Anchor-Free Traffic Sign Recognition Algorithm Based on Attention Model

Jinghui Chu; Hao Huang; Wei Lü

doi:10.3788/LOP202158.1610020

Journals >Laser & Optoelectronics Progress >Volume 58 >Issue 16 >Page 1610020 > Article

Laser & Optoelectronics Progress
Vol. 58, Issue 16, 1610020 (2021)

Anchor-Free Traffic Sign Recognition Algorithm Based on Attention Model

Jinghui Chu, Hao Huang, and Wei Lü^*

Author Affiliations

School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China

show less

DOI: 10.3788/LOP202158.1610020 Cite this Article Set citation alerts

Jinghui Chu, Hao Huang, Wei Lü. Anchor-Free Traffic Sign Recognition Algorithm Based on Attention Model[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1610020 Copy Citation Text

show less

Fig. 1. Structure of AAFCNN model

Download full size

Fig. 2. Structure of semantic connection path

Download full size

Fig. 3. Different attention modules. (a) Channel attention module; (b) spatial attention module

Download full size

Fig. 4. Structure of attention model

Download full size

Fig. 5. Size distribution of traffic signs in TT100K dataset

Download full size

Fig. 6. Accuracy-recall curves of traffic signs at three scales. (a) Pixel interval of (0,32); (b) pixel interval of (32,96]; (c) pixel interval of (96,400]

Download full size

Fig. 7. Part of visual recognition results of AAFCNN model

Download full size

Method	Backbone	Params /10⁶	Index	S /%	M /%	L /%
Faster R-CNN	ResNet-101	52.2	Recall	72.0	91.3	91.5
			Precision	76.1	87.5	86.1
			F1-score	74.0	89.4	88.7
Faster R-CNN +FPN	ResNet-101	60.1	Recall	86.6	95.5	95.1
			Precision	85.0	92.9	92.3
			F1-score	85.8	94.2	93.7
Ref. [15]		81.2	Recall	87.4	93.6	87.7
			Precision	81.7	90.8	90.6
			F1-score	84.5	92.0	89.1
RetinaNet	ResNeXt-101	94.7	Recall	87.4	95.1	93.1
			Precision	84.3	95.9	94.2
			F1-score	85.8	95.5	93.6
FCOS	ResNeXt-101	89.7	Recall	88.7	95.6	92.4
			Precision	85.6	96.4	93.5
			F1-score	86.8	96.0	93.0
CenterNet	HourglassNet	191.3	Recall	89.7	96.0	92.4
			Precision	90.1	96.7	94.9
			F1-score	89.9	96.3	93.6
AAFCNN	DenseNet-121	48.1	Recall	90.6	95.6	93.1
			Precision	91.2	97.3	96.8
			F1-score	90.9	96.4	94.9

Table 1. Performance comparison of different traffic sign recognition methods

Backbone	Params /10⁶	AP /%
Backbone	Params /10⁶	S	M	L
DenseNet-121	48.1	63.4	80.1	86.1
DenseNet-169	65.4	62.5	79.9	86.1
DenseNet-201	101.4	61.7	79.7	85.7
DenseNet-264	154.8	61.9	80.0	85.0

Table 2. Effect of depth of densely connected network on recognition performance

Location	Params /10⁶	AP /%
Location	Params /10⁶	S	M	L
In coding path	48.1	63.4	80.1	86.1
In decoding path	47.8	62.1	80.0	85.8
Both coding path and decoding path	48.2	62.6	80.0	85.1

Table 3. Effect of location of attention model on recognition performance

Model	Params /10⁶	AP /%
Model	Params /10⁶	S	M	L
Base	14.1	60.8	79.7	85.9
Base+AM	14.2	61.7	79.8	85.1
Base+SCP	47.8	61.9	80.0	87.2
Base+AM+SCP	48.1	63.4	80.1	86.1

Table 4. Performance comparison of each module

Jinghui Chu, Hao Huang, Wei Lü. Anchor-Free Traffic Sign Recognition Algorithm Based on Attention Model[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1610020

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information