雾霾天气车辆检测的改进YOLOv3算法
作者:
中图分类号:

TP391.4

基金项目:

国家自然科学基金资助项目(61164009)。


Improved YOLOv3 algorithm for vehicle detection in hazy weather
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [18]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    针对传统YOLOv3算法中存在检测框定位不精确的问题,提出了一种改进的YOLOv3算法用来重新估计检测框位置,提高智能汽车在雾霾交通环境下的定位精度。首先运用图像去雾算法对采集到的图片进行预处理,然后构造定位置信度替代分类置信度作为参考项来选择估计检测框位置,并改进非极大值抑制(NMS)算法,引入软化非极大值抑制(soft-NMS),最后使用加权平均的方式来更新坐标位置,以达到提高定位精度的目的。实验结果表明,先经过单尺度retinex去雾算法处理图片,再通过改进的YOLOv3算法进行车辆检测,与使用原始的YOLOv3算法进行检测相比平均精度均值mAP(mean average precision)提高了0.44%,在满足检测实时性的同时,能够检测到更多的目标,对检测车辆的定位也更加精确。

    Abstract:

    Traditional YOLOv3 algorithm has the problem of inaccurate detection frame positioning. In this paper, an improved YOLOv3 algorithm was proposed to re-estimate the detection frame position and improve the positioning accuracy of smart cars in hazy traffic environment. Firstly, the collected images were preprocessed using image dehazing algorithms. Then, to improve positioning accuracy, estimated test box position was selected by constructing positioning confidence as the reference to replace classification confidence, and the non-maximum suppression (NMS) algorithm was improved. Finally, the soft-NMS was introduced, and the coordinates were updated using the weighted average. The experimental results show that compared with the original YOLOv3 algorithm, the mAP(mean average precision) of improved YOLOv3 algorithm increased by 0.44%, which could detect more targets and locate the detected vehicles more accurately in real-time detection.

    参考文献
    [1] 刘家旭. 基于HOG特征提取的车辆检测方法研究[D]. 北京:华北电力大学, 2017. Liu J X. Research on vehicle detection method based on HOG feature extraction[D]. Beijing:North China Electric Power University, 2017. (in Chinese)
    [2] 周行, 陈淑荣. 一种基于多特征融合级联分类器的车辆检测算法[J]. 现代计算机(专业版), 2018(17):38-43. Zhou X, Chen S R. A vehicle detection algorithm based on multi-feature fusion and cascade classifier[J]. Modern Computer, 2018(17):38-43. (in Chinese)
    [3] Redmon J, Divvala S, Girshick R, et al. You only look once:unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016:779-788.
    [4] Liu W, Anguelov D, Erhan D, et al. SSD:single shot multibox detector[M]//Computer vision-ECCV 2016. Cham:Springer International Publishing, 2016:21-37.
    [5] Zhang S F, Wen L Y, Bian X, et al. Single-shot refinement neural network for object detection[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. IEEE, 2018:4203-4212.
    [6] Girshick R, Donahue J, Darrell T, et al. Region-based convolutional networks for accurate object detection and segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(1):142-158.
    [7] Girshick R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV), December 7-13, 2015, Santiago, Chile. IEEE, 2015:1440-1448.
    [8] Ren S Q, He K M, Girshick R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
    [9] Redmon J, Farhadi A. YOLOv3:an incremental improvement[EB/OL].[2020-07-15]. https://arxiv.org/abs/1804.02767.
    [10] 冯加明,储茂祥,杨永辉,等.改进YOLOv3算法的车辆信息检测[J/OL].重庆大学学报:1-12[2020-07-10]. http://kns.cnki.net/kcms/detail/50.1044.N.20200619.1503.004.html. Feng J M, Chu M X, Yang Y H, et al. Vehicle information detection based on improved YOLOv3 algorithm[J]. Journal of Chongqing University:1-12[2020-07-10]. http://kns.cnki.net/kcms/detail/50.1044.N.20200619.1503.004.html. (in Chinese)
    [11] 杜金航, 何宁. 基于改进的YOLOv3道路车辆实时检测[J]. 计算机工程与应用, 2020, 56(11):26-32. Du J H, He N. Real-time road vehicles detection based on improved YOLOv3[J]. Computer Engineering and Applications, 2020, 56(11):26-32. (in Chinese)
    [12] 崔文靓, 王玉静, 康守强, 等. 基于改进YOLOv3算法的公路车道线检测方法[J/OL].自动化学报:1-9[2020-07-29]. https://doi.org/10.16383/j.aas.c190178. Cui W J, Wang Y J, Kang S Q, et al. Road lane line detection method based on improved YOLOv3 algorithm[J/OL]. Acta Automatica Sinica:1-9[2020-07-29]. https://doi.org/10.16383/j.aas.c190178. (in Chinese)
    [13] 胡贵桂. 改进的YOLOv3算法在道路环境目标检测中的应用[J]. 汽车实用技术, 2020(5):117-121. Hu G G. The application of improved YOLOv3 algorithm in road environment target detection[J]. Automobile Applied Technology, 2020(5):117-121.(in Chinese)
    [14] 吴仁彪, 冯晓赛, 屈景怡, 等. 雾霾环境下基于PLATE-YOLO的车牌检测方法[J]. 信号处理, 2020, 36(5):666-676. Wu R B, Feng X S, Qu J Y, et al. License plate detection method based on PLATE-YOLO in smog environment[J]. Journal of Signal Processing, 2020, 36(5):666-676. (in Chinese)
    [15] 汪昱东, 郭继昌, 王天保. 一种改进的雾天图像行人和车辆检测算法[J]. 西安电子科技大学学报, 2020, 47(4):70-77. Wang Y D, Guo J C, Wang T B. Algorithm for foggy-image pedestrian and vehicle detection[J]. Journal of Xidian University, 2020, 47(4):70-77. (in Chinese)
    [16] 段世杰,黄华,王鹏飞,等.一种单帧图像的快速去雾方法[J].软件, 2015, 36(5):1-6,15. Duan S J, Huang H, Wang P F, et al. A fast defogging method for single image[J]. Computer Engineering & Software, 2015, 36(5):1-6,15. (in Chinese)
    [17] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016:770-778.
    [18] Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. IEEE, 2017:936-944.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

黄开启,刘小荣,钱艳群,黄茂云.雾霾天气车辆检测的改进YOLOv3算法[J].重庆大学学报,2021,44(12):95-102.

复制
分享
文章指标
  • 点击次数:520
  • 下载次数: 760
  • HTML阅读次数: 905
  • 引用次数: 0
历史
  • 收稿日期:2020-07-31
  • 在线发布日期: 2021-12-16
文章二维码