CNNs Fusion for Building Detection in Aerial Images for the Building Detection Challenge
This is an incremental improvement for aerial image analysis in urban planning or disaster response.
The authors tackled building detection in aerial images by enhancing a SpaceNet Challenge solution with a new CNN fusion strategy, achieving 1-7% segmentation improvements across different cities.
This paper presents our contribution to the DeepGlobe Building Detection Challenge. We enhanced the SpaceNet Challenge winning solution by proposing a new fusion strategy based on a deep combiner using segmentation both results of different CNN and input data to segment. Segmentation results for all cities have been significantly improved (between 1% improvement over the baseline for the smallest one to more than 7% for the largest one). The separation of adjacent buildings should be the next enhancement made to the solution.