A Comparative Analysis of Modern Object Detection Algorithms: YOLO vs. SSD vs. Faster R-CNN
Abstract
In recent years, object detection has become a crucial component in various computer vision applications, including autonomous driving, surveillance, and image recognition. This study provides a comprehensive comparative analysis of three prominent object detection algorithms: You Only Look Once (YOLO), Single Shot MultiBox Detector (SSD), and Faster Region-Based Convolutional Neural Networks (Faster R-CNN). The background of this research lies in the growing need for efficient and accurate object detection methods that can operate in real-time. YOLO is known for its speed, SSD for its balance between speed and accuracy, and Faster R-CNN for its high detection accuracy, albeit at a slower pace. The methodology involves implementing these algorithms on a standardized dataset and evaluating their performance based on various metrics, including detection accuracy, processing speed, and computational resource requirements. Each algorithm is tested under similar conditions to ensure a fair comparison. The results indicate that while YOLO excels in real-time applications due to its high speed, SSD offers a middle ground with respectable accuracy and speed, making it suitable for applications requiring a balance of both. Faster R-CNN demonstrates superior accuracy, making it ideal for scenarios where detection precision is paramount, despite its slower performance. This comparative analysis highlights the strengths and weaknesses of each algorithm, providing valuable insights for researchers and practitioners in selecting the appropriate object detection method for their specific needs.
Downloads
References
F. Alsakka, S. Assaf, I. El-Chami, and M. Al-Hussein, “Computer vision applications in offsite construction,†Autom. Constr., vol. 154, p. 104980, Oct. 2023, doi: 10.1016/j.autcon.2023.104980.
X. Chen and S. Wang, “An Object Detection Method Based on Topological Structure,†no. Iccsnt, pp. 1302–1305, 2015.
Y. Huang, Y. Qian, H. Wei, Y. Lu, B. Ling, and Y. Qin, “A survey of deep learning-based object detection methods in crop counting,†Comput. Electron. Agric., vol. 215, p. 108425, Dec. 2023, doi: 10.1016/j.compag.2023.108425.
F. Kistler and E. Andr, “Motion Capturing Empowered Interaction with a Virtual Agent in an Augmented Reality Environment,†2013 IEEE Int. Symp. Mix. Augment. Real., no. October, pp. 1–6, 2013.
U. M. Butt, S. Letchmunan, F. H. Hassan, M. Ali, A. Baqir, and H. H. R. Sherazi, “Spatio-Temporal Crime HotSpot Detection and Prediction: A Systematic Literature Review,†IEEE Access, vol. 8, pp. 166553–166574, 2020, doi: 10.1109/access.2020.3022808.
M. C. S. Santana, L. A. P. Junior, T. P. Moreira, D. Colombo, V. H. C. De Albuquerque, and J. P. Papa, “A Novel Siamese-Based Approach for Scene Change Detection with Applications to Obstructed Routes in Hazardous Environments,†IEEE Intell. Syst., vol. 35, no. 1, pp. 44–53, 2020, doi: 10.1109/MIS.2019.2949984.
Y. Zhang, Y. Yin, and Z. Shao, “An Enhanced Target Detection Algorithm for Maritime Search and Rescue Based on Aerial Images,†Remote Sens., vol. 15, no. 19, 2023, doi: 10.3390/rs15194818.
D. Lin, Z. Zhou, B. Guo, W. Min, and Q. Han, “YOLO-G Abandoned Object Detection Method Combined with Gaussian Mixture Model and GhostNet | 高斯混åˆæ¨¡åž‹ä¸Ž GhostNet 结åˆçš„ YOLO-G é—留物检测方法,†Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal Comput. Des. Comput. Graph., vol. 35, no. 1, pp. 99–107, 2023, doi: 10.3724/SP.J.1089.2023.19276.
L. Wang, Y. Zhao, S. Liu, Y. Li, S. Chen, and Y. Lan, “Precision Detection of Dense Plums in Orchards Using the Improved YOLOv4 Model,†Front. Plant Sci., vol. 13, 2022, doi: 10.3389/fpls.2022.839269.
C. Wang and H. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,†Comput. Vis. Pattern Recognit., 2020.
B. I. N. Liu, W. Zhao, and Q. Sun, “Study Of Object Detection Based On Faster R-CNN,†pp. 7–10, 2016.
S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN : Towards Real-Time Object Detection with Region Proposal Networks,†pp. 1–14.
S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN : Towards Real-Time Object Detection with Region Proposal Networks,†IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137–1149, 2017, doi: 10.1109/TPAMI.2016.2577031.
W. Fang, L. Wang, and P. Ren, “Tinier-YOLO: A Real-Time Object Detection Method for Constrained Environments,†IEEE Access, vol. 8, pp. 1935–1944, 2020, doi: 10.1109/ACCESS.2019.2961959.
J. Ma and O. A. Yakimenko, “The concept of sUAS/DL-based system for detecting and classifying abandoned small firearms,†Def. Technol., vol. 30, pp. 23–31, 2023, doi: 10.1016/j.dt.2023.04.017.
L. Wang, Y. Zhao, S. Liu, Y. Li, S. Chen, and Y. Lan, “Precision Detection of Dense Plums in Orchards Using the Improved YOLOv4 Model,†Front. Plant Sci., vol. 13, Mar. 2022, doi: 10.3389/fpls.2022.839269.
R. Li, X. Zeng, S. Yang, Q. Li, A. Yan, and D. Li, “ABYOLOv4: improved YOLOv4 human object detection based on enhanced multi-scale feature fusion,†EURASIP J. Adv. Signal Process., vol. 2024, no. 1, p. 6, Jan. 2024, doi: 10.1186/s13634-023-01105-z.
D. Ren, T. Sun, C. Yu, and C. Zhou, “Research on Safety Helmet Detection for Construction Site,†in Proceedings - 2021 International Conference on Computer Information Science and Artificial Intelligence, CISAI 2021, 2021, pp. 186–189, doi: 10.1109/CISAI54367.2021.00042.
C. Wan, X. Chang, and Q. Zhang, “Improvement of Road Instance Segmentation Algorithm Based on the Modified Mask R-CNN,†Electronics, vol. 12, no. 22, p. 4699, Nov. 2023, doi: 10.3390/electronics12224699.
W. Liu et al., “SSD : Single Shot MultiBox Detector.â€
D. Saluja, H. Kukreja, A. Saini, D. Tegwal, P. Nagrath, and J. Hemanth, “Analysis and comparison of various deep learning models to implement suspicious activity recognition in CCTV surveillance,†Intell. Decis. Technol., vol. 17, no. 4, pp. 917–942, Nov. 2023, doi: 10.3233/IDT-230469.
Z. Liu and H. Lv, “YOLO_Bolt: a lightweight network model for bolt detection,†Sci. Rep., vol. 14, no. 1, p. 656, Jan. 2024, doi: 10.1038/s41598-023-50527-0.
A. E. Maxwell, T. A. Warner, and L. A. Guillén, “Accuracy assessment in convolutional neural network-based deep learning remote sensing studies—part 1: Literature review,†Remote Sens., vol. 13, no. 13, 2021, doi: 10.3390/rs13132450.
D. Pestana, P. R. Miranda, J. D. Lopes, R. U. I. P. Duarte, and M. P. Véstias, “A Full Featured Configurable Accelerator for Object Detection With YOLO,†IEEE Access, vol. 9, 2021, doi: 10.1109/ACCESS.2021.3081818.
