A novel approach for semantic segmentation of automatic road network extractions from remote sensing images by modified UNet

Miral J. Patel, Ashish M. Kothari, Hasmukh P. Koringa

Abstract


Accurate and up-to-date road maps are crucial for numerous applications such as urban planning, automatic vehicle navigation systems, and traffic monitoring systems. However, even in the high resolutions remote sensing images, the background and roads look similar due to the occlusion of trees and buildings, and it is difficult to accurately segment the road network from complex background images. In this research paper, an algorithm based on deep learning was proposed to segment road networks from remote sensing images. This semantic segmentation algorithm was developed with a modified UNet. Because of the lower availability of remote sensing images for semantic segmentation, the data augmentation method was used.  Initially, the semantic segmentation network was trained by a large number of training samples using traditional UNet architecture. After then, the number of training samples is reduced gradually, and measures the performance of a traditional UNet model. This basic UNet model gives better results in the form of accuracy, IOU, DICE score, and visualization of the image for the 362 training samples. The idea here is to simply extract road data from remote sensing images. As a result, unlike traditional UNet, there is no need for a deeper neural network encoder-decoder structure. Hence, the number of convolutional layers in the modified UNet is lower than that in the standard UNet. Therefore, the complexity of the deep learning architecture and the training time required by the road network model was reduced. The model performance measured by the intersection over union (IOU) was 93.71% and the average segmentation time of a single image was 0.28 sec. The results showed that the modified UNet could efficiently segment road networks from remote sensing images with identical backgrounds. It can be used under various situations.

Keywords


Semantic Segmentation; UNet; Road Network; Extraction; modified UNet

Full Text:

PDF

References


Liu, J., Miao, Q., Song, J., Quan, Y., Li, Y., Xu, P., Dai, J. Multiscale road centerlines extraction from high-resolution aerial imagery. Neurocomputing, 2019, vol. 329, pp. 384-396. DOI: 10.1016/j.neucom.2018.10.036.

Gao, X., Sun, X., Zhang, Y., Yan, M., Xu, G., Sun, H., Jiao, J., Fu, K. An end-to-end neural network for road extraction from remote sensing imagery by multiple feature pyramid network. IEEE Access, 2018, vol. 6, pp. 39401-39414. DOI: 10.1109/ACCESS.2018.2856088.

Wulamu, A., Shi, Z., Zhang, D., He, Z. Multiscale road extraction in remote sensing images. Computational intelligence and neuroscience, 2019, vol. 2019, article id 2373798. DOI: 10.1155/2019/2373798.

Wang, L., Qin, Q., Du, S., Chen, D., Tao, J. Road extraction from remote sensing image based on multi-resolution analysis. 31thInternational Symposium on Remote Sensing of Environment, 2005. 4 p.

Cheng, G., Wang, Y., Xu, S., Wang, H., Xiang, S., Pan, C. Automatic Road Detection And Centerline Extraction Via Cascaded End-To-End Convolutional Neural Network. IEEE Transactions on Geoscience and Remote Sensing, 2017, vol. 55, no. 6, pp. 3322-3337. DOI: 10.1109/TGRS.2017.2669341.

Hormese, J., Saravanan, C. Automated Road Extraction From High Resolution Satellite Images. Procedia Technology, 2016, vol. 24, pp. 1460-1467. DOI: 10.1016/j.protcy.2016.05.180.

Wang, W., Yang, N., Zhang, Y., Wang, F., Cao, T., Eklund, P. A Review of Road Extraction from Remote Sensing Images. J. Traffic Transp. Eng., 2016, vol. 3, iss. 3, pp. 271-282. DOI: 10.1016/j.jtte.2016.05.005.

Vincent, L., Soille, P. Watersheds In Digital spaces: An Efficient Algorithm Based On Immersion simulation. IEEE Trans. On Pattern Analysis And Machine Intelligence, 1991, vol. 13, iss. 6, pp. 583-598. DOI: 10.1109/34.87344.

Wang, D. A Multiscale Gradient Algorithm For Image Segmentation Using Watersheds. Pattern Recognition, 1997, vol. 30, iss. 12, pp. 2043-2052. DOI: 10.1016/S0031-3203(97)00015-0.

Shen, J., Lin, X., Shi, Y., Wong, C. Knowledge-Based Road Extraction From High Resolution Remotely Sensed Imagery. IEEECongress on Image and Signal Processing, 2008, pp. 608-612. DOI: 10.1109/CISP.2008.519.

Bakhtiari, H. R. R., Abdollahi, A., Rezaeian, H. Semi Automatic Road Extraction From Digital Images. The Egypt. J. Remote Sensing and Space Science, 2017, vol. 20, iss. 1, pp. 117-123. DOI: 10.1016/j.ejrs.2017.03.001.

Xu, G., Zhang, D., Li, X. Road Extraction In High Resolution Images From Google Earth.7th International Conference on Information, Communications and Signal Processing, China, 2009, pp. 1-5. DOI: 10.1109/ICICS.2009.5397470.

Anil, P.N., Natarajan, S. A Novel Approach Using Active Contour Model For Semi-Automatic Road Extraction From High Resolution Satellite Imagery. Second International Conference On Machine Learning And Computing, 2010, pp. 263-266. DOI: 10.1109/ICMLC.2010.36.

Liu, Y., Yao, J., Lu, X., Xia, M., Wang, X., Liu, Y. RoadNet: Learning To Comprehensively Analyze Road Networks In Complex Urban Scenes From High-Resolution Remotely Sensed Images. IEEE Trans. Geosci. Remote Sens., 2019, vol. 57, no. 4, pp. 2043-2056. DOI: 10.1109/TGRS.2018.2870871.

Lukin, V., Proskura, G., Vasilieva, I. Comparison Of Algorithms For Controlled Pixel-By-Pixel Classification OfNoisy Multichannel Images. Radioelectronic And Computer Systems, 2019, no. 4, pp. 39-46. DOI: 10.32620/reks.2019.4.04.

Ghasemloo, N., Mobasheri, M. R., Zare, A. M., Eftekhari, M. M. Road And Tunnel Extraction From SPOT Satellite Images Using Neural Networks. Journal of Geographic Information System, 2013, vol. 5, iss. 1, pp. 69-74. DOI: 10.4236/jgis.2013.51007.

Alshehhi, R., Marpu, P. R., Woon, W. L., Mura, M. D. Simultaneous Extraction Of Roads And Buildings In Remote Sensing Imagery With Convolutional Neural Networks. ISPRS Journal of Photogrammetry And Remote Sensing, 2017, vol. 130, pp. 139-149. DOI: 10.1016/j.isprsjprs.2017.05.002.

Xin, J., Zhang, X., Zhang, Z., Fang, W. Road Extraction of High-Resolution Remote Sensing Images Derived From DenseUNet. Remote Sensing, 2019, vol. 11, iss. 21, article no. 2499. DOI: 10.3390/rs11212499.

Zhang, Z., Liu, Q., Wang, Y. Road Extraction By Deep Residual UNet. IEEE Geosci. Remote Sens. Lett., 2018, vol. 15, no. 5, pp. 749-753. DOI: 10.48550/arXiv.1711.10684.

Ronneberger, O., Fischer, P., Brox, T. UNet: Convolutional networks for biomedical image segmentation. Computer Vision and Pattern Recognition, 2015, pp. 1-8. DOI: 10.48550/arXiv.1505.04597.

Massachusetts dataset. Available at: https://www.cs.toronto.edu/~vmnih/data/mass_roads/train/sat/index.html (accessed on July 2021).

Shorten, C. C., Khoshgoftaar, M. T. A Survey on Image Data Augmentation for Deep Learning. J. Big Data, 2019, vol. 6, article no. 60. DOI: 10.1186/s40537-019-0197-0.

Jiang, Y. Research on road extraction of remote sensing image based on convolutional neural network. EURASIP Journal on Image and Video Processing, 2019, article no. 31. DOI: 10.1186/s13640-019-0426-7.

Barbedo, J. G. A. Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification. Computers and Electronics in Agriculture, 2018, vol. 153, pp. 46-53. DOI: 10.1016/j.compag.2018.08.013.

Yadav, S., Jadhav, S. M. Deep convolutional neural network based medical image classification for disease diagnosis. Journal of Big Data, 2019, vol. 6, article no. 113. DOI: 10.1186/s40537-019-0276-2.

Krizhevsky, A., Sutskever, I., Hinton, G. E. ImageNet Classification with Deep Convolutional Neural Networks. Communications of the ACM, 2017, vol. 60, iss. 6, pp. 84-90. DOI: 10.1145/3065386.

Szegedy, C., Vanhoucke, V., Ioffe, J., Shlens, J., Wojna, Z. Rethinking the Inception Architecture for Computer Vision. Computer Vision and Pattern Recognition, 2015, pp. 1-10. DOI: 10.48550/arXiv.1512.00567.

Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A. Going Deeper with Convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1-9. DOI: 10.1109/CVPR.2015.7298594.

Не, K., Zhang, X., Ren, S., Sun, J. Deep Residual Learning for Image Recognition. Computer Vision and Pattern Recognition, 2015, pp.1-12. DOI: 10.48550/arXiv.1409.4842.

Yaloveha, V., Podorozhniak, A., Kuchuk, H. Convolutional neural network hyperparameter optimization applied to land cover classification. Radioelectronic and computer systems, 2022, no. 1, pp. 115-128. DOI: 10.32620/reks.2022.1.09.

He, K., Sun, J. Convolutional neural networks at constrained time cost. IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 5353-5360. DOI: 10.1109/CVPR.2015.7299173.

Badrinarayanan, V., Kendall, A., Cipolla, R. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, vol. 39, iss. 12, pp. 2481-2495. DOI: 10.1109/TPAMI.2016.2644615.

Canziani, A., Paszke, A., Culurciello, E. An Analysis of Deep Neural Network Models for Practical Applications. Computer Vision and Pattern Recognition, 2016, pp. 1-7. DOI: 10.48550/arXiv.1605.07678.




DOI: https://doi.org/10.32620/reks.2022.3.12

Refbacks

  • There are currently no refbacks.