Evolutionary Trajectory and Groundbreaking Innovations in the YOLO Object Detection Algorithm
DOI:
https://doi.org/10.61173/541gkj05Keywords:
Convolutional Neural Networks, single-stage object detection, YOLO, algorithmsAbstract
This paper systematically traces the evolutionary trajectory of the YOLO series (versions 1 through 12) within the field of computer vision object detection. Pioneered by YOLOv1 in 2015, this framework introduced the groundbreaking single-stage detection and regression paradigm, enabling end-to-end detection through its S×S grid architecture. Its Fast YOLO variant demonstrated notable real-time performance advantages on the PASCAL VOC dataset. Subsequent iterations marked significant advancements: v2 incorporated batch normalization and anchor priors, enhancing efficiency with the Darknet-19 backbone while YOLO9000 expanded multi-category recognition capabilities; v3 optimized accuracy through Darknet-53 and multi-scale feature fusion; v4 formalized the modular "Backbone-Neck-Head" design. Enhancements continued from v8 to v12—v8's C2f module bolstered feature fusion, v9 addressed gradient misalignment via its PGI framework, v10 achieved NMS-free end-to-end detection, v11 improved efficiency with the C3k2 module, and v12 enhanced real-time capabilities via the R-ELAN structure. Through iterative development, the series exhibits substantial improvements in detection speed, accuracy, and adaptability to complex scenarios, securing its position as a mainstream solution. Future applications hold considerable promise for leveraging this technology in demanding contexts such as embodied intelligence, medical diagnostics, and tunnel inspection.
References
[1] REDMON J, DIVVALA S, GIRSHICK R, etc. You Only Look Once: Unified, Real-Time Object Detection[J/OL]. arXiv preprint arXiv:1506.02640, 2015.
[2] REDMON J, FARHADI A. YOLO9000: Better, Faster, Stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 7263-7271.
[3] REDMON J, FARHADI A. YOLOv3: An Incremental Improvement[J/OL]. arXiv preprint arXiv:1804.02767, 2018.
[4] LIN T Y, DOLLÁR P, GIRSHICK R, etc. Feature Pyramid Networks for Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 2117-2125.
[5] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: Optimal Speed and Accuracy of Object Detection[J/OL]. arXiv Dean&Francis ISSN 2959-6157 preprint arXiv:2004.10934, 2020.
[6] DO T. Evolution of YOLO algorithm and YOLOv5: The state-of-the-art object detection algorithm[D]. Oulu: Oulu University of Applied Sciences, 2021.
[7] GE Z, LIU S, WANG F, et al. YOLOX: Exceeding YOLO series in 2021[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 8377-8386.
[8] LI C, LI L, JIANG H, et al. YOLOv6: A single-stage object detection framework for industrial applications[J]. arXiv preprint arXiv:2209.02976, 2022.
[9] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 7464-7475.
[10] HUSSAIN M. YOLOv1 to v8: Unveiling each variant— A comprehensive review of YOLO[J]. IEEE Access, 2024, 12: 40573-40627. DOI: 10.1109/ACCESS.2024.3378568.
[11] WANG C Y, YEH I H, LIAO H Y M. YOLOv9: Learning what you want to learn using programmable gradient information[J]. arXiv preprint arXiv:2402.13616, 2024.
[12] WANG A, CHEN H, LIU L, et al. YOLOv10: Real-time end-to-end object detection[J/OL]. 2024.
[13] KHANAM R, HUSSAIN M. YOLOv11: An overview of the key architectural enhancements[J/OL]. 2024.
[14] ALIF M A R, HUSSAIN M. YOLOv12: A breakdown of the key architectural features[J/OL]. 2025.
[15] RAGAB M G, ABDULKADIR S J, MUNEER A, et al. A comprehensive systematic review of YOLO for medical object detection (2018 to 2023)[J]. IEEE Access, 2023.
[16] ZHANG W, GOODWILL J, CHASE T, et al. Evaluation and integration of YOLO models for autonomous crater detection[C]//IEEE Aerospace Conference. 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
