基于深度学习的OBD端口占用状态自动识别算法

doi:10.13190/j.jbupt.2019-180

北京邮电大学学报 ›› 2019, Vol. 42 ›› Issue (6): 49-57.doi: 10.13190/j.jbupt.2019-180

基于深度学习的OBD端口占用状态自动识别算法

苏东, 余宁梅

西安理工大学自动化与信息工程学院, 西安 710048

收稿日期:2019-09-03 出版日期:2019-12-28 发布日期:2019-11-15
通讯作者: 余宁梅(1963-),女,教授,博士生导师,E-mail:yunm@xaut.edu.cn. E-mail:yunm@xaut.edu.cn
作者简介:苏东(1979-),男,硕士生.

Research on Automatic Recognition Algorithm of OBD Port Occupancy State Based on Deep Learning

SU Dong, YU Ning-mei

School of Automation and Information Engineering, Xi'an University of Technology, Xi'an 710048, China

Received:2019-09-03 Online:2019-12-28 Published:2019-11-15

摘要/Abstract

摘要： 针对光分路器（OBD）端口占用状态不能自动采集的问题，提出了一种改进型YOLOv3算法.增加第4个上采样特征图，提升高分辨率下密集小物体检测敏感度；针对端口固定高宽比特征，利用k-means聚类算法重新确定目标候选框个数和高宽比；提出软非极大值抑制算法，缓解端口靠近且被遮挡情况下引起的漏检、误检；针对4种疑难生产场景下的端口占用状态完成检测.实验结果表明，改进后的YOLOv3准确率达90.12%，相比原YOLOv3提升了5.17%.改进后的算法对于端口类物体具有更高的检测准确率.

关键词: 光分路器, YOLOv3, 聚类算法, 软非极大值抑制, 特征图

Abstract: Because that optical branching device (OBD) port occupancy state can not be automatically acquired, an improved YOLOv3 algorithm was proposed. Firstly, by adding the fourth upsampling feature map, the detection sensitivity of dense small objects at high resolution is increased. Secondly, for characteristics of the fixed height-width ratio of port, the k-means clustering algorithm is used to re-determine the number of target candidate boxes and the height-width ratio. Thirdly, the soft non-maximum suppression algorithm is proposed to alleviate the missed detection and false detection caused by the proximity and occlusion of the port. Finally, four difficult production scenario in the port occupancy state is detected to verify the performance of the improved YOLOv3 algorithm. Experiments show that the accuracy of the improved YOLOv3 is 90.12%, 5.17% higher than the original YOLOv3. In conclusion, the improved algorithm has higher detection accuracy for port-like objects.

Key words: optical branching device, YOLOv3, clustering algorithm, soft non-maximum suppression, feature map

中图分类号:

TN913.7

苏东, 余宁梅. 基于深度学习的OBD端口占用状态自动识别算法[J]. 北京邮电大学学报, 2019, 42(6): 49-57.

SU Dong, YU Ning-mei. Research on Automatic Recognition Algorithm of OBD Port Occupancy State Based on Deep Learning[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2019, 42(6): 49-57.

参考文献

[1] Llorca D F, Arroyo R, Sotelo M A. Vehicle logo recognition in traffic images using HOG features and SVM[C]//16^th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013). Hague:IEEE Press, 2013:2229-2234.
[2] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[3] 闫敬文, 陈宏达, 刘蕾. 高光谱图像分类的研究进展[J]. 光学精密工程, 2019, 27(3):680-693. Yan Jingwen, Chen Hongda, Liu Lei. Overview of hyperspectral image classification[J]. Optics and Precision Engineering, 2019, 27(3):680-693.
[4] Zhang X, Yang W, Tang X, et al. A fast learning method for accurate and robust lane detection using two-stage feature extraction with YOLO v3[J]. Sensors, 2018, 18(12), 4308-4320.
[5] Zhang J P, Zhang J M, Yu S. Hot anchors:a heuristic anchors sampling method in rcnn-based object detection[J]. Sensors, 2018, 18(10):3415-3431.
[6] 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). Las Vegas:IEEE Press, 2016:779-788.
[7] Liu W, Anguelov D, Erhan D, et al. Ssd:single shot multibox detector[C]//European Conference on Computer Vision. Amsterdam:Springer press, 2016:21-37.
[8] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Ohio:IEEE Press, 2014:580-587.
[9] Girshick R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV).Chile:IEEE Press, 2015:1440-1448.
[10] Ren S, He K, Girshick R, et al. Faster r-cnn:towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems. Montreal:MIT press, 2015:91-99.
[11] Joseph Redmon, Ali Farhadi. YOLO9000:better, faster, stronger[C]//2017 IEEE Computer Vision and Pattern Recognition (CVPR).Hawaii:IEEE Press, 2017:6517-6525.
[12] Joseph Redmon, Ali Farhadi. YOLOv3:an incremental improvement[J]. arXiv:Computer Vision and Pattern Recognition, 2018:1804,02767.
[13] Bodla N, Singh B, Chellappa R, et al. Soft-NMS:improving object detection with one line of code[C]//2017 IEEE International Conference on Computer Vision (ICCV). Venice:IEEE Press, 2017:5561-5569.
[14] Ding J, Chen B, Liu H, et al. Convolutional neural network with data augmentation for SAR target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(3):364-368.
[15] Pan S J, Yang Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10):1345-1359.
[16] Lin T Y, Maire M, Belongie S, et al. Microsoft COCO:common objects in context[M]//Computer Vision-ECCV 2014. Zurich:Springer International Publishing, 2014:740-755.
[17] Kingma D P, Ba J. Adam:a method for stochastic optimization[C]//International Conference for Learning Representations. California:arXiv preprint, 2014:1412, 6980.

基于深度学习的OBD端口占用状态自动识别算法

Research on Automatic Recognition Algorithm of OBD Port Occupancy State Based on Deep Learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价

[1]	杨杰张书杰. 基于密集YOLOv3的印刷电路板缺陷识别[J]. 北京邮电大学学报, 2022, 45(5): 42-48.
[2]	袁仁进, 陈刚, 李锋, 魏双建. 基于VSM和Bisecting K-means聚类的新闻推荐方法[J]. 北京邮电大学学报, 2019, 42(1): 114-119.
[3]	王李彧, 孙斌, 秦童. 改进的DBSCAN聚类算法在云任务调度中的应用[J]. 北京邮电大学学报, 2017, 40(s1): 68-71.
[4]	王鑫, 黄忠义. 网络资源中基于K-Means聚类的个性化推荐[J]. 北京邮电大学学报, 2014, 37(s1): 120-124.
[5]	张剑，钱宗珏，寿国础，胡怡红. 在线聚类的网络流量识别[J]. 北京邮电大学学报, 2011, 34(1): 103-106.
[6]	朱思峰刘芳柴争义. 免疫聚类算法在基因表达数据分析中的应用[J]. 北京邮电大学学报, 2010, 33(2): 54-57.
[7]	范琳，王换招，王海. WSN中基于FCM算法的多目标跟踪数据融合[J]. 北京邮电大学学报, 2006, 29(s1): 158-162.