Google Pixel Smartphones and AI Revolutionize Subway Track Inspections in New York City

The Metropolitan Transportation Authority (MTA) of New York City is currently experimenting with the Google Pixel as a diagnostic tool, using the smartphones to identify defects in subway tracks.

In a project known as TrackInspect, Google Pixel phones are attached to subway cars, utilizing built-in microphones and motion sensors to capture vibrations and sound patterns. These sounds can indicate areas of the track that require maintenance.

Once the data is collected, it is uploaded to Google Cloud, where artificial intelligence analyzes it to highlight segments that need attention.

«This process works as follows: an agent identifies a sound segment with significant vibration or noise, and then our inspectors verify this data by physically inspecting the tracks,» explained Robert Sarno, Assistant Chief Track Inspector at MTA New York.

According to him, MTA specialists provide feedback to the AI regarding which of the flagged segments truly represent track defects. Throughout the TrackInspect pilot, the MTA gathered 335 million sensor readings and 1,200 hours of audio recordings. Impressively, 92% of the defects detected by the system were later confirmed by human inspectors.