Improved vehicle detection accuracy using CLAHE

Improved vehicle detection accuracy using CLAHE

Authors

  • A Widiyanto Department of Information Technology, Universitas Muhammadiyah Magelang, Magelang, Indonesia
  • S Nugroho 2 Department of Informatic Engineering, Universitas Muhammadiyah Magelang, Magelang, Indonesia
  • M R A Yudianto Department of Informatic Engineering, Universitas Muhammadiyah Magelang, Magelang, Indonesia

Keywords:

Vehicle detection accuracy, CLAHE, Image processing

Abstract

The large number of vehicles can cause new problems in various fields. Vehicle detection errors can occur in the vehicle detection system when several vehicles are side by side so that they are not detected or are detected as larger vehicles. This research produces a vehicle type detection system to improve vehicle detection accuracy by applying image processing on Convolutional Neural Network (CNN). In this study, experiments were conducted with 20 image processing scenarios in the pre-processing image before the training process to produce an object detection testing model. The simulation test results show that not all image processing scenarios can improve the accuracy of the detection process. The combined image processing scenario of Blue Channel + CLAHE + gaussian filter + thresholding produces an accuracy of 97%.

References

[1] BPS Jumlah Kendaraan Bermotor (Unit), 2016-2018 Available online: https://www.bps.go.id/indicator/17/57/1/jumlah-kendaraan-bermotor.html (accessed on Oct 25, 2020).

[2] Roshintha, R.R.; Mangkoedihardjo, S. Analisis Kecukupan Ruang Terbuka Hijau Sebagai Penyerap Emisi Gas Karbon Dioksida (CO2) pada Kawasan Kampus ITS Sukolilo, Surabaya. J. Tek. ITS 2016, 5, doi:10.12962/j23373539.v5i2.17510.

[3] Limantara, A.D.; Candra, A..; Mudjanarko, S.W. Manajemen Data Lalu Lintas Kendaraan Berbasis Sistem Internet Cerdas Ujicoba Implementasi di Laboratorium Universitas Kadiri. In Proceedings of the Pros. Semnastek; 2017; Vol. 4, pp. 1–11.

[4] Prasetyo, B.A.; Rizani, D.A.; Setiyo, M.; Widodo, N.; Saifudin; Purnomo, B.C. Estimasi Pemborosan Bahan Bakar Akibat Kemacetan Menggunakan Analisis Citra Google Map (Studi Kasus pada Simpang Armada Town Square Mall Magelang). Automot. Exp. 2018, 1, 36–42.

[5] Hariyanto, M.S.; Sofwan, A.; Hidayatno, A. Perancangan Sistem Penghitung Jumlah Kendaraan Pada Area Parkir Dengan Metode Background Subtraction Berbasis Internet of Things. Transient 2019, 7, 775, doi:10.14710/transient.7.3.775-781.

[6] Hardiyanto, R.D.; Rochim, A.F.; Windasari, I.P. Pembuatan Penghitung Jumlah Mobil Otomatis Berbasis Mikrokontroler ATMega 8535 Menggunakan Sensor Ultrasonik. J. Teknol. dan Sist. Komput. 2015, 3, 185, doi:10.14710/jtsiskom.3.2.2015.185-191.

[7] Aynurrohmah, M.; Sunyoto, A. Penghitung Jumlah Mobil Menggunakan Pengolahan Citra Digital Dengan Input Video Digital. Data Manaj. dan Teknol. Inf. 2011, 12, 2–6.

[8] Mu’arifah, S.; Pratomo, A.H.; Kaswidjanti, W. Pengolahan Citra Untuk Klasifikasi dan Perhitungan Jumlah Kendaraan. In Proceedings of the SEMNASTIK; STMIK Binadarma: Palembang, 2016; pp. 771–782.

[9] Budiarto, J.; Qudsi, J. Deteksi Citra Kendaraan Berbasis Web Menggunakan Javascript Framework Library. MATRIK J. Manajemen, Tek. Inform. dan Rekayasa Komput. 2018, 18, 125–133, doi:10.30812/matrik.v18i1.325.

[10] Adistya, R.; Muslim, M.A. Deteksi dan Klasifikasi Kendaraan menggunakan Algoritma Backpropagation dan Sobel. J. Mech. Eng. Mechatronics 2016, 1, 65–73.

[11] Purwiyanti, S.; Herlinawati; Murdika, U. Rancang Bangun Penghitung Jumlah Kendaraan Menggunakan Metode Tracking Feature Point Berbasis Raspberry. Fakultas Teknik Universitas Lampung, 2017.

[12] Setyawan, G.E.; Adiwijaya, B.; Fitriyah, H. Sistem Deteksi Jumlah, Jenis dan Kecepatan Kendaraan Menggunakan Analisa Blob Berbasis Raspberry Pi. J. Teknol. Inf. dan Ilmu Komput. 2019, 6, 211, doi:10.25126/jtiik.2019621405.

[13] Gozali, F.; Iskandardinata, R.; Subrata, R.H. Sistem Pemantauan Dan Perekaman Gerak Kendaraan Secara Nirkabel Dengan Menggunakan Raspberry Pi. J. Teknol. Elektro 2017, 8, 9, doi:10.22441/jte.v8i1.1365.

[14] Lazaro, A.; Buliali, J.L.; Amaliah, B. Deteksi Jenis Kendaraan di Jalan Menggunakan OpenCV. J. Tek. ITS 2017, 6, doi:10.12962/j23373539.v6i2.23175.

[15] Caesarendra, W.; Triwiyanto, T.; Pandiyan, V.; Glowacz, A.; Permana, S.D.H.; Tjahjowidodo, T. A CNN Prediction Method for Belt Grinding Tool Wear in a Polishing Process Utilizing 3-Axes Force and Vibration Data. Electronics 2021, 10, 1429, doi:10.3390/electronics10121429.

[16] Miranda, N.D.; Novamizanti, L.; Rizal, S.; Elektro, F.T.; Telkom, U. Convolutional Neural Network Pada Klasifikasi Sidik Jari Menggunakan Resnet-50 Classification of Fingerprint Pattern Using Convolutional Neural Network in Clahe Image. J. Tek. Inform. 2020, 1, 61–68.

[17] Nurzaenab; Hadis, M.S.; Angriawan, R. Nilai Optimal Clip Limit Metode Clahe Untuk Meningkatkan Akurasi Pengenalan Wajah Pada Video Cctv. J. INSTEK 2020, 5, 178–187.

[18] Abu Bakar, M.N.; Abdullah, A.H.; Abdul Rahim, N.; Yazid, H.; Misman, S.N.; Masnan, M.J. Rice leaf blast disease detection using multi-level colour image thresholdin. J. Telecommun. Electron. Comput. Eng. 2018, 10, 1–6.

[19] Wong, Y.C.; Lai, J.A.; Ranjit, S.S.S.; Syafeeza, A.R.; Hamid, N.A. Convolutional Neural Network for Object Detection System for Blind People. J. Telecommun. Electron. Comput. Eng. 2019, 11, 1–6.

[20] Manajang, D.; Dompie, S.; Jacobus, A. Implementasi Framework Tensorflow Object Detection Dalam Mengklasifikasi Jenis Kendaraan Bermotor. J. Tek. Inform. 2020, 15, 171–178.

Downloads

Published

2024-10-20

How to Cite

Improved vehicle detection accuracy using CLAHE. (2024). BIS Information Technology and Computer Science, 1, V124006. https://doi.org/10.31603/bistycs.123

Similar Articles

You may also start an advanced similarity search for this article.