Learning to Segment Objects of Various Sizes in VHR Aerial Images
The goal of semantic segmentation is to assign semantic categories to each pixel in an image. In the context of aerial images, it is very important to yield dense labeling results, which can be applied for land use and land change detection. But small and large objects are difficult to be labeled correctly simultaneously in a single framework. Convolutional neural networks (CNN) can learn rich features and has achieved the state-of-the-art results in image labeling. We construct a novel CNN architecture: Pyramid Atrous Skip Deconvolution Network (PASDNet), which combines features of different levels and scales to learn small and large objects. Secondly, we employ a weighted loss function to overcome class imbalance problem, which improves the overall performance. Our proposed framework outperforms the other state-of-art methods on a public benchmark.
KeywordsConvolutional neural networks (CNNs) Semantic segmentation Very high resolution aerial images
The work was supported by the National Key R&D Program of China under the Grant 2017YFC1405600, the National Natural Science Foundation of China under the Grant 61671037 and the Open Research Fund of State Key Laboratory of Space-Ground Integrated Information Technology under grant NO.2016_SGIIT_KFJJ_YG_03.
- 1.Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 60(2), 1097–1105 (2012)Google Scholar
- 3.Mnih, V.: Machine learning for aerial image labeling. Ph.D. thesis, 109 (2013)Google Scholar
- 4.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR, pp. 1–14 (2015)Google Scholar
- 5.Szegedy, C., et al.: Going deeper with convolutions, pp. 1–12 (2014)Google Scholar
- 6.Wu, S., Zhong, S., Liu, Y.: Deep residual learning for image steganalysis. Multimed. Tools Appl. 77, 1–17 (2017)Google Scholar
- 7.Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2014)Google Scholar
- 13.Penatti, A.B., Nogueira, K., Santos, J.A.: Do deep features generalize from everyday objects to remote sensing and aerial scenes domains?, pp. 44–51 (2015)Google Scholar
- 14.Castelluccio, M., Poggi, G., Sansone, C., Verdoliva, L.: Land use classification in remote sensing images by convolutional neural networks, pp. 1–11 (2015)Google Scholar
- 17.Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding (2014)Google Scholar