SDFCNv2: An Improved FCN Framework for Remote Sensing Images Semantic Segmentation

• Published in: Remote sensing (Basel, Switzerland) Switzerland), 2021-12, Vol.13 (23), p.4902
• Main Authors: Chen, Guanzhou, Tan, Xiaoliang, Guo, Beibei, Zhu, Kun, Liao, Puyun, Wang, Tong, Wang, Qing, Zhang, Xiaodong
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Computer vision; convolutional neural networks (CNNs); Datasets; deep learning; Design; fully convolutional networks (FCNs); Image analysis; Image processing; Image segmentation; Mathematical models; Neural networks; Parameters; Receptive field; Remote sensing; SDFCN; Semantic segmentation; Semantics; Stochasticity
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs13234902

Semantic segmentation is a fundamental task in remote sensing image analysis (RSIA). Fully convolutional networks (FCNs) have achieved state-of-the-art performance in the task of semantic segmentation of natural scene images. However, due to distinctive differences between natural scene images and remotely-sensed (RS) images, FCN-based semantic segmentation methods from the field of computer vision cannot achieve promising performances on RS images without modifications. In previous work, we proposed an RS image semantic segmentation framework SDFCNv1, combined with a majority voting postprocessing method. Nevertheless, it still has some drawbacks, such as small receptive field and large number of parameters. In this paper, we propose an improved semantic segmentation framework SDFCNv2 based on SDFCNv1, to conduct optimal semantic segmentation on RS images. We first construct a novel FCN model with hybrid basic convolutional (HBC) blocks and spatial-channel-fusion squeeze-and-excitation (SCFSE) modules, which occupies a larger receptive field and fewer network model parameters. We also put forward a data augmentation method based on spectral-specific stochastic-gamma-transform-based (SSSGT-based) during the model training process to improve generalizability of our model. Besides, we design a mask-weighted voting decision fusion postprocessing algorithm for image segmentation on overlarge RS images. We conducted several comparative experiments on two public datasets and a real surveying and mapping dataset. Extensive experimental results demonstrate that compared with the SDFCNv1 framework, our SDFCNv2 framework can increase the mIoU metric by up to 5.22% while only using about half of parameters.