航空学报 > 2023, Vol. 44 Issue (14): 327951-327951   doi: 10.7527/S1000-6893.2022.27951

基于梯度差自适应学习率优化的改进YOLOX目标检测算法

宋玉存1, 葛泉波2,3,4(), 朱军龙5, 陆振宇1   

  1. 1.南京信息工程大学 人工智能学院(未来技术学院),南京  210044
    2.南京信息工程大学 自动化学院,南京  210044
    3.南京信息工程大学 江苏省大气环境与装备技术协同创新中心,南京  210044
    4.南京信息工程大学 江苏省智能气象探测机器人工程研究中心,南京  210044
    5.河南科技大学 信息工程学院,洛阳  471000
  • 收稿日期:2022-08-29 修回日期:2022-10-18 接受日期:2022-11-09 出版日期:2022-11-21 发布日期:2022-11-17
  • 通讯作者: 葛泉波 E-mail:qbge_tju@163.com
  • 基金资助:
    国家自然科学基金(62033010);航空科学基金(2019460T5001)

Improved YOLOX object detection algorithm based on gradient difference adaptive learning rate optimization

Yucun SONG1, Quanbo GE2,3,4(), Junlong ZHU5, Zhenyu LU1   

  1. 1.School of Artificial Intelligence/School of Future Technology,Nanjing University of Information Science and Technology,Nanjing  210044,China
    2.School of Automation,Nanjing University of Information Science and Technology,Nanjing  210044,China
    3.Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET),Nanjing University of Information Science and Technology,Nanjing  210044,China
    4.Jiangsu Province Engineering Research Center of Intelligent Meteorological Exploration Robot (C?IMER),Nanjing University of Information Science and Technology,Nanjing  210044,China
    5.College of Information Engineering,Henan University of Science and Technology,Luoyang  471000,China
  • Received:2022-08-29 Revised:2022-10-18 Accepted:2022-11-09 Online:2022-11-21 Published:2022-11-17
  • Contact: Quanbo GE E-mail:qbge_tju@163.com
  • Supported by:
    National Natural Science Foundation of China(62033010);Aeronautical Science Foundation of China(2019460T5001)

摘要:

目标检测一直都是计算机视觉领域最具挑战的问题之一,其广泛应用于人脸识别、自动驾驶和交通检测等任务中。为更进一步提升当前主流目标检测算法的性能表现,提出了基于YOLOX的目标检测改进算法,并在标准的PASCAL VOC 07+12和RSOD数据集上进行实验验证。针对YOLOX目标检测算法主要通过数据增强、改进网络结构和损失函数3方面做出改进,同时提出基于梯度差的自适应学习率优化算法用于训练改进后的YOLOX算法,该优化算法同样适用于其他神经网络优化。在PASCAL VOC 07+12标准数据集上进行实验,与原YOLOX-S进行比较,改进后的YOLOX-S算法的AP由61.63%提升到66.35%,提升效果明显。同时在RSOD标准数据集上进行实验,并与其他主流的YOLO系列算法进行了比较,改进后的YOLOX-S算法在RSOD数据集的AP由69.4%提升到73.2%,提升效果显著。实验表明:针对YOLOX的目标检测做出改进是有效的。

关键词: 目标检测, YOLOX, 神经网络优化, PASCAL VOC, RSOD

Abstract:

Object detection has always been one of the most challenging problems in the field of computer vision, and is widely used in the tasks such as face recognition, autonomous driving and traffic detection. To further improve the performance of current mainstream object detection algorithms, this paper proposes an improved object detection algorithm based on YOLOX, and carries out experiments on the standard PASCAL VOC 07+12 and RSOD datasets. The YOLOX object detection algorithm is improved mainly through data enhancement, improving network structure and loss function. At the same time, an adaptive learning rate optimization algorithm based on gradient difference is proposed to train the improved YOLOX algorithm, which is also suitable for optimization of other neural networks. Experiments are carried out on PASCAL VOC 07+12 standard data sets. Results show that the AP of the improved YOLOX-S algorithm is increased from 61.63% to 66.35% compared with that of the original YOLOX-S algorithm. The improvement effect is obvious. Experiments are also carried out on the RSOD standard data set. The results show that the AP of the improved YOLOX-S algorithm is increased from 69.4% to 73.2% on the RSOD data set, compared with those of other mainstream YOLO series algorithms. The improvement effect is also significant. Experiments show effective improvement of YOLOX’s object detection.

Key words: object detection, YOLOX, neural network optimization, PASCAL VOC, RSOD

中图分类号: