Introduction This article summarizes and gives an in depth explanation on the paper by Thomas Roddick and Roberto Cipolla, ‘Predicting Semantic Map Representations from images using Pyramid Occupancy Networks’ roddick2020predicting. The authors present a novel approach for creating a orthographic top down map of the environment based on a single or series of monocular images. This approach uses a wide variety of techniques and incorporates them into a single end to end trainable machine learning model.

SVM Introduction Support vector machines (in short SVMs) are a binary classification machine learning algorithm. SVMs try to find an $n$-dimensional hyperplane, separating two classes from each other. The hyperplane should maximize the margin between both classes, because of this the generalization potential of SVMs is superior to most other similar classification algorithms. This makes support vector machines a very popular choice for a wide range of use cases. SVMs use a linear function $f(x) = wx+b$ that should separate two classes ($-1$ and $1$).