基于改进级联卷积神经网络的交通标志识别*

doi:10.19562/j.chinasae.qcgc.2020.09.016

摘要/Abstract

摘要： 自动驾驶场景中交通标志的检测和识别十分重要,为提高自然场景下交通标志检测精度,本文中提出了一种基于Cascade-RCNN改进的交通标志识别算法。首先,针对交通标志这类小目标特殊任务,将 FPN 模块的深层特征信息融合进浅层特征层。其次,改进了目标检测任务中的评价指标IoU,引入目标检测任务的直接评价指标 GIoU 指导定位任务,提高了检测精度。最后,算法在德国交通标志数据集GTSDB下进行了实验验证,以ResNet101为基础特征提取网络,mAP 可达 98.8%,实验结果表明了所提算法的有效性,具有优越的工程实用价值。

关键词: 交通标志检测, 深度学习, 卷积神经网络, 级联RCNN

Abstract: The detection and recognition of traffic signs in automatic driving scene is very important. In order to improve the accuracy of traffic sign detection in the natural scene, this paper proposes an improved traffic sign recognition algorithm based on Cascade-RCNN. Firstly, the deep feature information of FPN module is fused into the shallow feature layer for the special task of small targets such as traffic signs. Secondly, the evaluation index IoU of the target detection task is improved by introducing in the direct evaluation index GIoU of the target detection task to guide the positioning task, which improves the detection accuracy. Finally, the algorithm is verified by experiments in GTSDB, a German traffic sign data set. When the network extraction is based on ResNet101 features, the mAP can reach 98.8%. The experimental results show that the proposed algorithm is effective and has superior engineering practical value

Key words: traffic sign detection, deep learning, convolutional neural network, Cascade-RCNN

王海, 王宽, 蔡英凤, 刘泽, 陈龙. 基于改进级联卷积神经网络的交通标志识别^*[J]. 汽车工程, 2020, 42(9): 1256-1262.

Wang Hai, Wang Kuan, Cai Yingfeng, Liu Ze, Chen Long. Traffic Sign Recognition Based on Improved Cascade Convolution Neural Network[J]. Automotive Engineering, 2020, 42(9): 1256-1262.

参考文献

[1] LIM K H, SENG K P, ANG L, et al. Intra color-shape classification for traffic sign recognition[C]. International Computer Symposium, 2010: 642-647.
[2] BARNES N, ZELINSKY A, FLETCHER L, et al. Real-time speed sign detection using the radial symmetry detector[J]. IEEE Transactions on Intelligent Transportation Systems, 2008, 9(2): 322- 332.
[3] LA ESCALERA A D, MORENO L, SALICHS M A, et al. Road traffic sign detection and classification[J]. IEEE Transactions on Industrial Electronics, 1997, 44(6): 848-859.
[4] FANG C Y, CHEN S W, FUH C S. Road-sign detection and stochastic gradient descent tracking[J]. IEEE Transcations on Vehicular Technology, 2003, 52(5): 1329-1341.
[5] QIAN R, ZHANG B, YUE Y, et al. Robust chinese traffic sign detection and recognition with deep convolutional neural network[C]. International Conference on Natural Computation, 2015: 791- 796.
[6] GREENHALGH J, MIRMEHDI M. Real-time detection and recognition of road traffic signs[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(4): 1498-1506.
[7] MEUTER M , NUNN C , GORMER S M , et al. A decision fusion and reasoning module for a traffic sign recognition system[J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(4):1126-1134.
[8] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv: Computer Vision and Pattern Recognition, 2018.
[9] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]. European Conference on Computer Vision. Springer International Publishing, 2016:21-37.
[10] LIN T Y , GOYAL P , GIRSHICK R , et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 99: 2999-3007.
[11] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]. Computer Vision and Pattern Recognition, 2014: 580-587.
[12] DAI J, LI Y, HE K, et al. R-FCN: object detection via region-based fully convolutional networks[C]. Neural Information Processing Systems, 2016: 379-387.
[13] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]. Neural Information Processing Systems, 2015: 91-99.
[14] CAI Z, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]. Computer Vision and Pattern Recognition, 2018: 6154-6162.
[15] HOUBEN S, STALLKAMP J, SALMEN J, et al. Detection of traffic signs in real-world images: the German traffic sign detection benchmark[C]. International Joint Conference on Neural Network, 2013: 1-8.
[16] LIN T, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]. Computer Vision and Pattern Recognition, 2017: 936-944.
[17] REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C]. Computer Vision and Pattern Recognition, 2019: 658-666.
[18] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]. Computer Vision and Pattern Recognition, 2016: 770-778.
[19] ADELSON E H. Pyramid methods in image processing[J]. Rca Engineer,1984:29.
[20] PARAS. Stochastic gradient descent[J].Optimization,2014,doi:10.1007/978-1-4842-2766-4_8.

基于改进级联卷积神经网络的交通标志识别^*

Traffic Sign Recognition Based on Improved Cascade Convolution Neural Network

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	高泽, 楚遵康, 石稼晟, 林滏, 饶卫雄, 余海燕. 基于图网络的汽车零部件应力场快速预测方法研究[J]. 汽车工程, 2024, 46(1): 170-178.
[2]	管欣,仲昭辉,詹军,奚腾龙,叶昊,高深圳,成健,廖世辉,蔡均. 基于卷积神经网络的汽车操纵稳定性试验类型识别方法[J]. 汽车工程, 2023, 45(9): 1765-1771.
[3]	刘卫国,项志宇,刘锐,李国栋,王子旭. 基于深度学习的端到端车辆运动规划方法研究[J]. 汽车工程, 2023, 45(8): 1343-1352.
[4]	王明,唐小林,杨凯,李国法,胡晓松. 考虑预测风险的自动驾驶车辆运动规划方法[J]. 汽车工程, 2023, 45(8): 1362-1372.
[5]	张雷, 关可人, 丁晓林, 郭鹏宇, 王震坡, 孙逢春. 基于图像识别与动力学融合的路面附着系数估计方法[J]. 汽车工程, 2023, 45(7): 1222-1234.
[6]	赵嘉豪,齐志权,齐智峰,王皓,何磊. 基于轮胎特征点的并行大型车辆朝向角计算[J]. 汽车工程, 2023, 45(6): 1031-1039.
[7]	赵霞,李朝,付锐,葛振振,王畅. 基于深度卷积-Tokens降维优化视觉Transformer的分心驾驶行为实时检测[J]. 汽车工程, 2023, 45(6): 974-988.
[8]	陈妍妍,王海,蔡英凤,陈龙,李祎承. 基于检测的高效自动驾驶实例分割方法[J]. 汽车工程, 2023, 45(4): 541-550.
[9]	兰凤崇,陈继开,陈吉清,蒋心平,李子涵,潘威. 实车数据驱动的锂电池剩余使用寿命预测方法研究[J]. 汽车工程, 2023, 45(2): 175-182.
[10]	李琳辉,张鑫亮,付一帆,连静,马家旭. 基于TC-YOLOv7算法的可见光与红外后融合检测研究[J]. 汽车工程, 2023, 45(12): 2280-2290.
[11]	张小俊,奚敬哲,史延雷,袁安录. 面向路侧视角目标检测的轻量级YOLOv7-R算法[J]. 汽车工程, 2023, 45(10): 1833-1844.
[12]	胡杰,李源洁,耿號,耿黄政,郭雄,易红卫. 基于深度学习的汽车故障知识图谱构建[J]. 汽车工程, 2023, 45(1): 52-60.
[13]	胡杰,徐博远,熊宗权,昌敏杰,郭迪,谢礼浩. 基于多尺度掩码分类域自适应网络的跨域目标检测算法[J]. 汽车工程, 2022, 44(9): 1327-1338.
[14]	毕贵红,谢旭,蔡子龙,骆钊,陈臣鹏,赵鑫. 动态条件下基于深度学习的锂电池容量估计[J]. 汽车工程, 2022, 44(6): 868-878.
[15]	王大方,杜京东,曹江,张梅,赵刚. 面向自动驾驶数据生成的风格迁移网络研究[J]. 汽车工程, 2022, 44(5): 684-690.