Analisis Perbandingan Metode Yolo Dan Faster R-CNN Dalam Deteksi Objek Manusia
Abstract
Human object detection is an important component in surveillance systems, behavior analysis, and crowd management in public spaces such as stadiums, shopping malls, and terminals. However, the detection process often faces obstacles such as inconsistent lighting, complex backgrounds, and high object density. This study aims to compare the performance of two object detection algorithms, namely YOLOv10 and Faster R-CNN, in detecting humans. The dataset used is uniform and covers a wide range of environmental conditions to ensure fair and objective evaluation. This research involves the stages of data collection, pre-processing, model training, testing, and performance evaluation. The test results show that YOLOv10 has a performance advantage with an mAP50 value of 0.75, higher than that of Faster R-CNN which obtained an AP50 of 0.67. Based on these findings, YOLOv10 is recommended for use in applications that require real-time human detection with a high level of accuracy.
Kata kunci: YOLOV10; Faster R-CNN; Object Detection
Abstrak
Deteksi objek manusia merupakan komponen penting dalam sistem pengawasan, analisis perilaku, dan pengelolaan keramaian di ruang publik seperti stadion, pusat perbelanjaan, dan terminal. Namun, proses deteksi sering menghadapi kendala seperti pencahayaan yang tidak konsisten, latar belakang kompleks, dan kepadatan objek tinggi. Penelitian ini bertujuan buat membandingkan kinerja dua algoritma deteksi objek, yaitu YOLOv10 dan Faster R-CNN, dalam mendeteksi manusia. Dataset yang digunakan bersifat seragam dan mencakup berbagai kondisi lingkungan untuk memastikan evaluasi yang adil dan objektif. Penelitian ini melibatkan tahapan pengumpulan data, pra-pemrosesan, pelatihan model, pengujian, dan evaluasi performa. Hasil pengujian menunjukkan bahwa YOLOv10 memiliki keunggulan performa dengan nilai mAP50 sebesar 0,75, lebih tinggi dibandingkan Faster R-CNN yang memperoleh AP50 sebesar 0,67. Berdasarkan temuan tersebut, YOLOv10 direkomendasikan untuk digunakan dalam aplikasi yang membutuhkan deteksi manusia secara real-time dengan tingkat akurasi tinggi.
Kata kunci: YOLOV10; Faster R-CNN; Deteksi Objek
References
B. Putra, G. Pamungkas, B. Nugroho, and F. Anggraeny, “Deteksi dan Menghitung Manusia Menggunakan YOLO-CNN,” J. Inform. dan Sist. Inf., vol. 2, no. 1, pp. 67–76, 2021.
G. Ş. Gündüz dan G. Işık, “A new YOLO‑based method for real‑time crowd detection from video and performance analysis of YOLO models,” J. Real‑Time Image Process., vol. 20, art. no. 5, pp 1-12, Jan. 2023, doi: 10.1007/s11554‑023‑01276‑w.
D. S. Wirandi, E. D. Permadi, A. Ardiyansyah, D. Prasetio, M. R. Perani, and R. Rosyani, “Kecerdasan buatan alat pendeteksi maling berbasis Arduino menggunakan sensor ultrasonic melalui SMS,” Scientia Sacra: J. Sains, Teknol. dan Masy., vol. 2, no. 2, pp. 841–849, Jun. 2022. [Online]. Available: http://pijarpemikiran.com/index.php/Scientia
T. Diwan, G. Anirudh, and J. V. Tembhurne, “Object detection using YOLO: challenges, architectural successors, datasets and applications,” Multimed Tools Appl, vol. 82, no. 6, pp. 9243–9275, Mar. 2023, doi: 10.1007/s11042-022-13644-y.
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, p. 012032, 2020, doi: 10.1088/1742-6596/1682/1/012032.
C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Jul. 2022, pp. 7464-7475. Available: http://arxiv.org/abs/2207.02696
G. Kucukayan and H. Karacan, “YOLO-IHD: Improved Real-Time Human Detection System for Indoor Drones,” Sensors, vol. 24, no. 3, art. p. 922, Feb. 2024, doi: 10.3390/s24030922.
S. V. Akram et al., “Performance analysis of iot and long-range radio-based sensor node and gateway architecture for solid waste management,” Sensors, vol. 21, no. 8, art. p. 2774, Apr. 2021, doi: 10.3390/s21082774.
N. Mihuandayani, W. H. S. Pesik, S. Mamuaya, A. N. Putra, and E. Mulyaman, “Implementasi YOLOv8 untuk deteksi dan hitung objek manusia dengan convolutional neural network,” J. Ilm. Informatika (BUFFER), vol. 11, no. 1, pp. 27–33, Apr. 2025. [Online]. Available: https://journal.fkom.uniku.ac.id/index.php/buffer
M. A. Mansyur and N. Pratiwi, “Deteksi Manusia Dengan Algoritma YOLO Untuk Pemutaran Audio Otomatis Di Area Tertentu,” JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), vol. 10, no. 1, pp. 667–674, Jan. 2025, doi: 10.29100/jipi.v10i1.5967.
M. G. Ragab et al., “A Comprehensive Systematic Review of YOLO for Medical Object Detection (2018 to 2023),” IEEE Access, vol. 12, pp. 57815–57836, 2024, doi: 10.1109/ACCESS.2024.3386826.
Y. Xu dan Y. Fu, “Complex Indoor Human Detection with You Only Look Once: An Improved Network Designed for Human Detection in Complex Indoor Scenes,” Appl. Sci., vol. 14, no. 22, art. p. 10713, Nov. 2024, doi: 10.3390/app142210713.
J. Zheng, H. Li, Q. Wen, Y. Fu, J. Wu, and H. Chen, “Artificial intelligent recognition for multiple supernumerary teeth in periapical radiographs based on faster R-CNN and YOLOv8,” J Stomatol Oral Maxillofac Surg, p. 102293, 2025, doi: 10.1016/j.jormas.2025.102293.
C. Navamani, S. Sam Daniel, P. Saravanaperumal, R. Thavasi, and S. Venkatesh, “Skin disease type prediction using improved faster R-CNN algorithm,” in Challenges in Information, Communication and Computing Technology, CRC Press, 2024, pp. 109–114. doi: 10.1201/9781003559092-19.
L. Purnama and T. Wahyudi, “Analisa Sentimen Tentang Piala Dunia u-20 Indonesia Menggunakan Algoritma K-Nearest Neighbor,” Jurnal Sains dan Teknologi, vol. 6, no. 2, pp. 217–222, 2024, doi: 10.55338/saintek.v6i2.1397.
Z. Rahman Hakim and S. Sugiyono, “Analisa Sentimen Terhadap Kereta Cepat Jakarta – Bandung Menggunakan Algoritma Naïve Bayes Dan K-Nearest Neighbor,” Jurnal Sains dan Teknologi, vol. 5, no. 3, pp. 939–945, Apr. 2024, doi: 10.55338/saintek.v5i3.1423.
R. Khanam and M. Hussain, “What is YOLOv5: A deep look into the internal features of the popular object detector,” no. 2407, p. 20892, Jul. 2024, [Online]. Available: http://arxiv.org/abs/2407.20892
E. Malagoli dan L. Di Persio, "2D Object Detection: A Survey," Mathematics, vol. 13, no. 6, art. p. 893, Mar. 2025, doi: 10.3390/math13060893.
A. T. Sari, E. Nurlatifah, dan U. Sunan Gunung Djati Bandung, "Penerapan Convolutional Neural Network untuk Mengklasifikasikan Citra Sampah Organik dan Non Organik," J. Inform., vol. 8, no. 2, pp. 120–125, 2024.
A. Sharma, V. Kumar, dan L. Longchamps, "Comparative performance of YOLOv8, YOLOv9, YOLOv10, YOLOv11 and Faster R-CNN models for detection of multiple weed species," Smart Agric. Technol., vol. 9, art. p. 100648, Dec. 2024, doi: 10.1016/j.atech.2024.100648.
How To Cite This :
Refbacks
- There are currently no refbacks.
