Homelessness is a complex social problem and there have been limited attempts to use machine learning algorithms to understand the various issues that public health agencies would like to solve. For instance, it is important for the policy makers to know where homeless populations live so that they can provide necessary services accordingly. This article presents a satellite image tent-detection solution with three deep learning methods that utilize transfer learning from the ResNetV2, InceptionV3, and MobileNetV2 models, trained on ImageNet, attached to a unique architecture referred to as "TentNet". The performance of these models are first shown in detecting planes and ships within satellite imagery in previously defined datasets as a baseline. Then, a new dataset is created from a compilation of tents from the xView project to use for testing, along with another dataset of synthetic images from the generative adversarial networks StyleGAN2 and DCGAN for training. After training on a dataset containing only synthetic images for the tents class, the ResNetV2 architecture achieved the highest accuracy of 73.68% when testing on the real satellite imagery.