Journals
Advanced Photonics
Photonics Insights
Advanced Photonics Nexus
Photonics Research
Advanced Imaging
View All Journals
Chinese Optics Letters
High Power Laser Science and Engineering
Articles
Optics
Physics
Geography
View All Subjects
Conferences
CIOP
HPLSE
AP
View All Events
News
About CLP
Search by keywords or author
Login
Registration
Login in
Registration
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
metasurface
laser
polarization
nir
lidar
lithium niobate
Journals >
Laser & Optoelectronics Progress >
Volume 58 >
Issue 16 >
Page 1610008 > Article
Laser & Optoelectronics Progress
Vol. 58, Issue 16, 1610008 (2021)
Image Semantic Segmentation Method Based on Improved DeepLabv3+ Network
Cong Xu
*
and Li Wang
Author Affiliations
School of Computer and Information Engineering, Tianjin Chengjian University, Tianjin 300384, China
show less
DOI:
10.3788/LOP202158.1610008
Cite this Article
Set citation alerts
Cong Xu, Li Wang. Image Semantic Segmentation Method Based on Improved DeepLabv3+ Network[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1610008
Copy Citation Text
EndNote(RIS)
BibTex
Plain Text
show less
Fig. 1.
Structure of the DeepLabv3+ network
Download full size
Fig. 2.
Structure of the improved DeepLabv3+ network
Download full size
Fig. 3.
Structure of the ASPP module
Download full size
Fig. 4.
Flow chart of the depth separable convolution
Download full size
Fig. 5.
Structure of the FPN
Download full size
Fig. 6.
Segmentation results of different methods. (a) Input image; (b) labeled image; (c) DeepLabv3+ network; (d) Ours 1
Download full size
Project
Detail
CPU
Inter i7-4770k
RAM
32 G
Graphics card
TITAN V
Operating system
64-bit Ubuntu 18.04.3
CUDA
Cuda 10.2
Data processing
Pytorch 3.6
Table 1.
Hardware and software configurations of the machine
Dilation rate
mIoU
(6,12,18)
79.73
(6,12,18,24)
79.80
(4,8,12,16)
79.97
Table 2.
Test results under different combinations of dilation rate in ASPP module unit: %
Convolution method in ASPP
Time/h
mIoU/%
Standard convolution
23.2
79.97
Depthwise separable convolution
17.3
79.46
Table 3.
Training time and mIoU of different networks
Network
Parameter /M
FLOPs /
GMAC
Speed /
(frame·s
-1
)
DeepLabv2
61.41
75.40
12.55
DeepLabv3
58.04
71.16
13.07
DeepLabv3+
59.34
92.93
13.45
Ours 1
64.65
99.53
12.66
Ours 2
47.97
81.34
16.96
Table 4.
Performances of different networks
Network
mIoU/%
DeepLabv1
68.70
DeepLabv2
76.35
DeepLabv3
77.21
DeepLabv3+
78.85
Ours 2
79.46
Ours 1
79.97
Table 5.
mIoU of different networks on the PASCAL VOC2012 verification set
Abstract
Get PDF(in Chinese)
Figures&Tables (11)
Equations (0)
References (20)
Cited By (8)
Get Citation
Copy Citation Text
Cong Xu, Li Wang. Image Semantic Segmentation Method Based on Improved DeepLabv3+ Network[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1610008
Download Citation
EndNote(RIS)
BibTex
Plain Text
Set citation alerts for the article
Tools
Share
Set citation alerts for the article
Save the article for my favorites
Paper Information
Category: Image Processing
Received: Oct. 24, 2020
Accepted: Dec. 8, 2020
Published Online: Aug. 18, 2021
The Author Email: Xu Cong (769458796@qq.com)
DOI:
10.3788/LOP202158.1610008
Recommended Topics
laser devices and laser physics
Lasers and Laser Optics
Laser physics
laser manufacturing
Instrumentation, Measurement and Metrology
Set citation alerts for the article
Please enter your email address
Cancel
Confirm