Optimasi Mendeteksi Klasifikasi Citra Digital Logo Mobil Indonesia Dengan Metode Single Shot Multibox Detector

Dadang Iskandar Mulyana, Muhammad Zikri

Abstract


Logo kendaraan mobil merupakan salah satu fitur yang dapat mengidentifikasi suatu kendaraan. Namun, banyak dari sistem transportasi cerdas yang saat ini masih dalam pengembangan dan belum menggunakan sistem pengenalan logo kendaraan mobil sebagai bagian dari alat identifikasi kendaraan. Metode sebelumnya yaitu dengan Metode Local Binary Pattern dan Random Forest memiliki tingkat pengenalan yang rendah untuk sebagian besar logo kendaraan kecil dan kinerja yang buruk di bawah lingkungan yang rumit. Tujuanya pada penelitian ini untuk mengenalkan logo mobil yang unik serta untuk meningkatkan akurasi deteksi pada logo mobil di Indonesia. Logo yang terdeteksi kemudian digunakan untuk mengenali merek mobil dalam waktu singkat. Dalam penelitian ini kami menggunakan metode Single Shot Multibox Detector yang dikenal untuk deteksi objek yang berjalan di Aplikasi Jupyter Notebook. Data yang digunakan untuk penelitian ini bersifat publik yang didapat dari sumber dataset website Kaggle yang berisi dari beberapa jumlah gambar yang bervariasi. Terdapat 7 kelas merek mobil yaitu Volkswagen, Hyundai, Lexus, Mercedes, Peugeot, Renault, dan Tesla. Data pengujian pada penelitian ini menadapatkan 1.240 citra untuk kategori data latih dan 270 citra pada kategori data uji yang telah dilakukan pengujian dan menghasilkan nilai evaluasi dengan nilai akurasi terbaik sebesar 98.89 Persen dan nilai loss sebesar 0.025 persen.

Keywords


Logo; Single Shot Multibox Detector; Transportasi; Deteksi Objek; Mobil

Full Text:

PDF

References


P. Gupta, V. Sharma, and S. Varma, “People detection and counting using YOLOv3 and SSD models,” Mater. Today Proc., no. xxxx, 2021, doi: 10.1016/j.matpr.2020.11.562.

D. F. Llorca, R. Arroyo, and M. A. Sotelo, “Vehicle logo recognition in traffic images using HOG features and SVM,” IEEE Conf. Intell. Transp. Syst. Proceedings, ITSC, no. Itsc, pp. 2229–2234, 2013, doi: 10.1109/ITSC.2013.6728559.

Q. Zhao and W. Guo, “applied sciences Detection of Logos of Moving Vehicles under Complex Lighting Conditions,” 2022.

T. D. Q. Dang, H. V. G. Che, and T. B. Dinh, “Mobile multi-scale vehicle detector and its application in traffic surveillance,” ACM Int. Conf. Proceeding Ser., pp. 265–272, 2018, doi: 10.1145/3287921.3287957.

S. Riyadi and D. I. Mulyana, “Optimasi Image Classification pada Wayang Kulit Dengan Convolutional Neural Network,” pp. 1–8, 1850.

T. Mudumbi, N. Bian, Y. Zhang, and F. Hazoume, “An Approach Combined the Faster RCNN and Mobilenet for Logo Detection,” J. Phys. Conf. Ser., vol. 1284, no. 1, 2019, doi: 10.1088/1742-6596/1284/1/012072.

Alda Putri Utami, Febryanti Sthevanie, and Kurniawan Nur Ramadhani, “Pengenalan Logo Kendaraan Menggunakan Metode Local Binary Pattern dan Random Forest,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 5, no. 4, pp. 639–646, 2021, doi: 10.29207/resti.v5i4.3085.

N. Boonsirisumpun, W. Puarungroj, and P. Wairotchanaphuttha, “Automatic detector for bikers with no helmet using deep learning,” 2018 22nd Int. Comput. Sci. Eng. Conf. ICSEC 2018, pp. 1–4, 2018, doi: 10.1109/ICSEC.2018.8712778.

X. Gao, Y. Tao, X. Ding, and R. Hou, “Research on food recognition of smart refrigerator based on SSD target detection algorithm,” ACM Int. Conf. Proceeding Ser., pp. 303–308, 2019, doi: 10.1145/3349341.3349421.

R. Liu, Q. Han, W. Min, L. Zhou, and J. Xu, “Vehicle logo recognition based on enhanced matching for small objects, constrained region and SSFPD network,” Sensors (Switzerland), vol. 19, no. 20, 2019, doi: 10.3390/s19204528.

F. Zhang, Y. Jin, S. Kan, L. Zhang, Y. Cen, and J. Wen, “Vehicle Detection in Distorted Driving Video Based on Metric Learning and Single Shot MultiBox Detector,” BESC 2019 - 6th Int. Conf. Behav. Econ. Socio-Cultural Comput. Proc., 2019, doi: 10.1109/BESC48373.2019.8963547.

K. H. Chen, T. D. Shou, J. K. H. Li, and C. M. Tsai, “Vehicles Detection on Expressway Via Deep Learning: Single Shot Multibox Object Detector,” Proc. - Int. Conf. Mach. Learn. Cybern., vol. 2, pp. 467–473, 2018, doi: 10.1109/ICMLC.2018.8526958.

G. Yuan et al., “Research on face tracking Algorithm Based on Detection and Supervision Tracking,” J. Phys. Conf. Ser., vol. 2209, no. 1, 2022, doi: 10.1088/1742-6596/2209/1/012028.

Q. Chen, N. Huang, J. Zhou, and Z. Tan, “An SSD Algorithm Based on Vehicle Counting Method,” Chinese Control Conf. CCC, vol. 2018-July, pp. 7673–7677, 2018, doi: 10.23919/ChiCC.2018.8483037.

Y. Wang, P. Niu, X. Guo, G. Yang, and J. Chen, “Single Shot Multibox Detector with Deconvolutional Region Magnification Procedure,” IEEE Access, vol. 9, pp. 47767–47776, 2021, doi: 10.1109/ACCESS.2021.3068486.

R. Liang and G. Ji, “Vehicle Detection Algorithm Based on Embedded Video Image Processing in the Background of Information Technology,” vol. 2022, 2022.

S. Yang, C. Bo, J. Zhang, and M. Wang, “Vehicle Logo Detection Based on Modified YOLOv2,” pp. 75–86, 2020, doi: 10.1007/978-3-030-17763-8_8.

P. Liu, X. Li, H. Cui, S. Li, and Y. Yuan, “Hand Gesture Recognition Based on Single-Shot Multibox Detector Deep Learning,” Mob. Inf. Syst., vol. 2019, pp. 25–28, 2019, doi: 10.1155/2019/3410348.

S. Sotheeswaran and A. Ramanan, “A Coarse-to-Fine Strategy for Vehicle Logo Recognition from Frontal-View Car Images,” Pattern Recognit. Image Anal., vol. 28, no. 1, pp. 142–154, 2018, doi: 10.1134/S1054661818010170.

C. Pan, Z. Yan, X. Xu, M. Sun, J. Shao, and D. Wu, “Vehicle logo recognition based on deep learning architecture in video surveillance for intelligent traffic system,” IET Conf. Publ., vol. 2013, no. 635 CP, pp. 132–135, 2013, doi: 10.1049/cp.2013.1994.

S. Yang, J. Zhang, C. Bo, M. Wang, and L. Chen, “Fast vehicle logo detection in complex scenes,” Opt. Laser Technol., vol. 110, no. August, pp. 196–201, 2019, doi: 10.1016/j.optlastec.2018.08.007.

B. Dai, Y. Nie, W. Cui, R. Liu, and Z. Zheng, “Real-time safety helmet detection system based on improved SSD,” ACM Int. Conf. Proceeding Ser., pp. 95–99, 2020, doi: 10.1145/3421766.3421774.




DOI: http://dx.doi.org/10.36448/jsit.v13i2.2660

Article Metrics

Abstract view : 3 times
PDF - 4 times

Refbacks

  • There are currently no refbacks.


About the JournalJournal PoliciesAuthor Information

Explore: Jurnal Sistem Informasi dan Telematika (Telekomunikasi, Multimedia dan Informatika)
e-ISSN: 2686-181X
Website: http://jurnal.ubl.ac.id/index.php/explore
Email: explore@ubl.ac.id
Published by: Pusat Studi Teknologi Informasi, Fakultas Ilmu Komputer, Universitas Bandar Lampung
Office: Jalan Zainal Abidin Pagar Alam No 89, Gedong Meneng, Bandar Lampung, Indonesia

This work is licensed under a Creative Commons Attribution 4.0 International License
Technical Support by:  RYE Education Hub