Visual Perception for Self-Driving Cars! Part4: Road Segmentation
<p>Segmentation is the task of clustering elements of an image corresponding to the same object class. It is also known as <a href="https://en.wikipedia.org/wiki/Image_segmentation" rel="noopener ugc nofollow" target="_blank">pixel-level classification</a>. It entails partitioning images (or video frames) into multiple segments of objects. Depending on the classification nature, image segmentation is divided into two categories: <strong>semantic segmentation</strong> (pixels with semantic labels) and <strong>instance segmentation</strong> (partitioning of individual objects). For example, in an image with a bunch of cars: while semantic segmentation label all the objects as car objects, instance segmentation can classify the separate instances where an object appears. In our today’s blog, we will use semantic segmentation.</p>
<p><a href="https://medium.com/@shahrullo/visual-perception-for-self-driving-cars-part4-road-segmentation-c3b48d2ba8c9"><strong>Visit Now</strong></a></p>