BATT Vision utilizes high-resolution, 360-degree cameras, along with action cameras, a GPS unit, and accelerometers to robustly capture pavement conditions. GPS-labeled video frames are analyzed by proprietary software to extract images at specified intervals to remove duplication and sample the pavement network continuously. The result is a far superior analysis than commonly used data collection vehicles can produce, and a more consistent analysis than subjectively based, feet-on-the-ground surveys.

In contrast to older analysis methods, BATT Vision utilizes a suite of software that applies machine learning and deep learning techniques for detecting distress in both flexible and rigid pavements. The BATT Team can then use the system’s algorithms to detect the type, extent and severity of the distresses and calculate a PCI using standardized equations. On a scale from 0 to 100, a PCI value of 100 would signify a superior pavement condition.

The system provides reports that allow engineers, agencies, and owners to fully understand their pavements. It generates performance condition index (PCI) data that can be used to evaluate and fine-tune pavement treatment decisions over the life of the pavement. The report provides access to an online data visualization tool that includes distress photos and graphs.