Analisis Kinerja Prototipe Traffic Sign Recognition Untuk Sistem Autonomous Car Menggunakan You Only Look Once
DOI:
https://doi.org/10.34818/eoe.v7i3.13975Abstrak
Autonomous car adalah sistem mobil yang dikendalikan dengan komputer yang dapat memandu, beradaptasi dengan lingkungan dan beroperasi tanpa interaksi manusia. Ini membuat keadaan lalu lintas semakin rumit sehingga kecerdasan buatan seperti memberikan informasi rambu, dan membantu dalam kontrol kendaraan sangat dibutuhkan untuk memastikan keselamatan berkendara. Tugas Akhir ini akan merancang sebuah sistem yang dapat mengenali rambu lalu lintas dengan metode You Only Look Once (YOLO). YOLO merupakan pendeteksi objek dengan menggunakan convolutional network yang hanya akan dilewatkan satu kali saja. Berbeda dengan convolutional network pada umumnya yang melewatkan ribuan network untuk mendapatkan satu citra dengan komputasi yang cukup lama. Tugas akhir ini akan menggunakan arsitektur YOLO9000 dengan dataset sebanyak 3 class, yaitu rambu belok kanan, belok kiri, dan stop. Konfigurasi sistem yang digunakan adalah learning rate, batch size, dan step training. Dataset terdiri dari 384 citra data latih dan 1920 citra data uji. Dalam Tugas Akhir ini, konfigurasi sistem terbaik didapatkan pada konfigurasi learning rate 0.00002, batch size 8, dan step training 20K dengan hasil akurasi sebesar 93,41%. Kata kunci : You Only Look Once, Traffic Sign Recognition, Akurasi.Unduhan
Referensi
[1] S. A. Wibowo, H. Lee, E. K. Kim, and S. Kim, “Collaborative Learning based on Convolutional Features and
Correlation Filter for Visual Tracking,” Int. J. Control. Autom. Syst., vol. 16, no. 1, pp. 335–349, 2018, doi:
10.1007/s12555-017-0062-x.
[2] S. A. Wibowo, H. Lee, E. K. Kim, and S. Kim, “Convolutional Shallow Features for Performance
Improvement of Histogram of Oriented Gradients in Visual Object Tracking,” Math. Probl. Eng., vol.
2017, 2017, doi: 10.1155/2017/6329864.
[3] S. A. Wibowo, H. Lee, E. K. Kim, and S. Kim, “Visual tracking based on complementary learners with distractor handling,” Math. Probl. Eng., vol. 2017, 2017, doi: 10.1155/2017/5295601.
[4] K. Jo, J. Kim, D. Kim, C. Jang, and M. Sunwoo, “Development of autonomous car-part i: Distributed
system architecture and development process,” IEEE Trans. Ind. Electron., vol. 61, no. 12, pp. 7131–7140,
2014, doi: 10.1109/TIE.2014.2321342.
[5] R. Hussain and S. Zeadally, “Autonomous Cars: Research Results, Issues, and Future Challenges,” IEEE Commun. Surv. Tutorials, vol. 21, no. 2, pp. 1275–1313, 2019, doi: 10.1109/COMST.2018.2869360.
[6] C. Wang, “Research and application of traffic sign detection and recognition based on deep learning,”
Proc. - 2018 Int. Conf. Robot. Intell. Syst. ICRIS 2018, pp. 150–152, 2018, doi:
10.1109/ICRIS.2018.00047.
[7] Y. Han, K. Virupakshappa, and E. Oruklu, “Robust traffic sign recognition with feature extraction and k -
NN classification methods,” IEEE Int. Conf. Electro Inf. Technol., vol. 2015-June, pp. 484–488, 2015, doi:
10.1109/EIT.2015.7293386.
[8] R. Gavrilescu, C. Fo, C. Zet, and D. Cotovanu, “Faster R-CNN : an Approach to Real-Time Object
Detection,” pp. 165–168, 2018.
[9] S. Jung, U. Lee, J. Jung, and D. H. Shim, “Real-time Traffic Sign Recognition system with deep convolutional neural network,” in 2016 13th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2016, 2016, pp. 31–34, doi: 10.1109/URAI.2016.7734014.
[10] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object
detection,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 779–788,
2016, doi: 10.1109/CVPR.2016.91.
[11] J. Redmon and A. Farhadi, “YOLO9000: Better, faster, stronger,” Proc. - 30th IEEE Conf. Comput. Vis.
Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 6517–6525, 2017, doi: 10.1109/CVPR.2017.690. [12] M. D. Zeiler and R. Fergus, “Visualizing and understanding convolutional networks,” Lect. Notes Comput.
Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 8689 LNCS, no. PART 1, pp. 818–833, 2014, doi: 10.1007/978-3-319-10590-1_53.
[13] R. Phadnis, J. Mishra, and S. Bendale, “Objects Talk - Object Detection and Pattern Tracking Using
TensorFlow,” Proc. Int. Conf. Inven. Commun. Comput. Technol. ICICCT 2018, pp. 1216–1219, 2018, doi:
10.1109/ICICCT.2018.8473331.
[14] G. Hu et al., “When Face Recognition Meets with Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition,” Proc. IEEE Int. Conf. Comput. Vis., vol. 2016-Febru, pp. 384–392, 2016, doi: 10.1109/ICCVW.2015.58.
[15] S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Trans. Knowl. Data Eng., vol. 22, no. 10, pp.
1345–1359, 2010, doi: 10.1109/TKDE.2009.191.
[16] L. N. Smith, “Cyclical learning rates for training neural networks,” Proc. - 2017 IEEE Winter Conf. Appl.
Comput. Vision, WACV 2017, no. April 2015, pp. 464–472, 2017, doi: 10.1109/WACV.2017.58.
[17] P. M. Radiuk, “Impact of Training Set Batch Size on the Performance of Convolutional Neural Networks
for Diverse Datasets,” Inf. Technol. Manag. Sci., vol. 20, no. 1, pp. 20–24, 2018, doi: 10.1515/itms-2017-
0003.
[18] R. L. Halterman, Learning to program with Python. 2011.
[19] Y. Zhang, Y. Chen, C. Huang, and M. Gao, “Object detection network based on feature fusion and attention mechanism,” Futur. Internet, vol. 11, no. 1, pp. 1–14, 2019, doi: 10.3390/fi11010009.



