could be further augmented through the use of smartphone’s flashlight and RGB cameras and its use can be complemented by WiFi-based solutions to pinpoint the general locations where the cameras are hidden.
The researchers plan to open source the app, so that people can help make it better; to implement some of the aforementioned complementary technologies; and then finally to release it to the public, so that anyone who has a smartphone with a ToF sensor can freely use it to find hidden cameras.