Sensor Adaptation for Improved Semantic Segmentation of Overhead Imagery
This work addresses the challenge of accurate semantic segmentation in overhead imagery for applications like large-scale scene understanding, though it appears incremental as it builds on existing frameworks.
The paper tackles the problem of semantic segmentation in overhead imagery by proposing an algorithm based on DeepLab to refine small objects like vehicles and using sensor adaptation to augment training data for better generalization to new environments and sensors. They report results on several datasets and compare with state-of-the-art architectures.
Semantic segmentation is a powerful method to facilitate visual scene understanding. Each pixel is assigned a label according to a pre-defined list of object classes and semantic entities. This becomes very useful as a means to summarize large scale overhead imagery. In this paper we present our work on semantic segmentation with applications to overhead imagery. We propose an algorithm that builds and extends upon the DeepLab framework to be able to refine and resolve small objects (relative to the image size) such as vehicles. We have also investigated sensor adaptation as a means to augment available training data to be able to reduce some of the shortcomings of neural networks when deployed in new environments and to new sensors. We report results on several datasets and compare performance with other state-of-the-art architectures.