Improving Car Detection from Aerial Footage with Elevation Information and Markov Random Fields

Convolutional neural networks are often trained on RGB images because it is standard practice to use transfer learning using a pre-trained model. Satellite and aerial imagery, however, usually have additional bands, such as infrared or elevation channels. Especially when it comes to detection of small objects, like cars, this additional information could provide a significant benefit. We developed a semantic segmentation model trained on the combined optical and elevation data. Moreover, a post-processing routine using Markov Random Fields was developed and compared to a sequence of pixel-wise and object-wise filtering steps. The models are evaluated on the Potsdam dataset on the pixel and object-based level, whereby accuracies around 90% were obtained.