基于RetinaNet改进的车辆信息检测

doi:10.11772/j.issn.1001-9081.2019071262

计算机应用 ›› 2020, Vol. 40 ›› Issue (3): 854-858.DOI: 10.11772/j.issn.1001-9081.2019071262

• 虚拟现实与多媒体计算 • 上一篇下一篇

基于RetinaNet改进的车辆信息检测

刘革, 郑叶龙, 赵美蓉

天津大学精密测试技术及仪器国家重点实验室, 天津 300072

收稿日期:2019-07-19 修回日期:2019-09-27 出版日期:2020-03-10 发布日期:2019-10-25
通讯作者: 郑叶龙
作者简介:刘革(1994-),男,湖北襄阳人,硕士研究生,主要研究方向:计算机视觉;郑叶龙(1987-),男,浙江温州人,讲师,博士,主要研究方向:机器视觉、力学测量;赵美蓉(1967-),女,天津人,教授,博士,主要研究方向:机器视觉、力学测量。
基金资助:
国家自然科学基金资助项目（51805367）；天津市自然科学基金资助项目（18JCQNJC04800，18JCZDJC31800）。

Vehicle information detection based on improved RetinaNet

LIU Ge, ZHENG Yelong, ZHAO Meirong

State Key Laboratory of Precision Testing Technology and Instruments, Tianjin University, Tianjin 300072, China

Received:2019-07-19 Revised:2019-09-27 Online:2020-03-10 Published:2019-10-25
Supported by:
This work is partially supported by the National Natural Science Foundation of China (51805367), the Tianjin Natural Science Foundation (18JCQNJC04800, 18JCZDJC31800).

摘要/Abstract

摘要： 移动端计算力不足和存储有限导致车辆信息检测模型精度不高、速度较慢。针对这一问题，提出一种基于RetinaNet改进的车辆信息检测算法。首先，开发新的车辆信息检测框架，将特征金字塔网络（FPN）模块的深层特征信息融合进浅层特征层，以MobileNet V3为基础特征提取网络；其次，引入目标检测任务的直接评价指标GIoU指导定位任务；最后，使用维度聚类算法找出Anchor的较好尺寸并匹配到相对应的特征层。与原始RetinaNet目标检测算法的对比实验表明，所提算法在车辆信息检测数据集上的精度有10.2个百分点的提升。以MobileNet V3为基础网络时平均准确率均值（mAP）可达97.2%且在ARM v7设备上单帧前向推断用时可达100 ms。实验结果表明，所提方法能够有效提高移动端车辆信息检测算法性能。

关键词: 卷积神经网络, 目标检测, 维度聚类, 特征融合, GIoU

Abstract: The lack of computational power and limited storage of the mobile terminals lead to the low accuracy and slow speed of vehicle information detection models. Therefore, an improved vehicle information detection algorithm based on RetinaNet was proposed to solve this problem. Firstly, a new vehicle information detection framework was developed, and the deep feature information of the FPN （Feature Pyramid Network） module was merged into the shallow feature layer, and MobileNet V3 was used as the basic feature extraction network. Secondly, the direct evaluation index of target detection task——GIoU (Generalized Intersection over Union) was introduced to guide the positioning task. Finally, the dimension clustering algorithm was used to find the better size of Anchors and match them to the corresponding feature layers. Compared with the original RetinaNet target detection algorithm, the proposed algorithm has the accuracy improved by 10.2 percentage points on the vehicle information detection dataset. When using MobileNet V3 as the basic network, the mAP （mean Average Precision） can reach 97.2% and the forward inference time of single frame can reach 100 ms on ARM v7 devices. The experimental results show that the proposed method can effectively improve the performance of mobile vehicle information detection algorithms.

Key words: Convolutional Neural Network (CNN), target detection, dimension clustering, feature fusion, Generalized Intersection over Union (GIoU)

中图分类号:

TP391.4

刘革, 郑叶龙, 赵美蓉. 基于RetinaNet改进的车辆信息检测[J]. 计算机应用, 2020, 40(3): 854-858.

LIU Ge, ZHENG Yelong, ZHAO Meirong. Vehicle information detection based on improved RetinaNet[J]. Journal of Computer Applications, 2020, 40(3): 854-858.

参考文献

[1] 徐子豪, 黄伟泉, 王胤. 基于深度学习的监控视频中多类别车辆检测[J]. 计算机应用,2019,39(3):700-705. (XU Z H, HUANG W G,WANG Y. Multi-class vehicle detection in surveillance video based on deep learning[J]. Journal of Computer Applications,2019,39(3):700-705.)
[2] 王卫东, 程丹. 监控场景下的实时车辆检测方法[J]. 电子测量与仪器学报,2018,32(7):83-88. (WANG W D,CHENG D. Real-time vehicle detection method for video surveillance[J]. Journal of Electronic Measurement and Instrument,2018,32(7):83-88.)
[3] LIU Y,TIAN B,CHEN S,et al. A survey of vision-based vehicle detection and tracking techniques in ITS[C]//Proceedings of 2013 IEEE International Conference on Vehicular Electronics and Safety. Piscataway:IEEE,2013:72-77.
[4] KIM H,LEE Y,YIM B,et al. On-road object detection using deep neural network[C]//Proceedings of the 2016 IEEE International Conference on Consumer Electronics-Asia. Piscataway:IEEE, 2016:1-4.
[5] LAW H,DENG J. CornerNet:detecting objects as paired keypoints[C]//Proceedings of the 2018 European Conference on Computer Vision,LNCS 11218. Cham:Springer,2018:765-781.
[6] ZHOU X,ZHUO J,KRAHENBUHL P. Bottom-up object detection by grouping extreme and center points[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:850-859.
[7] DUAN K,BAI S,XIE L,et al. CenterNet:keypoint triplets for object detection[EB/OL].[2019-04-19]. https://arxiv.org/pdf/1904.08189.pdf.
[8] GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2015:1440-1448.
[9] REN S,HE K,GIRSHICK R,et al. Faster R-CNN:towards realtime object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(6):1137-1149.
[10] DAI J,LI Y,HE K,et al. R-FCN:object detection via regionbased fully convolutional networks[C]//Advances in Neural Information Processing Systems 29. Barcelona:NIPS, 2016:379-387.
[11] REDMON J,DIVVALA S,GIRSHICK R,et al. You only look once:unified,real-time object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2016:779-788.
[12] REDMON J,FARHADI A. YOLO9000:better,faster,stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2017:6517-6525.
[13] LIU W,ANGUELOV D,ERHAN D,et al. SSD:single shot multibox detector[C]//Proceedings of the 2016 European Conference on Computer Vision,LNCS 9905. Cham:Springer,2016:21-37.
[14] FU C,LIU W,RANGA A,et al. DSSD:deconvolutional single shot detector[EB/OL].[2019-01-17]. https://arxiv.org/pdf/1701.06659.pdf.
[15] LI Z,ZHOU F. FSSD:feature fusion single shot multibox detector[EB/OL].[2018-12-17]. https://arxiv.org/pdf/1712.00960.pdf.
[16] LIN T Y,GOYAL P,GIRSHICK R,et al. Focal loss for dense object detection[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE,2017:2999-3007.
[17] HOWARD A,SANDLER M,CHU G,et al. Searching for MobileNetV3[EB/OL].[2019-05-19]. https://arxiv.org/pdf/1905.02244.pdf.
[18] REZATOFIGHI H,TSOI N,GWAK J Y,et al. Generalized intersection over union:a metric and a loss for bounding box regression[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:658-666.
[19] ARTHUR D,VASSILVITSKII S. K-means++:the advantages of careful seeding[C]//Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms. New York:ACM,2007:1027-1035.
[20] LIN T Y,DOLLÁR P,GIRSHICK R,et al. Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2017:936-944.
[21] EVERINGHAM M,VAN GOOL L,WILLIAMS C K I,et al. The pascal Visual Object Classes(VOC)challenge[J]. International Journal of Computer Vision,2010,88(2):303-338.
[22] HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:770-778.
[23] SAINATH T N,KINGSBURY B,SAON G,et al. Deep convolutional neural networks for large-scale speech tasks[J]. Neural Networks,2015,64:39-48.

基于RetinaNet改进的车辆信息检测

Vehicle information detection based on improved RetinaNet

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	马佳良, 陈斌, 孙晓飞. 基于改进的Faster R-CNN的通用目标检测框架[J]. 计算机应用, 2021, 41(9): 2712-2719.
[2]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[3]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[4]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[5]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[6]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[7]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[8]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[9]	陈静, 毛莺池, 陈豪, 王龙宝, 王子成. 基于改进单点多盒检测器的大坝缺陷目标检测方法[J]. 计算机应用, 2021, 41(8): 2366-2372.
[10]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[11]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[12]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[13]	王伟, 赵尔平, 崔志远, 孙浩. 基于HowNet义原和Word2vec词向量表示的多特征融合消歧方法[J]. 计算机应用, 2021, 41(8): 2193-2198.
[14]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[15]	周险兵, 樊小超, 任鸽, 杨勇. 基于多层次语义特征的英文作文自动评分方法[J]. 计算机应用, 2021, 41(8): 2205-2211.