首页 > 论文 > 激光与光电子学进展 > 57卷 > 14期(pp:141503--1)

交通场景目标检测指标优化研究

Indices Optimizing for Object Detection in Traffic Scenes

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对YOLOv3网络模型在交通场景中的目标检测指标优化问题,通过在网络训练过程中结合多种策略和技巧对模型指标进一步优化,同时提出了一种基于Cutout改进的抗遮挡策略。优化工作不涉及YOLOv3网络结构改动,并且优化后的模型不影响帧率指标。选用PASCAL VOC数据集和KITTI 2D数据集进行对比实验,结果表明,所采用的策略和技巧能够显著提升YOLOv3网络模型性能指标。实验完整代码已公布在以下链接,请点击查看或下载:https://github.com/LiweiDai/YOLOv3-training-optimization-with-applying-ACDC。

Abstract

On the issue about optimizing the indices of object detection for YOLOv3 model in traffic scenes, we make the model indices further optimized by combining various strategies and tricks in the process of training, meanwhile, and we propose an improved anti-occlusion strategy based on Cutout. The optimization does not involve changes of the original YOLOv3 network structure, and there is no impact on FPS after optimizing. Comparison experiments are conducted on both PASCAL VOC and KITTI 2D, the obtained results show that these strategies and tricks can significantly improve the performance of YOLOv3 model. Full code has been released, click to view or download at: https://github.com/LiweiDai/YOLOv3-training-optimization-with-applying-ACDC.

中国激光微信矩阵
补充资料

中图分类号:TP391.4

DOI:10.3788/LOP57.141503

所属栏目:机器视觉

收稿日期:2019-10-09

修改稿日期:2019-12-11

网络出版日期:2020-07-01

作者单位    点击查看

戴立伟:四川大学电气工程学院, 四川 成都 610065
黄山:四川大学电气工程学院, 四川 成都 610065

联系人作者:戴立伟(3376321599@qq.com)

【1】Hua X, Wang X Q, Wang D, et al. Multi-objective detection of traffic scenes based on improved SSD [J]. Acta Optica Sinica. 2018, 38(12): 1215003.
华夏, 王新晴, 王东, 等. 基于改进SSD的交通大场景多目标检测 [J]. 光学学报. 2018, 38(12): 1215003.

【2】Wu X W, Sahoo D. -08-10)[2019-10-09] . https:∥arxiv. 2019, org/abs/1908: 03673.

【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】Redmon J, Farhadi A. YOLO9000:better, faster, stronger . [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017. Honolulu, HI. IEEE. 2017, 6517-6525.

【5】Redmon J. -04-08)[2019-10-09] . https:∥arxiv. 2018, org/abs/1804: 02767.

【6】Liu W, Anguelov D, Erhan D, et al. SSD: single shot MultiBox detector[M]. ∥Computer Vision - ECCV 2016. Cham: , 2016, 21-37.

【7】Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection . [C]∥2017 IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017. Venice. IEEE. 2017, 2999-3007.

【8】Devries T. -08-15)[2019-10-09] . https:∥arxiv. 2017, org/abs/1708: 04552.

【9】Everingham M. Eslami S M A, van Gool L, et al. The pascal visual object classes challenge: a retrospective [J]. International Journal of Computer Vision. 2015, 111(1): 98-136.

【10】Geiger A, Lenz P, Stiller C, et al. Vision meets robotics: the KITTI dataset [J]. The International Journal of Robotics Research. 2013, 32(11): 1231-1237.

【11】Rezatofighi S H, Tsoi N, Gwak J Y, et al. -02-25)[2019-10-09] . https:∥arxiv. 2019, org/abs/1902: 09630.

【12】Zhang H Y, Cissé M, Dauphin Y, et al. -10-25)[2019-10-09] . https:∥arxiv. 2017, org/abs/1710: 09412.

【13】Loshchilov I. -08-13)[2019-10-09] . https:∥arxiv. 2016, org/abs/1608: 03983.

【14】Howard A, Sandler M, Chu G, et al. -05-06)[2019-10-09] . https:∥arxiv. 2019, org/abs/1905: 02244.

【15】Ramachandran P, Zoph B. -10-16)[2019-10-09] . https:∥arxiv. 2017, org/abs/1710: 05941.

引用该论文

Dai Liwei,Huang Shan. Indices Optimizing for Object Detection in Traffic Scenes[J]. Laser & Optoelectronics Progress, 2020, 57(14): 141503

戴立伟,黄山. 交通场景目标检测指标优化研究[J]. 激光与光电子学进展, 2020, 57(14): 141503

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF