Power-Line Road Segmentation Menggunakan Improved Residual Networks
DOI:
https://doi.org/10.26418/jp.v10i2.77946Keywords:
Improved Residual Networks, Pemetaan Jalan, Massachusetts Road Dataset, Deep Learning, Citra SatelitAbstract
Pemetaan jalan menjadi komponen penting dalam pengembangan infrastruktur jalan untuk mendukung kebutuhan mobilitas yang semakin kompleks. Pemetaan jalan memiliki cakupan areal yang sangat luas dan pendataannya cukup sulit, namun pemetaan jalan masih dilakukan secara manual. Pemetaan jalan dapat memalui citra satelit, namun karena dilakukan secara manual maka memerlukan waktu yang cukup lama. Dalam perkembangannya dibutuhkan pemetaan jalan secara otomatis salah satunya dengan menggunakan machine learning berdasarkan fitur-fitur dari citra satelit yang telah ditentukan. Namun pengambilan fitur atau informasi yang diperoleh dari citra satelit memiliki kendala yang cukup sulit untuk diatasi, antara lain persamaan warna dan bentuk yang mempunyai kemiripan. Oleh karena itu pada penelitian ini diajukan metode deep learning berbasis U-Net dengan susunan residual block untuk mengatasi permasalahan tersebut. Data yang digunakan pada penelitian ini adalah Massachusetts Road Dataset berupa data citra satelit beresolusi tinggi. Pemetaan jalan dilakukan dengan menggunnakan metode Improved Residual Networks. Hasil pengujian model menunjukkan nilai Precision 81.6%, Recall 77.9%, Accuracy 98.1%, dan F1-score 79.7%. Kinerja tersebut lebih baik dari sejumlah penelitian sebelumnya.References
. Handayani, L.G.S., Piarsa, I.N., Wibawa, K.S., 2015. Sistem Informasi Geografis Pemetaan Jalan Desa Berbasis Web 6.
. Lan, M., Zhang, Y., Zhang, L., Du, B., 2020. Global context based automatic road segmentation via dilated convolutional neural network. Inf. Sci. 535, 156–171. https://doi.org/10.1016/j.ins.2020.05.062.
. Nazir, A., Cheema, M. N., Sheng, B., Li, P., Li, H., Xue, G., ... & Feng, D. D. (2021). ECSU-net: an embedded clustering sliced U-net coupled with fusing strategy for efficient intervertebral disc segmentation and classification. IEEE Transactions on Image Processing, 31, 880-893.
. Oliveira, G.L., Burgard, W., Brox, T., 2016. Efï¬cient Deep Models for Monocular Road Segmentation..
. Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., ... & Chen, T. (2018). Recent advances in convolutional neural networks. Pattern recognition, 77, 354-377.
. Levi, D., Garnett, N., Fetaya, E., 2015. StixelNet: A Deep Convolutional Network for Obstacle Detection and Road Segmentation, in: Procedings of the British Machine Vision Conference 2015. Presented at the British Machine Vision Conference 2015, British Machine Vision Association, Swansea, p. 109.1-109.12. https://doi.org/10.5244/C.29.109.
. Mattyus, G., Wang, S., Fidler, S., Urtasun, R., 2016. HD Maps: Fine-Grained Road Segmentation by Parsing Ground and Aerial Images, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Presented at the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Las Vegas, NV, USA, pp. 3611–3619. https://doi.org/10.1109/CVPR.2016.393.
. Xu, Y., Xie, Z., Feng, Y., Chen, Z., 2018. Road Extraction from High-Resolution Remote Sensing Imagery Using Deep Learning. Remote Sens. 10, 1461. https://doi.org/10.3390/rs10091461.
. Panboonyuen, T., Jitkajornwanich, K., Lawawirojwong, S., Srestasathiern, P., Vateekul, P., 2017. Road Segmentation of Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields. Remote Sens. 9, 680. https://doi.org/10.3390/rs9070680
. Abderrahim, N.Y.Q., Abderrahim, S., Rida, A., 2020. Road Segmentation using U-Net architecture, in: 2020 IEEE International Conference of Moroccan Geomatics (Morgeo). Presented at the 2020 International conference of Moroccan Geomatics (Morgeo), IEEE, Casablanca, Morocco, pp. 1–4. https://doi.org/10.1109/Morgeo49228.2020.9121887.
. He, K., Zhang, X., Ren, S., Sun, J., 2016. Identity Mappings in Deep Residual Networks.
. Duta, I.C., Liu, L., Zhu, F., Shao, L., 2021. Improved Residual Networks for Image and Video Recognition, in: 2020 25th International Conference on Pattern Recognition (ICPR). Presented at the 2020 25th International Conference on Pattern Recognition (ICPR), IEEE, Milan, Italy, pp. 9415–9422. https://doi.org/10.1109/ICPR48806.2021.9412193.
. Mnih, V., 2013 Machine Learning for Aerial Image Labeling.
. Ronneberger, O., Fischer, P., Brox, T., 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation, in: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (Eds.), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Lecture Notes in Computer Science. Springer International Publishing, Cham, pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28.
. Z. Zhong, J. Li, W. Cui, and H. Jiang, "Fully convolutional networks for building and road extraction: Preliminary results," in 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2016: IEEE, pp. 1591-1594.
. Y. Wei, Z. Wang, and M. Xu, "Road structure refined CNN for road extraction in aerial image," IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 5, pp. 709-713, 2017.
. T. Panboonyuen, K. Jitkajornwanich, S. Lawawirojwong, P. Srestasathiern, and P. Vateekul, "Road segmentation of remotelysensed images using deep convolutional neural networks with landscape metrics and conditional random fields," Remote Sensing, vol. 9, no. 7, p. 680, 2017.
. Wong, V. W. H., Ferguson, M., Law, K. H., Lee, Y. T. T., & Witherell, P. (2022). Segmentation of additive manufacturing defects using U-net. Journal of Computing and Information Science in Engineering, 22(3), 031005.
. Yuan, M., Liu, Z., & Wang, F. (2019). Using the wide-range attention U-Net for road segmentation. Remote sensing letters, 10(5), 506-515.
. Di Benedetto, A., Fiani, M., & Gujski, L. M. (2023). U-Net-based CNN architecture for road crack segmentation. Infrastructures, 8(5), 90.
. Song, X., Jiang, Y., Tu, S., Du, Y., & Neyshabur, B. (2019). Observational overfitting in reinforcement learning. arXiv preprint arXiv:1912.02975.
. Rice, L., Wong, E., & Kolter, Z. (2020, November). Overfitting in adversarially robust deep learning. In International conference on machine learning (pp. 8093-8104). PMLR.
. Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., ... & Farhan, L. (2021). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of big Data, 8, 1-74
. Wang, Z., Chen, J., & Hoi, S. C. (2020). Deep learning for image super-resolution: A survey. IEEE transactions on pattern analysis and machine intelligence, 43(10), 3365-3387.
