基于深度可分离卷积的交通标志识别算法

杨晋生; 杨雁南; 李天骄

doi:10.3788/YJYXS20193412.1191

您当前的位置：

首页 >

文章列表页 >

基于深度可分离卷积的交通标志识别算法

图像处理 | 更新时间：2020-07-16

- 基于深度可分离卷积的交通标志识别算法
- Traffic sign recognition algorithm based on depthwise separable convolutions
- 液晶与显示 2019年34卷第12期页码：1191-1201
- 作者机构：
  
  天津大学微电子学院, 天津 030072
- 作者简介：
  
  [ "杨晋生(1965—), 男, 河北邢台人, 副教授, 硕士生导师, 1999年于天津大学获得硕士学位, 主要从事无线传播理论与技术的研究。E-mail:jsyang@tju.edu.cn" ]
  [ "杨雁南(1993—), 男, 山西阳高人, 硕士研究生, 2016年于武汉理工大学获得学士学位, 主要研究方向为计算机视觉。E-mail:1191547337@qq.com" ]
- 基金信息：
- DOI：10.3788/YJYXS20193412.1191
  中图分类号： TP391
- 收稿日期：2019-08-26，
  
  录用日期：2019-9-26，
  
  纸质出版日期：2019-12-05
- 稿件说明：
移动端阅览
杨晋生, 杨雁南, 李天骄. 基于深度可分离卷积的交通标志识别算法[J]. 液晶与显示, 2019,34(12):1191-1201.

Jin-sheng YANG, Yan-nan YANG, Tian-jiao LI. Traffic sign recognition algorithm based on depthwise separable convolutions[J]. Chinese journal of liquid crystals and displays, 2019, 34(12): 1191-1201.
杨晋生, 杨雁南, 李天骄. 基于深度可分离卷积的交通标志识别算法[J]. 液晶与显示, 2019,34(12):1191-1201. DOI： 10.3788/YJYXS20193412.1191.

Jin-sheng YANG, Yan-nan YANG, Tian-jiao LI. Traffic sign recognition algorithm based on depthwise separable convolutions[J]. Chinese journal of liquid crystals and displays, 2019, 34(12): 1191-1201. DOI： 10.3788/YJYXS20193412.1191.

摘要

针对目前实时交通标志识别中出现的对于中小型目标检测精度低的问题，本文提出了一种基于YOLOv3-tiny的深度可分离卷积（Depthwise Separable Convolutions）的轻量级交通标志检测网络。采用深度可分离卷积构建深度可分离卷积模块代替普通卷积搭建特征提取网络，在保证计算量的前提下更好地提取中小型目标的特征信息。同时，改进多尺度特征融合网络，提高对中小型交通标志的检测精度，使用h-swish激活函数减少因为网络层数增加而丧失的图像特征，实现对多类交通标志的检测。实验结果表明：本算法有效的提高了对中小型交通标志的检测，在验证集上对警告标志（Warining）指示标志（Mandatory）、禁止标志（Prohibitory）3类交通标志进行检测，检测精度（AP）结果分别为98.57%，96.03%，98.04%。检测平均精度（mAP）97.54%、检测速度为201.5 f/s.平均精度较YOLOv3-tiny提高了14.01%。在保证轻型网络的计算量低、检测时效性好的前提下，有效地提升了检测精度。

Abstract

In order to solve the problem of low precision detection for small and medium-sized targets in the real-time traffic sign recognition

a lightweight traffic sign detection network based on YOLOv3-tiny depthwise separable convolution is proposed. In this paper

a deep separable convolution module is constructed by using deep separable convolution instead of the common convolution to construction feature extraction network

the feature information of small and medium-sized targets is better extracted under the premise of ensuring the calculation amount.At the same time

the multi-scale feature fusion network is improved to improve the detection accuracy of small and medium-sized traffic signs. The h-swish activation function is used to reduce the image features lost due to the increase of the number of network layers

and the detection of multiple types of traffic signs is realized.The experimental results show that the algorithm effectively improves the detection of small and medium-sized traffic signs. Warining

mandatory and prohibitory traffic signs are detected on the verification set. The detection accuracy (AP) is 98.57%

96.03% and 98.04% respectively. The average detection accuracy (mAP) was 97.54% and the detection speed was 201.5 f/s. The average accuracy was 14.01% higher than that of YOLOv3-tiny. The algorithm effectively improves the detection accuracy under the premise of ensuring low calculation of light network and good timeliness of detection.

关键词

Keywords

references

MUKHTAR A, XIA L K, TANG T B. Vehicle detection techniques for collision avoidance systems:a review[J]. IEEE Transactions on Intelligent Transportation Systems , 2015, 16(5):2318-2338.

马永杰, 宋晓凤.基于YOLO和嵌入式系统的车流量检测[J].液晶与显示, 2019, 34(6):613-618.

MA Y J, SONG X F. Vehicle flow detection based on YOLO and embedded system[J]. Chinese Journal of Liquid Crystals and Displays , 2019, 34(6):613-618. (in Chinese)

DENG Z D, ZHOU L P. Detection and recognition of traffic planar objects using colorized laser scan and perspective distortion rectification[J]. IEEE Transactions on Intelligent Transportation Systems , 2018, 19(5):1485-1495.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]// Proceedings of the 25 th International Conference on Neural Information Processing Systems . Lake Tahoe, Nevada: Curran Associates Inc, 2012. https://www.researchgate.net/publication/267960550_ImageNet_Classification_with_Deep_Convolutional_Neural_Networks

GIRSHICK R, DONAHUE J, DARRELLT, et al . Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition . Columbus, OH, USA: IEEE, 2014.

GIRSHICK R. Fast R-CNN[C]//IEEE International Conference on Cornputer Vision Santiago, Chile: IEEE, 2015: 1440-1448.

REN S Q, HE K M, GIRSHICKR, 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.

王丹丹, 何东健.基于R-FCN深度卷积神经网络的机器人疏果前苹果目标的识别[J].农业工程学报, 2019, 35(3):156-163.

WANG D D, HE D J.Recognition of apple targets before fruits thinning by robot based on R-FCN deep convolution neural network[J]. Transactions of the Chinese Society of Agricultural Engineering , 2019, 35(3):156-163. (in Chinese)

HUANG S Z, LI X Y, JIANG Z Q, et al . Hyper feature fusion pyramid network for object detection[C]// Proceedings of 2018 IEEE International Conference on Multimedia & Expo Workshops ( ICMEW ). San Diego, CA, USA: IEEE, 2018. https://www.researchgate.net/publication/329317696_Hyper_Feature_Fusion_Pyramid_Network_for_Object_Detection

LIU W, ANGUELOV D, ERHAND, et al . SSD: single shot MultiBox detector[C]// Proceedings of the 14 th European Conference Computer Vision ECCV 2016. The Netherlands: Springer, 2016. https://link.springer.com/chapter/10.1007/978-3-319-46448-0_2

REDMON J, DIVVALA S, GIRSHICK R, et al . You only look once: unified, real-time object detection[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Las Vegas, NV, USA: IEEE, 2016. https://www.researchgate.net/publication/278049038_You_Only_Look_Once_Unified_Real-Time_Object_Detection

VISHWAKARMA A, BHUYAN M K, IWAHORIY. An efficient algorithm for medical image fusion using nonsubsampled shearlet transform[C]//CHAUDHURI B B, KANKANHALLI M S, RAMAN B. Proceedings of 2 nd International Conference on Computer Vision & Image Processing : CVIP 2017, Volume 1. Singapore: Springer, 2018. https://link.springer.com/chapter/10.1007/978-981-10-7895-8_19

JO K U, IM J H, KIMJ, et al . A real-time multi-class multi-object tracker using YOLOv2[C]// Proceedings of 2017 IEEE International Conference on Signal and Image Processing Applications . Kuching, Malaysia: IEEE, 2017: 507-511.

CHOLLET F. Xception: deep learning with depthwise separable convolutions[C]// Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Honolulu, HI, USA: IEEE, 2017. https://arxiv.org/abs/1610.02357

CHIENG H H, WAHID N, ONG P, et al . Flatten-T Swish:a thresholded ReLU-Swish-like activation function for deep learning[J]. International Journal of Advances in Intelligent Informatics , 2018, 4(2):76-86.

ZHANG J M, HUANG Q Q, WU H L, et al . Effective traffic signs recognition via kernel PCA network[J]. International Journal of Embedded Systems , 2018, 10(2):120-125.

EVERINGHAM M, VAN GOOL L, WILLIAMS C K I, et al . The PASCAL visual object classes challenge 2007(VOC2007) results[EB/OL]. http://www.pascal-network.org/challenges/VOC/voc2007/index.html http://www.pascal-network.org/challenges/VOC/voc2007/index.html .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

复杂海背景下的自适应舰船目标检测

改进的GDT-YOLOV 3目标检测算法

基于统计信息的改进滑动平均目标检测算法

TFT-LCD表面Mura缺陷的AOI检测研究进展