Vision applications often rely on object detectors, which determine the nature and location of objects in a scene. But many vision applications require a different type of visual understanding: semantic segmentation. Semantic segmentation classifies each pixel of an image, associating each pixel with an object class (e.g., pavement, pedestrian). This is required for separating foreground objects from background, for example, or for identifying drivable surfaces for autonomous vehicles. A related type of functionality is object segmentation, which associates each pixel with a specific object (e.g., pedestrian #4), and panoptic segmentation, which combines the functionality of semantic and instance segmentation. In this talk, we’ll introduce deep learning-based semantic, instance and panoptic segmentation. We’ll explore the network topologies commonly used and how they are trained. We’ll discuss metrics for evaluating segmentation algorithm output, and considerations when selecting segmentation algorithms. Finally, we’ll identify resources useful for developers getting started with segmentation.