LULC Segmentation of RGB Satellite Image Using FCN-8

This work presents use of Fully Convolutional Network (FCN-8) for semantic segmentation of high-resolution RGB earth surface satel-lite images into land use land cover (LULC) categories. Specically, we propose a non-overlapping grid-based approach to train a Fully Convo-lutional Network (FCN-8) with vgg-16 weights to segment satellite im-ages into four (forest, built-up, farmland and water) classes. The FCN-8 semantically projects the discriminating features in lower resolution learned by the encoder onto the pixel space in higher resolution to get a dense classi cation. We experimented the proposed system with Gaofen-2 image dataset, that contains 150 images of over 60 di erent cities in china. For comparison, we used available ground-truth along with images segmented using a widely used commeriial GIS software called eCogni-tion. With the proposed non-overlapping grid-based approach, FCN-8 obtains signi cantly improved performance, than the eCognition soft-ware. Our model achieves average accuracy of 91.0% and average Inter-section over Union (IoU) of 0.84. In contrast, eCognitions average accu-racy is 74.0% and IoU is 0.60. This paper also reports a detail analysis of errors occurred at the LULC boundary.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Antonio J. Plaza,et al.  Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[3]  Antonio J. Plaza,et al.  Semisupervised Hyperspectral Image Segmentation Using Multinomial Logistic Regression With Active Learning , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Xia Li,et al.  Integration of Convolutional Neural Networks and Object-Based Post-Classification Refinement for Land Use and Land Cover Mapping with Optical and SAR Data , 2019, Remote. Sens..

[6]  Michele Volpi,et al.  Dense Semantic Labeling of Subdecimeter Resolution Images With Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Gui-Song Xia,et al.  Learning Transferable Deep Models for Land-Use Classification with High-Resolution Remote Sensing Images , 2018, ArXiv.

[8]  Chokri Ben Amar,et al.  Deep learning for semantic segmentation of remote sensing images with rich spectral content , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[9]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.