VisionTrack, the AI video telematics and connected fleet data specialist, has introduced a new sophisticated AI-powered post-analysis solution. NARA (Notification, Analysis and Risk Assessment) will revolutionise how vehicle camera footage is assessed and help vehicle operators dramatically reduce road deaths and injuries.
‘Our cloud-based NARA software is a game changer in the world of video telematics as it will help save time, costs and most importantly, lives, by providing proactive risk intervention and accurate incident validation,’ explains Richard Kent, President of Global Sales at VisionTrack. ‘NARA proactively removes false positives and monitors driver behaviour without the need for human involvement. Commercial fleets can experience hundreds of triggered daily events with traditional video telematics solutions, and the new solution enables them to deliver more efficiently while not compromising road safety.’
NARA is device agnostic, so it can be integrated with existing connected camera technology – whether VisionTrack or third-party hardware – and adds another robust layer of analysis to AI vehicle cameras, installed with edge-based AI technology, that are often limited by the processing capacity of the device.
Step forward for video telematics
NARA represents a huge step forward for video telematics as it uses ground-breaking computer vision models with sensor fusion to assess footage of driving events, near misses and collisions. This ensures the review process is manageable and timely while eliminating human availability or error. Vehicle operators can best use video telematics insight to protect road users better and help prevent collisions.
During the testing phase, an 1100-strong logistics fleet was found to generate, on average, 2,000 priority videos a week, typically taking someone over 8 hours to review. NARA reduced the time needed to review events that require human validation to just minutes per day. As a result, the company is targeting more efficient risk management, supporting its road safety strategy.
Advanced object recognition uses deep learning algorithms to identify different types of vehicles, cyclists and pedestrians automatically. With incredibly high accuracy levels, it can distinguish between collisions, near misses and false positives that can be generated by harsh driving, potholes or speed humps. The software will also include Occupant Safety Rating that uses a range of parameters to calculate the percentage probability of injury and immediately identify if a driver needs assistance.
‘As a true advocate of road safety, having already pledged our support to the global initiative Vision Zero, we are passionate about helping the industry achieve its target of eliminating all traffic fatalities. Our vision is to create a world where all road users are kept safe from harm. We are embracing the latest advances in machine learning and computer vision to enhance further our industry-leading IoT platform, Autonomise.ai, and AI video telematics solutions,’ concludes Richard.