Object recognition in hyperspectral images using Binary Partition Tree representation

Silvia Valero, Philippe Salembier, Jocelyn Chanussot

Abstract: Highlights•New object detection technique by using hierarchical region-based image representations.•Binary Partition Tree is proposed as a structured search space in order to incorporate the spectral and the spatial information.•The strategy is applied on several datasets of hyperspectral images of urban areas.•The obtained results show the interest of studying the objects of the scene with a region-based perspective.