Written Answer · 2026-10-06 · Parliament 15
AI-detected Bus Lane Offence Accuracy Assessment, Officer Review Requirements and Motorist Appeal Process
Mr Low Wu Yang Andre asked the Minister for Transport how LTA calculated the reported 90% trial accuracy of its AI bus lane encroachment detection system, whether every AI-detected offence would be reviewed by an officer before enforcement, and how motorists could challenge errors. Mr Jeffrey Siow replied that the system analysed over 800 hours of bus camera footage over three months, captured more than 450 encroachments, correctly detected 415 (about 90%) with 257 false positives, and that all AI detections are still manually reviewed before enforcement, with appeals assessed by human officers as with any other traffic offence.
Why it matters
In LTA's trial the AI correctly detected 415 bus lane encroachments and produced 257 false positives; every detection is still reviewed by an officer before enforcement, and appeals are decided by people.
Key Points
- • The bus lane AI system analysed over 800 hours of bus camera footage over three months.
- • It captured more than 450 encroachments in total and correctly detected 415, about 90% accuracy.
- • The system also produced 257 false-positive cases.
- • LTA will keep working with the vendor to refine the tools and reduce false positives, aiming to reduce human oversight over time.
- • AI-detected bus lane violations are still manually reviewed before enforcement, and appeals continue to be assessed by human officers.
The Government maintains human officer review of every AI-detected violation and all appeals for now, and did not commit to a timeline for removing human oversight, only saying this will be reduced as the technology matures.
Mr Low Wu Yang Andre's concern was how the AI's accuracy rate is calculated, its error rates, and whether motorists have an effective way to challenge wrong detections.
This shows Singapore taking a gradual approach to deploying AI in enforcement, keeping human review as a safeguard for now and only expanding the AI's role as accuracy improves.
"Meanwhile, bus lane violations detected by the AI system will still be manually reviewed before enforcement action is taken."
Participants (2)
- Low Wu Yang Andre
- Mr Jeffrey Siow
Original Text (English)
SPRS Hansard · Fetched: 2026-10-21
66 Mr Low Wu Yang Andre asked the Minister for Transport regarding LTA's planned AI system using bus cameras to detect bus lane encroachments (a) how its reported 90% trial accuracy is calculated, including sample size and false-positive and false-negative rates by intended use; (b) whether every AI-detected traffic offence will be reviewed by an authorised officer before enforcement; and (c) how motorists can challenge an erroneous detection.
Mr Jeffrey Siow : The artificial intelligence (AI) systems were trialled across a variety of use-cases, including to detect road defects, road works and bus lane encroachments. For bus lanes, the systems analysed over 800 hours of bus camera footage over three months, which captured more than 450 encroachments in total. The AI systems correctly detected 415 cases, or about 90% of encroachments. They also detected 257 cases which turned out to be false positives.
The Land Transport Authority (LTA) will continue to work with the vendor to refine these tools, including to reduce the number of false positives. In time, we will reduce the need for human oversight. Meanwhile, bus lane violations detected by the AI system will still be manually reviewed before enforcement action is taken. Motorists can contest or appeal a notice, similar to any other traffic offence today. These contests and appeals will continue to be assessed by human officers.
As the technology matures and accuracy improves, LTA will expand the use of bus cameras and AI across more public bus services to safeguard bus lanes and maintain bus speeds and reliability.