Real-Time Semantic Segmentation Algorithm Based on Feature Fusion Technology

Fig. 5. Example results of proposed segmentation algorithm based on Cityscapes dataset. (a) Original image;(b) true segmentation result; (c) result of proposed algorithm

Download full size

Table 1. Spatial information network structure

View table

Table 1. Spatial information network structure

Structure	Input	Convolution size	Mapping	Output
Conv1	W×H×3	3×7×7×64	ReLU	$\begin{matrix} \frac{1}{2} \end{matrix}$ W× $\begin{matrix} \frac{1}{2} \end{matrix}$ H×64
Conv2	$\begin{matrix} \frac{1}{2} \end{matrix}$ W× $\begin{matrix} \frac{1}{2} \end{matrix}$ H×64	64×3×3×64	ReLU	$\begin{matrix} \frac{1}{4} \end{matrix}$ W× $\begin{matrix} \frac{1}{4} \end{matrix}$ H×64
Conv3	$\begin{matrix} \frac{1}{4} \end{matrix}$ W× $\begin{matrix} \frac{1}{4} \end{matrix}$ H×64	64×3×3×64	ReLU	$\begin{matrix} \frac{1}{8} \end{matrix}$ W× $\begin{matrix} \frac{1}{8} \end{matrix}$ H×64
Conv4	$\begin{matrix} \frac{1}{8} \end{matrix}$ W× $\begin{matrix} \frac{1}{8} \end{matrix}$ H×64	64×1×1×128	ReLU	$\begin{matrix} \frac{1}{8} \end{matrix}$ W× $\begin{matrix} \frac{1}{8} \end{matrix}$ H×128

Table 2. Module performance
View table
Table 2. Module performance
Experiment Method MIOU /%
Experiment 1 Spatial information network 60.56
Experiment 2 Experiment 1+context information network 63.47
Experiment 3 Experiment 2+attention model 68.43

Table 3. Comparison of algorithm performance

View table

Table 3. Comparison of algorithm performance

Algorithm	Base model	Data set	Time /ms	Speed /(frame·s^-1)	MIOU /%
FCNN-8s	Paper source	Cityscapes	330.03	3.03	61.78
DeepLab-v3+CRF	Paper source	Cityscapes	1162.79	0.86	70.44
PSPNet	Paper source	Cityscapes	2380.95	0.42	75.84
ENet	Paper source	Cityscapes	73.42	13.62	52.34
Proposed algorithm	Xception	Cityscapes	70.72	14.14	68.43
Proposed algorithm	Xception	CamVid	70.72	14.14	67.28

Tools

Get Citation

Copy Citation Text

Cai Yu, Huang Xuegong, Zhang Zhian, Zhu Xinnian, Ma Xiang. Real-Time Semantic Segmentation Algorithm Based on Feature Fusion Technology[J]. Laser & Optoelectronics Progress, 2020, 57(2): 21011

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites