Design of Object Detection System for Tangkuban Parahu Volcano Monitoring Application
Downloads
Indonesia has 127 active volcanoes, which have to be monitored continuously in normal, eruption, or after-eruption conditions, to minimize the effects of disaster. Therefore, we have developed a four-wheeled mobile robot for both exploration and monitoring of volcanoes. To finish its mission on uneven terrain full of obstacles, the robot should be able to detect and avoid these obstacles. Therefore, real-time object detection was designed using the YOLOv5s deep learning algorithm, which was implemented on a Raspberry Pi3 for the front camera of the robot. Before it was tested on a real volcano, the model of the algorithm was trained to be able to detect obstacles. The dataset was trained with three variations of epochs (100, 300, and 500) in sixteen batches of YOLOv5s. The last variant yielded the best results, at 63.4% mAP_0.5 and 40.4% mAP_0.5:0.95, with almost zero loss. This model was then implemented on a Raspberry Pi3 to detect trees and rocks captured by camera on Tangkuban Parahu Volcano. Most of the trees and rocks were successfully detected, with 90.9% recall, 79.9% precision, and 91.5% accuracy. Furthermore, the detection error was low, as indicated by low FP and FN numbers.
Djamal, M., Evita, M., Zimanowski, B. & Schilling, K., Development of Volcano Early Warning System, Proc. of Seminar Nasional Fisika 2015, Keynote Paper, 2015.
Djamal, M., Evita, M., Zimanowski, B. & Schilling, K., Development of a Low-cost Mobile Volcano Early Warning System, J. Tech. Sci., 1(2), pp. 84-91, 2017.
Evita, M., Djamal, M., Zimanowski, B. & Schilling, K., Mobile Monitoring System for Indonesian Volcano, Proc. of the 4th International Conference on Instrumentation, Communication, Information Technology, and Biomedical Engineering (ICICI-BME), pp. 278-281, 2015.
Evita, M., Djamal, M., Zimanowski, B. & Schilling, K., Fixed-mode of Mobile Monitoring System for Indonesian Volcano, Proc. of the 4th International Conference on Instrumentation, Communication, Information Technology, and Biomedical Engineering (ICICI-BME), pp. 282-287, 2015.
Evita, M., Zakiyyatuddin, A., Seno, S., Aminah, N.S., Srigutomo, W., Meilano, I., Setiawan, A., Darmawan, H., Suyanto, I., Irzaman, Yasin, M., Perdinan, Apsari, R., Wahyudi, Suryanto, W. & Djamal, M., Development of Volcano Early Warning System for Kelud Volcano, J. Eng. Technol. Eng. Sci., 53(3), pp. 213-226, 2021.
Evita, M., Djamal, M., Zimanowski, B. & Schilling, K., Mobile Robot Deployment Experiment for Mobile Mode of Mobile Monitoring System for Indonesian Volcano, Proc. of International Conference on Technology and Social Science, Keynote Lecture, 2017.
Evita, M., Zakiyyatuddin, A., Seno, S., Kumalasari, R., Lukado, H. & Djamal, M., Development of a Robust Mobile Robot for Volcano Monitoring Application, IOP Proc. of the 9th International Conference on Theoretical and Applied Physics (ICTAP), 1572, 2019.
Bares, J.E. & Wettergreen, D.S., Dante II: Technical Description, Results, and Lessons Learned, The International Journal of Robotics Research, 18, pp.621-649, 1999
Nagatani, K., Ken, A., Genki, Y., Kazuya, Y., Yasushi, H., Shin’ichi, Y., Tomoyoki, I. & Mackay, R. Development and Field Test of Teleoperated Mobile Robots for Active Volcano Observation, Proc. of the International Conference on Intelligent Robots and Systems (IROS) Chicago, 2014.
Xinchi, T., Huajun, Z., Wenwen, C., Peimin, Z., Zhiwen, L. & Kai, C., A Research on Intelligent Obstacle Avoidance for Unmanned Surface Vehicles, Proc. of the 2018 Chinese Automation Congress (CAC), pp. 1431-1435, 2018.
Redmon, J., Divvala, S., Girshick, R. & Farhadi, A., You Only Look Once: Unified, Real-Time Object Detection, Proc. of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779-788, 2016.
Wang, J., Ma, Y., Zhang, L. & Gao R.X., Deep Learning for Smart Manufacturing: Methods and Applications, J. Manuf. Syst., 48, pp.144-156, 2018.
Ren, S., He, K., Girshick, R. & Sun, J., Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, Advances in Neural Information Processing System, pp. 91-99, 2015.
Girshick, R., Fast R-CNN, Proc. of the IEEE International Conference on Computer Vision, pp. 1440-1448, 2015.
Du, J., Understanding of Object Detection Based on CNN Family and YOLO, J. Phys.: Conf.Ser., pp 1-7, 2018.
Bochkovskiy, A., Wang, C.Y. & Liao, H.Y., YOLOv4: Optimal Speed and Accuracy of Object Detection, arXiv 2004,10934v1, 2020.
Tan, M., Pang, R. & Le, Q. V., EfficientDet: Scalable and Efficient Object Detection, Proc. of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10778-10787, 2020.
Layek, M.A., Uddin, Shahab, A.F.M., Hossain, M.D., Thu, N.T., Yu, S., Yong, C.H., Lee, G.W., Chung, T.C. & Huh, E.N., Cloud-based Smart Surveillance System using Raspberry Pi and YOLO, Proc. of the Korea Software Congress, 2018.
Angkasa, S., Ohba, T., Abdurachman, M., Setiawan, I. & Rosana, M., Altered Ash Particles Mineralogy from Mt. Tangkuban Parahu Volcanic Products, Indonesia: Constraint on the Sub-Volcanic Hydrothermal System, EGU General Assembly 2018, 20, pp.EGU2018-11339, 2018.
Gumilar, I., Putra, R.T.S., Haerani, N., Abidin, H.Z., Bramanto, B. & Lukmanulhakim, A., Preliminary Result of Ratu Crater - Tangkuban Parahu Deformation, West Java by Using Terrestrial Laser Scanner, Proc. of the Joint Convention Balikpapan 2015, 2015.
Angkasa., S.S., Ohba, T., Imura, T., Setiawan, I. & Rosana, M.F., Tephra-stratigraphy and Ash Componentry Studies of Proximal Volcanic Product at Mount Tangkuban Parahu, Indonesia: An Insight to Holocene Volcanic Activity, Indonesian Journal on Geoscience, 6(3), pp. 223-241, 2019.
Devnita, R., Melanic and Fulvic Andisols in Volcanic Soils Derived from some Volcanoes in West Java, Indonesian Journal of Geology, 7(4), pp. 227-240, 2012.
BBKSDA Jabar, Tangkuban Parahu, http://bbksdajabar.ksdae.menlhk.go.id/wp-content/uploads/2017/08/Profil-Bidwil-2-Fix_skw_4_tangkuban-perahu.pdf (14 July 2021).
Conrad, D. & DeSouza, G.N., Homography-Based Ground Plane Detection for Mobile Robot Navigation using a Modified EM Algorithm, Proc. of the IEEE International Conference on Information and Automation, pp. 910-915, 2010.
Gracia, A.G., Collado, I., Urquizo, R.C., Reyes, R., & Garrido, L., A 3D Vision Based Obstacle Avoidance Methodology for Unmanned Surface Vehicle, Proc. 21st Congreso Mexicano de Robótica, 2019.
Gunnarsson, Adam., Real Time Object Detection on a Raspberry Pi, Bachelor Degree Thesis, Linnaeus University, 2019.
Kanjee, R., YOLOv5 Controversy- Is YOLOv5 Real?, https://medium.com/swlh/yolov5-controversy-is-yolov5-real-20e048bebb08 (23 March 2024).
Nelson, J. & Solawetz, J., YOLOv5 is Here: State-of-the-Art Object Detection at 140 FPS, https://blog.roboflow.com/yolov5-is-here/ (23 March 2024).
Castells D., Rodrigues, J.M.F. & du Buf, J.M.H., Obstacle Detection and Avoidance Sidewalk, Proc. of the International Conference on Computer Vision Theory and Applications, pp. 235-240, 2010.
Evita, M., Mustikawati, S. & Djamal, M., Design of Real-Time Object Detection in Mobile Robot for Volcano Monitoring Application, IOP Proc. of the Asian Physics Symposium 2021, 2021.
Lin, T.Y., Goyal, P., Girshick, R., He, K. & Dollar, P., Focal Loss for Dense Object Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 99, pp.1-1, 2018.
Ahmad, K.R., Smart Pothole Detection using Deep Learning based on Dilated Convolution, Sensors (Basel), 21(24), pp. 8406, 2021.
Nayyar, A. & Puri, V., Raspberry Pi-A Small, Powerful, Cost Effective and Efficient Form Factor Computer: A Review, International Journal of Advanced Research in Computer Science and Software Engineering, pp. 720-737, 2015.
O’Mahony, N., Murphy, T. & Panduru, K., Real-time Monitoring of Powder Blend Composition using Near Infrared Spectroscopy, Proc. of The 11th International Conference on Sensing Technology (ICST), IEEE, pp. 1-6, 2017.
Hagan, M.T., Demuth, H.B. & Beale, M.H., Neural Network Design, Campus Pub. Service, University of Colorado Bookstore, 2002.
Walchli, A., Plotting Metrics with Tensorboard Plots Two Graphs Instead on One. What is the Second One?, https://github.com/PyTorchLightning/pytorch-lightning/issues/5316. (6 June 2021).
Koehrsen, W., Beyond Accuracy: Precision and Recall, https://towardsdatascience.com/beyond-accuracy-precision-and-recall-3da06bea9f6c. (10 August 2021)
Banerjeer, Understanding Accuracy, Recall, Precision, F1 Score and Confusion Matrices, https://www.realpythonproject.com/understanding-accuracy-recall-precision-f1-scores-and-confusion-matrices/. (10 August 2021)
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R. & Ren, D., Distance-IoU Loss: Faster and Bet-ter Learning for Bounding Box Regression, Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), pp.12993-13000, 2020.
Jocher, G., YOLOv5, https://github.com/ultralytics/yolov5 (6 Juni 2021).
Copyright (c) 2024 Journal of Engineering and Technological Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
