Deep learning techniques for building density estimation from remotely sensed imagery

This thesis is about point-wise estimation of building density on the remote sensing optical imageries by applying deep learning methods. The goal of the project is to reduce mean square error of the estimated density by applying architectural modifications on the deep learning network and using augmented training data. Our results show that fast and accurate building density estimation is possible by using vanilla CNNs. Sigmoid layer addition, simplification of the network for small dataset and data augmentation improves accuracy in the regression. Data augmentation is the most effective method to reduce RMSE in this thesis.