基于YOLO v3算法改进的交通标志识别算法

doi:10.11772/j.issn.1001-9081.2020010062

计算机应用 ›› 2020, Vol. 40 ›› Issue (8): 2472-2478.DOI: 10.11772/j.issn.1001-9081.2020010062

• 应用前沿、交叉与综合 • 上一篇

基于YOLO v3算法改进的交通标志识别算法

江金洪^1,2, 鲍胜利^1,2, 史文旭^1,2, 韦振坤^1,2

1. 中国科学院成都计算机应用研究所, 成都 610041;
2. 中国科学院大学, 北京 100049

收稿日期:2020-02-04 修回日期:2020-03-31 出版日期:2020-08-10 发布日期:2020-03-31
通讯作者: 江金洪(1994-),男,四川绵阳人,硕士研究生,主要研究方向:深度学习、数据挖掘,1127515524@qq.com
作者简介:鲍胜利(1973-),男,安徽黄山人,研究员级高级工程师,博士研究生,主要研究方向:智能信息处理、深度学习;史文旭(1995-),男,河南焦作人,硕士研究生,主要研究方向:深度学习、智能算法;韦振坤(1995-),男,安徽阜阳人,博士研究生,主要研究方向:强化学习、机器学习。
基金资助:
四川省科技厅重点研发项目（2018SZ0040）；四川省新一代人工智能重大专项（2018GZDZX0036）。

Improved traffic sign recognition algorithm based on YOLO v3 algorithm

JIANG Jinhong^1,2, BAO Shengli^1,2, SHI Wenxu^1,2, WEI Zhenkun^1,2

1. Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu Sichuan 610041, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2020-02-04 Revised:2020-03-31 Online:2020-08-10 Published:2020-03-31
Supported by:
This work is partially supported by the Key Research and Development Program of Science and Technology Commission of Sichuan Province (2018SZ0040), the Major Project of New Generation Artificial Intelligence in Sichuan Province (2018GZDZX0036).

摘要/Abstract

摘要： 针对目前交通标志识别任务在使用深度学习算法时存在模型参数量大、实时性较差和准确率较低的问题，提出了基于YOLO v3改进的交通标志识别算法。该算法首先将深度可分离卷积引入YOLO v3算法的特征提取层，将卷积过程分解为深度卷积、逐点卷积两部分，实现通道内卷积与通道间卷积之间的分离，从而保证了在较高识别准确率的基础上极大地减少了算法模型参数数量以及计算量。其次，在损失函数设计上使用广义交并比（GIoU）损失替换均方误差（MSE）损失，将评测标准量化为损失，解决了MSE损失存在的优化不一致和尺度敏感的问题，同时将Focal损失加入到损失函数以解决正负样本严重不均衡的问题，通过降低大量简单背景类的权重使得算法更专注于检测前景类。将该算法应用于交通标志任务中的结果表明，在TT100K数据集上，该算法的平均精度均值（mAP）指标达到了89%，相较于YOLO v3算法提升了6.6个百分点，且其参数量仅为原始YOLO v3算法的1/5左右，每秒帧数（FPS）亦比YOLO v3算法提升了60%。该算法在极大地减少模型参数量和计算量的同时，提高了检测速度和检测精度。

关键词: 交通标志识别, YOLO v3算法, 广义交并比, 深度可分离卷积, 损失函数, Focal损失

Abstract: Concerning the problems of large number of parameters, poor real-time performance and low accuracy of traffic sign recognition algorithms based on deep learning, an improved traffic sign recognition algorithm based on YOLO v3 was proposed. First, the depthwise separable convolution was introduced into the feature extraction layer of YOLO v3, as a result, the convolution process was decomposed into depthwise convolution and pointwise convolution to separate intra-channel convolution and inter-channel convolution, thus greatly reducing the number of parameters and the calculation of the algorithm while ensuring a high accuracy. Second, the Mean Square Error (MSE) loss was replaced by the GIoU (Generalized Intersection over Union) loss, which quantified the evaluation criteria as a loss. As a result, the problems of MSE loss such as optimization inconsistency and scale sensitivity were solved. At the same time, the Focal loss was also added to the loss function to solve the problem of severe imbalance between positive and negative samples. By reducing the weight of simple background classes, the new algorithm was more likely to focus on detecting foreground classes. The results of applying the new algorithm to the traffic sign recognition task show that, on the TT100K (Tsinghua-Tencent 100K) dataset, the mean Average Precision (mAP) of the algorithm reaches 89%, which is 6.6 percentage points higher than that of the YOLO v3 algorithm; the number of parameters is only about 1/5 of the original YOLO v3 algorithm, and the Frames Per Second (FPS) is 60% higher than YOLO v3 algorithm. The proposed algorithm improves detection speed and accuracy while reducing the number of model parameters and calculation.

Key words: traffic sign recognition, YOLO v3 algorithm, Generalized Intersection over Union (GIoU), depthwise separable convolution, loss function, Focal loss

中图分类号:

TP391.4

江金洪, 鲍胜利, 史文旭, 韦振坤. 基于YOLO v3算法改进的交通标志识别算法[J]. 计算机应用, 2020, 40(8): 2472-2478.

JIANG Jinhong, BAO Shengli, SHI Wenxu, WEI Zhenkun. Improved traffic sign recognition algorithm based on YOLO v3 algorithm[J]. Journal of Computer Applications, 2020, 40(8): 2472-2478.

参考文献

[1] 于硕. 交通标志识别技术综述[J]. 科技资讯, 2019, 17(6):15-16. (YU S. Overview of traffic sign recognition technology[J]. Science and Technology Information, 2019, 17(6):15-16.)
[2] FLEYEH H, BISWAS R, DAVAMI E. Traffic sign detection based on AdaBoost color segmentation and SVM classification[C]//Proceedings of the 2013 Eurocon. Piscataway:IEEE, 2013:2005-2010.
[3] CREUSEN I M, WIJNHOVEN R G J, HERBSCHLEB E, et al. Color exploitation in hog-based traffic sign detection[C]//Proceedings of the 2010 IEEE International Conference on Image Processing. Piscataway:IEEE, 2010:2669-2672.
[4] 杜影丽,贾永红,韩静敏. 自然场景车载视频道路交通限速标志的检测与识别方法[J]. 测绘地理信息, 2018, 43(2):32-34, 37. (DU Y L, JIA Y H, HAN J M. A detection and recognition method for traffic speed limit signs based on vehicle videos[J]. Journal of Geomatics, 2018, 43(2):32-34, 37.)
[5] 李志军,崔利娟. 基于深度森林的交通标志识别方法研究[J]. 工业控制计算机, 2019, 32(5):114-115, 120. (LI Z J, CUI L J. Research on traffic sign recognition algorithm based on deep forest[J]. Industrial Control Computer, 2019, 32(5):114-115, 120.)
[6] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Cambridge, MA:MIT Press, 2012, 1:1097-1105.
[7] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3):211-252.
[8] REN S, HE K, 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, 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.
[10] 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.
[11] SERMANET P, LECUN Y. Traffic sign recognition with multi-scale convolutional networks[C]//Proceedings of the 2011 International Joint Conference on Neural Networks. Piscataway:IEEE, 2011:2809-2813.
[12] STALLKAMP J, SCHLIPSING M, SALMEN J, et al. Man vs. computer:benchmarking machine learning algorithms for traffic sign recognition[J]. Neural Networks, 2012, 32:323-332.
[13] ZHU Z, LIANG D, ZHANG S, et al. Traffic-sign detection and classification in the wild[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:2110-2118.
[14] WANG G, XIONG Z, LIU D, et al. Cascade mask generation framework for fast small object detection[C]//Proceedings of the 2018 IEEE International Conference on Multimedia and Expo. Piscataway:IEEE, 2018:1-6.
[15] REDMON J, FARHADI A. YOLO v3:an incremental improvement[EB/OL].[2019-04-08].https://arxiv.org/pdf/1804.02767.pdf.
[16] CHOLLET F. Xception:deep learning with depthwise separable convolutions[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:1800-1807.
[17] REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union:a metric and a loss for bounding box regression[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2019:658-666.
[18] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2):318-327.
[19] 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.
[20] 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.
[21] 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.

基于YOLO v3算法改进的交通标志识别算法

Improved traffic sign recognition algorithm based on YOLO v3 algorithm

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]	王月, 江逸茗, 兰巨龙. 基于改进三元组网络和K近邻算法的入侵检测[J]. 计算机应用, 2021, 41(7): 1996-2002.
[2]	贾鹤鸣, 郎春博, 姜子超. 基于轻量级卷积神经网络的植物叶片病害识别方法[J]. 计算机应用, 2021, 41(6): 1812-1819.
[3]	陆鑫伟, 余鹏飞, 李海燕, 李红松, 丁文谦. 基于注意力自身线性融合的弱监督细粒度图像分类算法[J]. 计算机应用, 2021, 41(5): 1319-1325.
[4]	曹建芳, 田晓东, 贾一鸣, 闫敏敏. 改进DeepLabV3+模型在壁画分割中的应用[J]. 计算机应用, 2021, 41(5): 1471-1476.
[5]	胡嵽, 冯子亮. 基于深度学习的轻量级道路图像语义分割算法[J]. 计算机应用, 2021, 41(5): 1326-1331.
[6]	王永金, 左羽, 吴恋, 崔忠伟, 赵晨洁. 基于注意力机制的图像超分辨率重建[J]. 计算机应用, 2021, 41(3): 845-850.
[7]	罗晖, 贾晨, 芦春雨, 李健. 基于改进Faster R-CNN的钢轨踏面块状伤损检测方法[J]. 计算机应用, 2021, 41(3): 904-910.
[8]	蒋宁, 方景龙, 杨庆. 基于单点多盒检测器的全局-局部层级的域适应目标检测[J]. 计算机应用, 2021, 41(2): 517-522.
[9]	袁野, 谭晓阳. 复杂环境下的冰箱金属表面缺陷检测[J]. 计算机应用, 2021, 41(1): 270-274.
[10]	石陆魁, 马红祺, 张朝宗, 樊世燕. 基于改进残差结构的肺结节检测方法[J]. 计算机应用, 2020, 40(7): 2110-2116.
[11]	陈立潮, 郑佳敏, 曹建芳, 潘理虎, 张睿. 基于胶囊网络的智能交通标志识别方法[J]. 计算机应用, 2020, 40(4): 1045-1049.
[12]	杨文霞, 王萌, 张亮. 基于密集连接块U-Net的语义人脸图像修复[J]. 计算机应用, 2020, 40(12): 3651-3657.
[13]	李卉, 杨志霞. 基于Rescaled Hinge损失函数的多子支持向量机[J]. 计算机应用, 2020, 40(11): 3139-3145.
[14]	李翠锦, 瞿中. 基于深度学习的图像边缘检测算法综述[J]. 计算机应用, 2020, 40(11): 3280-3288.
[15]	邓天民, 方芳, 周臻浩. 基于改进空间金字塔池化卷积神经网络的交通标志识别[J]. 计算机应用, 2020, 40(10): 2872-2880.