A comprehensive review of YOLO object detection algorithms
Haonan Tian
Hunan University of Science and Technology, School of Computer Science and Engineering
DOI: https://doi.org/10.59429/esta.v12i2.10579
Keywords: Deep learning; Computer vision; Object detection; YOLO
Abstract
Object detection technology plays a crucial role in the field of computer vision and has made significant progress in recent years. Among them, the You Only Look Once(YOLO) object detection algorithms have attracted attention due to their speed, accuracy, and end-to-end characteristics. In order to promote the development and practical application of object detection, this paper provides a comprehensive review of the development history, technical principles, strengths, weaknesses, and future development directions of the YOLO object detection algorithms. Firstly, the technical principles of the YOLO algorithms are detailed, including the end-to-end detection frameworks based on a single neural network and the concept of dense prediction. Then, this paper reviews the evolution of YOLO algorithms, from YOLOv1 to the latest version, and combs their key technical innovations and performance improvements.Finally, we discuss the potential research directions for the future.
References
[1]Zou Z, Chen K, Shi Z, et al. Object detection in 20 years: A survey[J]. Proceedings of the IEEE, 2023, 111(3): 257-276.
[2]REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Piscataway, NJ: IEEE, 2016: 779-788.
[3]Redmon J, Farhadi A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 7263-7271.
[4]Redmon J, Farhadi A. Yolov3: An incremental improvement[J]. arXiv preprint arXiv:1804.02767, 2018.
[5]Bochkovskiy A, Wang C Y, Liao H Y M. Yolov4: Optimal speed and accuracy of object detection[J]. arXiv preprint arXiv:2004.10934, 2020.
[6]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.