CNNs Fusion for Building Detection in Aerial Images for the Building Detection Challenge

Rémi Delassus (1, 2) , Romain Giot (1)

1 LaBRI - Laboratoire Bordelais de Recherche en Informatique
2 Qucit

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.

Mots clés: Computer vision; Satellite images analysis; Ensemble modeling

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Rémi Delassus, Romain Giot. CNNs Fusion for Building Detection in Aerial Images for the Building Detection Challenge. Conference on Computer Vision and Pattern Recognition Workshops, Jun 2018, Salt Lake City, United States. ⟨hal-01824749⟩