In this project we tackle the problem of image segmentation in aerial data, where the goal is to draw accurate segmentation masks unto buildings. We utilize an existing machine learning model, Mask R-CNN, and attempt to optimize the mask loss function, such as to improve the accuracy of the segmentation masks. We therefore propose and implement two different loss functions for the model, to measure their effects on performance, specifically when applied on our dataset. We also produce a dataset, derived from aerial photographical data and LiDAR data. We find that the Edge Aware loss function results in a noteworthy improvement in output masks.