Sistem Deteksi Pothole Menggunakan Convulutional Neural Network Dengan Squeezenet Network

Andrew Sebastian Lehman; Andreas Widjaja; Benny Budiawan Tjandrasa; Joseph Sanjaya

doi:10.30591/smartcomp.v14i3.8323

Sistem Deteksi Pothole Menggunakan Convulutional Neural Network Dengan Squeezenet Network

Andrew Sebastian Lehman, Andreas Widjaja, Benny Budiawan Tjandrasa, Joseph Sanjaya

Abstract

Lubang di jalan merupakan salah satu permasalahan utama yang dihadapi pengguna jalan, karena dapat menyebabkan kerusakan serius pada kendaraan serta meningkatkan risiko kecelakaan lalu lintas. Selain berdampak pada keselamatan pengemudi, terutama mereka yang tidak familiar dengan kondisi jalan, keberadaan lubang juga dapat memicu kemacetan dan meningkatkan emisi karbon akibat perlambatan lalu lintas. Untuk mengatasi permasalahan ini, studi ini mengusulkan sistem deteksi lubang secara real-time berbasis Convolutional Neural Network (CNN) dengan arsitektur ringan SqueezeNet. Sistem dirancang untuk bekerja dengan memanfaatkan gambar yang diambil oleh kamera kendaraan yang sedang bergerak, guna mengidentifikasi lubang yang berpotensi membahayakan. Model CNN dilatih menggunakan dataset gambar yang telah diberi label berdasarkan keberadaan lubang. Kinerja sistem dievaluasi menggunakan metrik precision, recall, dan F1-score guna mengukur keakuratannya dalam mendeteksi lubang. Hasil penelitian menunjukkan bahwa pendekatan ini berpotensi tinggi untuk diterapkan dalam sistem transportasi cerdas, guna meningkatkan keselamatan jalan serta mengurangi biaya perawatan kendaraan akibat kerusakan yang disebabkan oleh lubang jalan.

Keywords

Computer Vision; Potholes; CNN; SqueezeNet.

Full Text:

References

S. K. Sharma and R. C. Sharma, "Pothole Detection and Warning System for Indian Roads," in Advances in Interdisciplinary Engineering, M. Kumar, R. K. Pandey, and V. Kumar Eds. Singapore: Springer Singapore, 2019, pp. 511-519.

M. P. B and S. K.C, "Enhanced pothole detection system using YOLOX algorithm," (in en), Autonomous Intelligent Systems, vol. 2, no. 1, p. 22, 2022-08-31 2022, doi: 10.1007/s43684-022-00037-z.

C. Li, X. Wei, H. Yu, J. Guo, X. Tang, and Y. Zhang, "An Enhanced SqueezeNet Based Network for Real-Time Road-Object Segmentation," in 2019 IEEE Symposium Series on Computational Intelligence (SSCI), 12/2019 2019, Xiamen, China: IEEE, pp. 1214-1218, doi: 10.1109/SSCI44817.2019.9002818.

A. A. Alhussan, D. S. Khafaga, E.-S. M. El-Kenawy, A. Ibrahim, M. M. Eid, and A. A. Abdelhamid, "Pothole and Plain Road Classification Using Adaptive Mutation Dipper Throated Optimization and Transfer Learning for Self Driving Cars," IEEE Access, vol. 10, pp. 84188-84211, 2022 2022, doi: 10.1109/ACCESS.2022.3196660.

A. K. Pandey, R. Iqbal, T. Maniak, C. Karyotis, S. Akuma, and V. Palade, "Convolution neural networks for pothole detection of critical road infrastructure," (in en), Computers and Electrical Engineering, vol. 99, p. 107725, 04/2022 2022, doi: 10.1016/j.compeleceng.2022.107725.

E. Moscoso Thompson et al., "SHREC 2022: Pothole and crack detection in the road pavement using images and RGB-D data," (in en), Computers & Graphics, vol. 107, pp. 161-171, 10/2022 2022, doi: 10.1016/j.cag.2022.07.018.

Aparna, Y. Bhatia, R. Rai, V. Gupta, N. Aggarwal, and A. Akula, "Convolutional neural networks based potholes detection using thermal imaging," (in en), Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 3, pp. 578-588, 03/2022 2022, doi: 10.1016/j.jksuci.2019.02.004.

A. Yang Her, W. Kean Yew, P. Jia Yew, and M. Chong Jia Ying, "Real-time pothole detection system on vehicle using improved YOLOv5 in Malaysia," in IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society, 2022-10-17 2022, Brussels, Belgium: IEEE, pp. 1-5, doi: 10.1109/IECON49645.2022.9968423.

U. Yahya, M. Lucky, M. Mansoor, N. Sharifah, A. Kasule, and K. Usama, "IoT-Based Pothole Mapping Agent with Remote Visualization," 2022 2022, doi: 10.48550/ARXIV.2212.14764.

A. K. Pandey, R. Iqbal, S. Amin, T. Maniak, V. Palade, and C. Karyotis, "Deep Neural Networks Based Approach for Pothole Detection," in 2021 4th International Conference on Signal Processing and Information Security (ICSPIS), 2021-11-24 2021, Dubai, United Arab Emirates: IEEE, pp. 1-4, doi: 10.1109/ICSPIS53734.2021.9652434.

K. R. Ahmed, "Smart Pothole Detection Using Deep Learning Based on Dilated Convolution," (in en), Sensors, vol. 21, no. 24, p. 8406, 2021-12-16 2021, doi: 10.3390/s21248406.

A. A. Shaghouri, R. Alkhatib, and S. Berjaoui, "Real-Time Pothole Detection Using Deep Learning," 2021-07-13 2021.

S. Kharel and K. R. Ahmed, "Potholes Detection Using Deep Learning and Area Estimation Using Image Processing," in Intelligent Systems and Applications, vol. 296, K. Arai Ed. Cham: Springer International Publishing, 2022, pp. 373-388.

E. S. Team. "What is Machine Learning? A definition." https://expertsystem.com/machine-learning-definition (accessed Jun. 8, 2020).

A. Burkov, The hundred-page machine learning book. Andriy Burkov (in English), 2019.

F. Ciabuschi and B. Venkateswaran, Neural networks with R: smart models using CNN, RNN, deep learning, and artificial intelligence principles. Birmingham, UK Mumbai: Packt (in eng), 2017, p. 256.

P. Srivastava and A. Rai. "Supervised and Unsupervised learning." https://www.geeksforgeeks.org/supervised-unsupervised-learning/ (accessed Jun. 08, 2020).

J. Andreanus and A. Kurniawan, "Sejarah, Teori Dasar dan Penerapan Reinforcement Learning: Sebuah Tinjauan Pustaka," Jurnal Telematika, vol. 12, no. 2, pp. 113-118, 2018.

V. Dhar, "Data science and prediction," (in en), Communications of the ACM, vol. 56, no. 12, pp. 64-73, 12/2013 2013, doi: 10.1145/2500499.

H. J. Adèr, G. J. Mellenbergh, and D. J. Hand, Advising on research methods: a consultant's companion. Huizen: Johannes van Kessel (in eng), 2008, p. 574.

A. W. Trask, Grokking deep learning. Shelter Island: Manning, 2019, p. 309.

J. D. Kelleher, Deep learning (The MIT press essential knowledge series). Cambridge, Massachusetts: The MIT Press, 2019, p. 280.

F. Malik, "Understanding Neural Networks: From Activation Function To Back Propagation," in Medium, ed, 2018.

G. Bonaccorso, Mastering machine learning algorithms: expert techniques to implement popular machine learning algorithms and fine-tune your models. (in English), 2018.

R. Venkatesan and B. Li, Convolutional neural networks in visual computing: a concise guide (Data-enabled engineering). Boca Raton: CRC Press, Taylor & Francis Group, CRC Press is an imprint of the Taylor & Francis Group, an informa business, 2018, p. 168.

A. Karpathy, "Cs231n convolutional neural networks for visual recognition," Neural networks, vol. 1, no. 1, 2016 2016.

S. Qiu, X. Xu, and B. Cai, "FReLU: Flexible Rectified Linear Units for Improving Convolutional Neural Networks," 2017 2017, doi: 10.48550/ARXIV.1706.08098.

H.-C. Park, I.-P. Hong, S. Poudel, and C. Choi, "Data Augmentation Based on Generative Adversarial Networks for Endoscopic Image Classification," IEEE Access, vol. 11, pp. 49216-49225, 2023 2023, doi: 10.1109/ACCESS.2023.3275173.

D. Liang, F. Yang, T. Zhang, and P. Yang, "Understanding Mixup Training Methods," IEEE Access, vol. 6, pp. 58774-58783, 2018 2018, doi: 10.1109/ACCESS.2018.2872698.

L. N. Smith, "A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay," 2018 2018, doi: 10.48550/ARXIV.1803.09820.

DOI: https://doi.org/10.30591/smartcomp.v14i3.8323