This course on "Semantic Segmentation Tutorial" will help you to master all the concepts of semantic segmentation. Semantic segmentation is very crucial in self-driving cars and robotics because it is important for the models to understand the context in the environment in which they're operating. You may be familiar with image classification- the network assigns a label or class to an input image, objects’ shape, sorting pixels with respect to objects etc. In this scenario, you will want to attain image segmentation that includes labeling each pixel of the image. Therefore, in simple terms, image segmentation involves training the neural network to output a pixel-wise mask of the image. This allows you to understand images at a pixel level - at a much lower level. You will find many image segmentation applications like in medical imaging, self-driving cars, and satellite imaging to name a few Semantic segmentation algorithms are super powerful and have many use cases, including self-driving cars — and in today’s video, we will be covering the certain application of Semantic Segmentation along with the Introduction to U-Net. At the end of the video, we will also be showing a demo of Semantic Segmentation.

Read More