Abstract
Object classification from images is among the many practical examples where deep learning algorithms have successfully been applied. In this paper, we present an improved deep convolutional encoder-decoder network (DCED) for segmenting road objects from aerial images. Several aspects of the proposed method are enhanced, incl. incorporation of ELU (exponential linear unit)—as opposed to ReLU (rectified linear unit) that typically outperforms ELU in most object classification cases; amplification of datasets by adding incrementally-rotated images with eight different angles in the training corpus (this eliminates the limitation that the number of training aerial images is usually limited), thus the number of training datasets is increased by eight times; and lastly, adoption of landscape metrics to further improve the overall quality of results by removing false road objects. The most recent DCED approach for object segmentation, namely SegNet, is used as one of the benchmarks in evaluating our method. The experiments were conducted on a well-known aerial imagery, Massachusetts roads dataset (Mass. Roads), which is publicly available. The results showed that our method outperforms all of the baselines in terms of precision, recall, and F1 scores.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, J., Song, J., Chen, M., Yang, Z.: Road network extraction: a neural-dynamic framework based on deep learning and a finite state machine. Int. J. Remote Sens. 36, 3144–3169 (2015)
Muruganandham, S.: Semantic segmentation of satellite images using deep learning. M.S. thesis, Czech Technical University in Prague and Luleå University of Technology (2016)
Saito, S., Yamashita, T., Aoki, Y.: Multiple object extraction from aerial imagery with convolutional neural networks. J. Imaging Sci. Technol. 60(1), 1–9 (2016)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: International Conference on Computer Vision (2015)
Badrinarayanan, V., Handa, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. arXiv:1505.07293v1 (2015)
Mnih, V.: Machine learning for aerial image labeling. Ph.D. thesis, University of Toronto (2013)
Maurya, R., Gupta, P.R., Shukla, A.S.: Road extraction using k-means clustering and morphological operations. In: International Conference on Image Information Processing, pp. 708–714 (2011)
Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. arXiv:1511.00561v3 (2016)
Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). In: 4th International Conference on Learning Representations (2016)
Xu, G., Zhang, D., Liu, X.: Road extraction in high resolution images from google earth. In: 7th International Conference on Information and Communication Systems, pp. 556–560 (2009)
Visin, F., Ciccone, M., Romero, A.: Reseg: a recurrent neural network-based model for semantic segmentation. arXiv:1511.07053 (2015)
Volpi, M., Ferrari, V.: Semantic segmentation of urban scenes by learning local class interactions. In: Computer Vision and Pattern Recognition Workshops, pp. 1–9 (2015)
Liu, J., Liu, B., Lu, H.: Detection guided deconvolutional network for hierarchical feature learning. Pattern Recogn. 48(8), 2645–2655 (2015)
Hong, S., Noh, H., Han, B.: Decoupled deep neural network for semi-supervised semantic segmentation. In: Conference on Neural Information Processing Systems, pp. 1495–1503 (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical. arXiv:1505.04597v1 (2015)
Mcgarigal, K.: Landscape metrics for categorical map patterns. McGarigal (Lecture notes), vol. 2001, Chap 5, pp. 1–77 (2001)
Poullis, C.: Tensor-cuts: a simultaneous multi-type feature extractor and classifier and its application to road extraction from satellite images. ISPRS J. Photogramm. Remote Sens. 95, 93–108 (2014)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 448–456 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations (2015)
Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111(1), 98–136 (2015)
Acknowledgements
T. Panboonyuen thanks the scholarship from Chulalongkorn University to commemorate the 72nd Anniversary of H.M. King Bhumibala Aduladeja. He also thanks Dr. Panu Srestasathiern from GISTDA for his invaluable guidance.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Panboonyuen, T., Vateekul, P., Jitkajornwanich, K., Lawawirojwong, S. (2018). An Enhanced Deep Convolutional Encoder-Decoder Network for Road Segmentation on Aerial Imagery. In: Meesad, P., Sodsee, S., Unger, H. (eds) Recent Advances in Information and Communication Technology 2017. IC2IT 2017. Advances in Intelligent Systems and Computing, vol 566. Springer, Cham. https://doi.org/10.1007/978-3-319-60663-7_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-60663-7_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-60662-0
Online ISBN: 978-3-319-60663-7
eBook Packages: EngineeringEngineering (R0)