中文
Share
Share
中文
ISSN 2096-7217 CN 32-1887/S2
Quick Search
Citation Search
Site Search
Adv Search
Toggle navigation
JIAM
Organizer
Home
About
Journal Introduction
Editorial Board
Open Access Statement
Ethic Statement
Academic Misconduct
Browse
Just Accepted
Current Issue
Archive
Hot Papers
Special Issues
Most Cited
Most Viewed
Most Downloaded
Author Center
Online Submission
Guides for Authors
Review Process
Peer Review
Copyright Transfer Agreement
Charge and Remuneration
Download
Manuscript Review
Expert Review
Edit office
Editor in chief
Included
CNKI
WANFANG DATA
VIP
SUPERSTAR
Subscribe
RSS
Email Alert
Subscription
Contact Us
Contact Us
Advertisement
Article Result
Journals
Publication Years
Keywords
Search within results
((( Hui Zhao[Author]) AND 1[Journal]) AND year[Order])
AND
OR
NOT
Title
Author
Institution
Keyword
Abstract
PACS
DOI
Please wait a minute...
Choose
Download reference
EndNote
Reference Manager
ProCite
BibTeX
RefWorks
Show/Hide thumbnails
Select
SENet optimized Deeplabv3+ freshwater fish body semantic segmentation
*
Hongjun Wang, Xiaoyu Ji, Hui Zhao, Youjun Yue
Journal of Intelligent Agricultural Mechanization (in Chinese and English) 2021, 2 (1): 36-43. DOI:
10.12398/j.issn.2096-7217.2021.01.005
Abstract
(
190
)
PDF
(1192KB)(
26
)
Knowledge map
The rapid identification and precise positioning of the freshwater fish's head, abdomen, and fins are prerequisites for the robot to achieve fast capturing, accurate segmentation, and the core of working efficiency improvement. The freshwater fish body's semantic segmentation algorithm conducts many invalid feature channels under the encoding feature extraction stage, and the constant network sample collection and pooling operation lead to the loss of detailed information of some fish bodies, decreasing the performance and poor the performance effect of edge cutting. A semantic segmentation algorithm base on SENet optimized Deeplabv3+ freshwater fish head, abdomen, and fins is proposed. Using dilated/atrous convolutions to enlarge the receptive field, prevent detail information loss, and actualize the precise positioning. Meanwhile, the SENet optimization enables Deeplabv3+ to improve the useful feature of freshwater fish and restrains its ineffectual feature. Eventually, the semantic segmentation
MIoU
of each part of the freshwater fish reached about 93% on the self-established freshwater fish data set. Its feature improved significantly and reached the current advanced segmentation level.
Reference
|
Related Articles
|
Metrics