叶佳林;苏子毅;马浩炎;袁夏;赵春霞;

• 1:南京理工大学计算机科学与工程学院

摘要(Abstract)：

随着交管部门对非机动车监管力度的增强,在道路交通监控视频中检测和识别非机动车将逐渐成为电子交警系统的必备功能。由于非机动车密度大,容易互相遮挡,且在监控视频中所占面积往往较小,容易出现检测定位不准确和漏检等问题。针对非机动车检测定位不准确和漏检问题,基于YOLOv3,提出一种改进的非机动车检测与识别模型,通过设计新的特征融合结构降低非机动车漏检率,使用GIOU损失提高定位准确度。实验结果表明,所提出的改进模型在自建真实复杂场景非机动车数据集上取得了优于YOLOv3的检测结果,将检测的平均检测准确率(mAP)提高了3.6%。

关键词(KeyWords)： 非机动车检测;YOLOv3;特征融合;GIOU损失

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金（61773210）;; 江苏省研究生科研与实践创新计划项目（SJCX20_0117）

作者(Author): 叶佳林;苏子毅;马浩炎;袁夏;赵春霞;

Email:

DOI:

参考文献(References)：

• [1]潘晓东，马小翔，赵晓翠，信号交叉口非机动车骑行特性及其安全性实验研究[J].交通科学工程，2010,26(4):60-64.
• [2] TAIGMAN Y,YANG M,RANZATO M,et al.De-epface:Closing the gap to human-level per-formance in face verification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2014:1701-1708.
• [3] MA X Y,GRIMSON W E L.Edge-based rich representation for vehicle classification[C]//Proceedings of the 10th IEEE International Conference on Computer Vision,2005:1185-1192.
• [4] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate objectdetection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2014:580-587.
• [5] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE Conference on Computer Vision,2015:1440-1448.
• [6] REN S,HE K,GIRSHICK R,et al.Faster RCNN:Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems,2015:91-99.
• [7] 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,2016:779-788.
• [8] LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shot multibox detector[C]//Proceedings of European Conference on Computer Vision,2016:21-37.
• [9] LAW H,DENG J.Cornernet:Detecting objects as paired keypoints[C]//Proceedings of the 15th European Conference on Computer Vision(ECCV).Munich,Germany:Springer,2018:734-750.
• [10] FCOSTIAN Z,SHEN C,CHEN H,et al.F-COS:Fully convolutional one-stage object detection[J].arXiv:1904.01355,2019.
• [11] REDMON J,FARHADI A.YOLOv3:An incremental improvement[J].arXiv:1804.02767,2018.
• [12] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[C]//Proceedings of International Conference on Neural Information Processing Systems,2012:1097-1105.
• [13] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of Conference on Computer Vision and Pattern Recognition,2015:770-778.
• [14] REZATOFIGHI H,TSOI N,GWAK J,et al.Generalized inter section over union:A metric and a loss for bounding box regression[C]//Proceedings of the IEEE Conference on Conference on Computer Vision and Pattern Recognition,2019.
• [15]张素洁，赵怀慈.最优聚类个数和初始聚类中心点选取算法研究[J].计算机应用研究，2017,34(6):1617-1620.