PENGARUH RESOLUSI VIDEO TERHADAP AKURASI MENGGUNAKAN ALGORITMA YOLOV4 DALAM DETEKSI CITRA OBJEK PADA CCTV KOTA MALANG
Keywords:
YOLO, CCTV, deteksi kendaraan, deep learningAbstract
Abstrak
Closed-circuit television atau yang biasa dikenal dengan CCTV merupakan sebuah sistem yang digunakan untuk mengawasi suatu lokasi menggunakan kamera sebagai perangkat utama untuk menangkap citra. CCTV biasanya memiliki resolusi yang rendah karena dapat mengurangi biaya penggunaan. Video dengan resolusi yang rendah memiliki kualitas yang kurang baik sehingga objek yang ada pada video sulit dikenali dengan pengamatan manusia. Penelitian ini menganalisis performa algoritma YOLO 4.0 untuk mengenali objek yang ada pada sebuah video CCTV pada kota Malang dengan resolusi rendah yaitu 144p hingga tinggi yaitu 4K. Hasil menujukkan bahwa Bounding Box deteksi objek YOLO berbanding lurus dengan kualitas resolusi CCTV serta akurasi objek yang berhasil dikenali oleh YOLO berbanding lurus dengan kualitas resolusi CCTV.
Abstract
Closed-circuit television or commonly known as CCTV is a system used to monitor a location using a camera as the main device to capture images. CCTV usually has a low resolution because it can reduce usage costs. Video with low resolution has poor quality so that objects in the video are difficult to recognize by human obser- vation. This study analyzes the performance of the YOLO 4.0 algorithm to recognize objects in a CCTV video in Malang with a low resolution of 144p to high, namely 4K. The results show that the Bounding Box detection of YOLO objects is directly proportional to the quality of CCTV resolution and the accuracy of the objects recog- nized by YOLO is directly proportional to the quality of CCTV resolution.
References
N. O. A. Rahman, M. C. Saputra, F. K. Wicaksono, F. A. Bachtiar, and F. Ramdani, “Voronoi diagram: Split nodes analysis of road networks of Malang great area,” 2017 Int. Symp. Geoinformatics, ISyG 2017, vol. 2018-January, pp. 42–47, 2018.
W. M. Saffanah, “Industrialisasi Dan Berkembangnya Kota Malang Pada Awal Abad ke-20,” Agastya J. Sej. Dan Pembelajarannya, vol. 8, no. 2, p. 167, 2018.
W. Yimyam, T. Pinthong, N. Chumuang, and M. Ketcham, “Face Detection Criminals through CCTV Cameras,” Proc. - 14th Int. Conf. Signal Image Technol. Internet Based Syst. SITIS 2018, pp. 351–357, 2018.
C. Nelasari, F. Ramdani, F. Wahabi, S. A. Wicaksono, H. A. Y. Ifada, and M. C. Saputra, “Crime and traffic accident mapping based on street profile analysis method: Case study malang and Batu city,” 2017 Int. Symp. Geoinformatics, ISyG 2017, vol. 2018-Janua, pp. 34–41, 2018.
A. Pribadi, F. Kurniawan, M. Hariadi, and S. M. S. Nugroho, “Urban distribution CCTV for Smart City using decision tree methods,” 2017 Int. Semin. Intell. Technol. Its Appl. Strength. Link Between Univ. Res. Ind. to Support ASEAN Energy Sect. ISITIA 2017 - Proceeding, vol. 2017-Janua, pp. 21–24, 2017.
M. Fraifer and M. Fernstrom, “Smart car parking system prototype utilizing CCTV nodes: A proof of concept prototype of a novel approach towards IoT-concept based smart parking,” 2016 IEEE 3rd World Forum Internet Things, WF-IoT 2016, pp. 649–654, 2017.
I. A. Dahlan, F. Hamami, S. H. Supangkat, and F. Hidayat, “Big Data Implementation of Smart Rapid Transit using CCTV Surveillance,” Proceeding - 2019 Int. Conf. ICT Smart Soc. Innov. Transform. Towar. Smart Reg. ICISS 2019, pp. 1–5, 2019.
F. D. Adhinata, M. Ikhsan, and W. Wahyono, “People counter on CCTV video using histogram of oriented gradient and Kalman filter methods,” J. Teknol. dan Sist. Komput., vol. 8, no. 3, pp. 222–227, 2020.
D. P. Lestari, R. Kosasih, T. Handhika, Murni, I. Sari, and A. Fahrurozi, “Fire Hotspots Detection System on CCTV Videos Using You only Look Once (YOLO) Method and Tiny YOLO Model for High Buildings Evacuation,” Proc. - 2019 2nd Int. Conf. Comput. Informatics Eng. Artif. Intell. Roles Ind. Revolut. 4.0, IC2IE 2019, pp. 87–92, 2019.
Y. Du, N. Pan, Z. Xu, F. Deng, Y. Shen, and H. Kang, “Pavement distress detection and classification based on YOLO network,” Int. J. Pavement Eng., vol. 0, no. 0, pp. 1–14, 2020.
W. Y. Hsu and W. Y. Lin, “Ratio-and-Scale-Aware YOLO for Pedestrian Detection,” IEEE Trans. Image Process., vol. 30, pp. 934–947, 2021.
P. Adarsh, P. Rathi, and M. Kumar, “YOLO v3-Tiny: Object Detection and Recognition using one stage improved model,” 2020 6th Int. Conf. Adv. Comput. Commun. Syst. ICACCS 2020, pp. 687–694, 2020.
H. Wang, X. Tong, and F. Lu, “Deep learning based target detection algorithm for motion capture applications,” J. Phys. Conf. Ser., vol. 1682, no. 1, 2020.
R. A. Asmara, B. Syahputro, D. Supriyanto, and A. N. Handayani, “Prediction of traffic density using yolo object detection and implemented in raspberry pi 3b + and intel ncs 2,” 4th Int. Conf. Vocat. Educ. Training, ICOVET 2020, pp. 391–395, 2020.
S. Jupiyandi et al., “Pengembangan Deteksi Citra Mobil Untuk Mengetahui Jumlah Tempat Parkir Menggunakan Cuda Dan Modified Yolo Development of Car Image Detection To Find Out the Number of Parking Space Using Cuda and Modified Yolo,” J. Teknol. Inf. dan Ilmu Komput., vol. 6, no. 4, pp. 413–419, 2019.
W. Li, Z. Shen, and P. Li, “Crack Detection of Track Plate Based on YOLO,” Proc. - 2019 12th Int. Symp. Comput. Intell. Des. Isc. 2019, pp. 15–18, 2019.
M. B. Ullah, “CPU Based YOLO: A Real Time Object Detection Algorithm,” 2020 IEEE Reg. 10 Symp. TENSYMP 2020, no. June, pp. 552–555, 2020.
J. P. Lin and M. Te Sun, “A YOLO-Based Traffic Counting System,” Proc. - 2018 Conf. Technol. Appl. Artif. Intell. TAAI 2018, pp. 82–85, 2018.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection.”
A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv, 2020.
Downloads
Posted
License
Copyright (c) 2021 Authors retain copyrights
This work is licensed under a Creative Commons Attribution 4.0 International License.
