Open Set Semantic Segmentation of Remote Sensing Images

Abstract

The development of computational vision approaches that exploit satellite imagery is relatively recent, mainly due to the limited availability of this type of image. In the area of remote sensing, applications that employ computational vision techniques are modeled for classification in closed set scenarios. However, the world is not purely closed set, many scenarios present classes that are not previously known by the algorithm, an open set scenario. Thus, the main objective of this paper is the study and development of semantic segmentation techniques considering the open set scenario applied to remote sensing images. Focusing on this problem, this is the first work to study and develop semantic segmentation techniques for open set scenarios applied to remote sensing images. The main contributions of this paper are: 1) a discussion of related works in open set semantic segmentation, showing evidence that these techniques can be adapted for open set remote sensing tasks; 2) the development and evaluation of four novel approaches for open set semantic segmentation. Our methods yielded competitive results when compared to closed set methods for the same dataset