基于Faster-RCNN的车牌检测

被引：10

作者：

艾曼

机构：

[1] 华中科技大学自动化学院

来源：

计算机与数字工程 | 2020年 / 48卷 / 01期

关键词：

车牌检测; Faster-RCNN; ZF; VGG-16; ResNet-101;

D O I：

暂无

中图分类号：

TP391.41 []; U495 [电子计算机在公路运输和公路工程中的应用];

学科分类号：

080203 ; 0838 ;

摘要：

车牌识别是智能交通中非常重要的应用,而车牌检测又是车牌识别的关键。针对现有的车牌识别系统在遇到复杂条件,例如暗光、遮挡、多车牌、能见度低等情况时,难以有效地定位车牌,提出了基于Faster-RCNN目标检测模型与ZF、VGG-16以及ResNet-101 3种卷积神经网络分别结合的方法。由于车牌没有公开的数据库,在自己准备的12740张车牌图像上进行实验,结果显示基于Faster-RCNN与ResNet-101结合的模型的准确率达到了97.2%,高于其余两种结合模型,明显优于传统的车牌检测方法,并避免了复杂的预处理,具有较好的实用性。

引用

页码：174 / 177

页数：4

共 39 条

[31] Geodesic active contours
Caselles, V
Kimmel, R
Sapiro, G
[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 1997, 22 (01) : 61 - 79
[32] Fast R-CNN. Girshick,Ross. IEEE international conference on computer vision(ICCV) . 2015
[33] Faster RCNN Towards Real-Time Object Detection with Region Proposal Networks. Ren S,He K,Girshick R et al. Neural Information Processing Systems (NIPS) . 2015
[34] You Only Look Once:Unified,Real-Time Object Detection. REDMON J,DIVVALA S,GIRSHICK R,et al. IEEE Conference on Computer Vision&Pattern Recognition 2016 . 2016
[35] Rich feature hierarchies for accurate object detection and semantic segmentation. Girshick R,Donahue J,Darrell T et al. Computer Vision and Pattern Recognition . 2014
[36] BING:Binarized Normed Gradients for Objectness Estimation at 300fps. Cheng M M,Zhang Z,Lin W Y,et al. Computer Vision and Pattern Recognition. . 2014
[37] SSD:Single Shot Multi Box Detector. Liu W,Anguelov D,Erhan D.et al. Conference on Computer Vision . 2016
[38] Faster RCNN Towards Real-Time Object Detection with Region Proposal Networks. Ren S,He K,Girshick R et al. Neural Information Processing Systems (NIPS) . 2015
[39] SSD:Single Shot Multi Box Detector. Liu W,Anguelov D,Erhan D.et al. Conference on Computer Vision . 2016

← 1 2 3 4 →