The goal of machine learning is to teach a program to learn by example. Our machine learning algorithms are developed to identify different characteristics of the road by looking at labeled image data.
What is labeled image data?
RoadBotics personnel draw on road images with a digital paintbrush in which the different colors represent different distress types – for example, one for unsealed cracks, another for alligator cracks, etc. – until we have every distress and object in the image categorized. In addition, each image is assigned a rating by a road expert. Therefore each image has both distresses labeled as well as the final desired rating.
What happens after?
When we have many thousands of these images in a variety of these conditions, we feed them into an Artificial Deep Neural Network (ADNN) – one of many types of machine learning programs. The ADNN is designed by our Data Scientists to take all the labeled image data and produce an algorithm that when given a new image the ADNN has never seen before, it will also label the image just like the RoadBotics personnel would have had they labeled that same image – most importantly, that the final rating produced by the ADNN is the same as the original rating label. This is called training.
It is an extremely complex process involving advanced processors and millions and millions of parameters. To learn more about our process read this blog post here.