Road traffic sign recognition algorithm based on improved YOLOv4

Daxiang LI; Zhongheng SU; Ying LIU

doi:10.37188/OPE.20233109.1366

Journals >Optics and Precision Engineering >Volume 31 >Issue 9 >Page 1366 > Article

Optics and Precision Engineering
Vol. 31, Issue 9, 1366 (2023)

Road traffic sign recognition algorithm based on improved YOLOv4

Daxiang LI, Zhongheng SU^*, and Ying LIU

Author Affiliations

College of Communication and Information Engineering， Xi'an University of Posts and Telecommunication， Xi'an710121， China

show less

DOI: 10.37188/OPE.20233109.1366 Cite this Article

Daxiang LI, Zhongheng SU, Ying LIU. Road traffic sign recognition algorithm based on improved YOLOv4[J]. Optics and Precision Engineering, 2023, 31(9): 1366 Copy Citation Text

show less

Fig. 1. Network structure of YOLOv4

Download full size | View in the Article

Fig. 2. Flow chart of YOLOv4 object recognition

Download full size | View in the Article

Fig. 3. Network structure of improved YOLOv4

Download full size | View in the Article

Fig. 4. Attention-driven scale-aware module

Download full size | View in the Article

Fig. 5. Feature-aligned pyramid convolution module

Download full size | View in the Article

Fig. 6. Feature-aligned module

Download full size | View in the Article

Fig. 7. Size distribution of traffic signs from TT100K

Download full size | View in the Article

Fig. 8. Recognition results of improved YOLOv4 and original YOLOv4

Download full size | View in the Article

类别	名称	型号和参数
硬件	中央处理器	Intel（R）Core（TM） Xeon E5-2640
	内存	128GB
	图像处理器	NVIDIA Titan X（12G）
软件	操作系统	Ubuntu 18.04
	深度学习框架	Pytorch-cuda 1.7.0
	开发语言	Python 3.8.0
	环境管理	Anaconda 3.6.5

Table 1. Experimental software and hardware configuration

View in the Article

Feature map

Receptive field

Anchor box

19×19

Large

（74，80）

（94，100）

（140，146）

38×38

Medium

（37，40）

（46，52）

（58，63）

76×76

Small

（14，18）

（22，24）

（28，32）

Table 2. Anchor size generated by K-means++ algorithm

View in the Article

Methods	Small			Medium			Large			Overall
Methods	P	R	F	P	R	F	P	R	F	P	R	F
Zhu et al.^［32］	81.7	87.4	84.5	90.8	93.6	92.2	90.6	87.7	89.1	87.7	89.6	88.6
Faster R-CNN^［33］	25.2	58.2	35.2	63.8	83.7	72.4	80.7	91.2	85.6	56.7	77.6	65.5
YOLOv4^［20］	83.0	87.5	85.2	91.3	95.2	93.2	90.6	88.2	89.4	88.3	90.3	89.3
FAMN^［34］	88.4	90.1	89.2	94.2	97.2	95.7	92.8	96.1	94.4	91.8	94.3	93.0
DR-CNN^［35］	83.1	89.3	86.1	91.7	94.8	93.2	92.4	89.6	91.0	89.0	91.2	90.1
Noh et al.^［36］	84.8	92.6	88.5	94.2	97.5	95.8	93.3	97.5	95.4	90.6	95.7	93.1
Wang et al.^［37］	87.3	89.4	88.3	92.5	96.4	94.4	92.8	90.5	91.6	90.8	92.3	91.5
TsingNet^［15］	89.0	90.6	89.8	95.2	95.6	95.4	96.2	92.8	94.5	93.4	92.9	93.1
Ours	89.4	92.3	90.8	95.5	96.8	96.1	96.4	97.4	96.9	93.7	94.5	94.1

Table 3. Performance comparison of different methods on TT100K dataset

View in the Article

Methods	ADSA	FAPC	$P_{s}$	$P_{m}$	$P_{l}$	$P_{a l l}$	FPS
YOLOv4 baseline	-	-	83.0	91.3	90.6	88.3	41.36
	$\sqrt$	-	87.3	92.7	93.4	91.2	37.74
	-	$\sqrt$	86.6	93.8	94.5	91.6	38.32
Ours	$\sqrt$	$\sqrt$	89.4	95.5	96.4	93.7	33.17

Table 4. Ablation experiment data

Daxiang LI, Zhongheng SU, Ying LIU. Road traffic sign recognition algorithm based on improved YOLOv4[J]. Optics and Precision Engineering, 2023, 31(9): 1366

Download Citation

Tools

Save the article for my favorites

Paper Information

微信扫一扫：分享

微信扫一扫：分享