Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
Camouflaged Object Segmentation in Images_3__final format approved LW 12-10-19.pdf (1.56 MB)
ETD Abstract Container
Abstract Header
Camouflaged Object Segmentation in Images
Author Info
Yan, Jinnan
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=dayton1576064709283297
Abstract Details
Year and Degree
2019, Master of Computer Science (M.C.S.), University of Dayton, Computer Science.
Abstract
Camouflaged objects are generally difficult to be detected in their natural environment even for human beings. In this thesis, we propose a novel bio-inspired network, named the CamoNet, that leverages both instance segmentation and adversarial attack for the camouflaged object segmentation. Differently from existing networks for segmentation, our proposed network possesses two segmentation streams: the main stream and the adversarial stream corresponding with the original image and its flipped image, respectively. The output from the adversarial stream is then fused into the main stream’s result for the final camouflage map to boost up the segmentation accuracy. We also introduce the Data Augmentation in the Wild to solve the data insufficiency for network training. Extensive experiments conducted on the public CAMO dataset demonstrate the effectiveness of our proposed network. Our proposed method achieves 89% in accuracy, significantly outperforming the state-of-the-arts.
Committee
Tam Nguyen (Advisor)
Pages
42 p.
Subject Headings
Computer Science
Keywords
Camouflaged Object Segmentation
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Yan, J. (2019).
Camouflaged Object Segmentation in Images
[Master's thesis, University of Dayton]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1576064709283297
APA Style (7th edition)
Yan, Jinnan.
Camouflaged Object Segmentation in Images.
2019. University of Dayton, Master's thesis.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=dayton1576064709283297.
MLA Style (8th edition)
Yan, Jinnan. "Camouflaged Object Segmentation in Images." Master's thesis, University of Dayton, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1576064709283297
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
dayton1576064709283297
Download Count:
751
Copyright Info
© 2019, all rights reserved.
This open access ETD is published by University of Dayton and OhioLINK.