Experimental camera-based ERP system records 97.2% average accuracy
The two-year test is intended to validate a viable alternative to road pricing, not to replace the existing system.
An experimental camera-based road toll payment system, ERP X, demonstrated a 97.2% average accuracy in recognising Singapore vehicle licence plates during a two-year trial, even in challenging weather conditions. Conducted by Open Government Products (OGP), the trial involved 403 motorists passing 22 ERP gantry locations, with 63 roadside cameras capturing and charging their tolls through their smartphones.
The system's accuracy varied between 91% under rainy night-time conditions and 99.2% on bright, sunny days. OGP evaluated the camera-based technology as a potential alternative to the satellite-based ERP 2 system being phased in to replace gantry-based systems. The trial, costing around $4.4 million and with an estimated $2.7 million to replace existing gantry sites, aimed to assess the viability of the camera-based system before deciding on its nationwide rollout.
While the system's accuracy is promising, challenges remain in accurately recognising licence plates obscured by heavy rain, steep camera angles, or traffic congestion. OGP stressed that the experiment's findings are not a replacement for the existing system but an evaluation for future implementation.
Written by urgent.news from Straits Times's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
