Councils have been using technology to inspect roads for years. Laser Crack Measurement, HD Video Camera, Ground Penetrating Radar, and more. The problem with these methods is that their cost and time to deliver data preclude them from being utilised with a higher frequency than every 6 months. In many cases they may only be done inline with Councils asset revaluations.
How do councils achieve these low-cost, high-frequency inspections? Clarence Valley has invested in using Computer Vision and Machine Learning to automatically detect defects and council issues in the road corridor. Clarence Valley Council has chosen Retina Visions (Data Provider for TfNSW / IPWEA Asset AI) to provide its cameras and machine learning technology to capture its defects and automatically, in near real time, feed them into its Asset Management System (TechnologyOne), where they can be actioned.
Retina Visions' solution allows Council the flexibility to mount the cameras on vehicles already travelling its road network (waste trucks, street sweepers etc), dedicated inspector vehicles and even e-bike for the footpath network.
By adopting this advanced method of road and footpath inspection, staff can make more informed decisions on intervention levels along with how, when, and where to undertake maintenance works on the network. This approach boosts the amount of maintenance performed, improving the road network’s efficiency and safety for drivers.
More frequent road inspection is also key to substantiating damage from the ever-increasing threat of natural disasters.
The AI technology has been developed to quarantine your road condition data and imagery to provide councils with pre-condition evidence to efficiently support the evidence requirements of the Disaster Recovery Funding Arrangements (DRFA). After the disaster event occurs, councils can use Retina Visions’ technology to quickly assess their network and rapidly compare pre-condition data against damage evidence to support all subsequent claims.