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
Hubbard_Jacob_Thesis.pdf (7.92 MB)
ETD Abstract Container
Abstract Header
Detecting Curvilinear Arrangements of Objects Surrounded By Clutter
Author Info
Hubbard, Jacob
ORCID® Identifier
http://orcid.org/0000-0002-5561-9287
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=miami1619183709358661
Abstract Details
Year and Degree
2021, Master of Computer Science, Miami University, Computer Science and Software Engineering.
Abstract
Modern Unmanned Aerial Vehicle (UAV) systems are able to collect multi-spectral overhead imagery which can be analyzed for targets of interest, such as landmines. Landmines exhibit specific multi spectral signatures which can be used to detect them automatically, they are also typically placed in patterns of regular spacing (i.e. "minelines"). Minelines can also occur in curvilinear arrangement as they are placed by trucks or airplanes on uneven terrain, to avoid obstacles, or to follow geographic or other boundaries. Prior mine detection methods exist when mines are placed on straight lines; however, when mines are placed in a curvilinear arrangement the number of miss-detected mines rises significantly. This thesis explores an approach for detecting mines without assuming they are on straight lines. The algorithm is capable of detecting any set of points along a curvilinear path, even when the detection algorithm tasked with finding those points has completely failed. After the capability of mine detection is evaluated over several different conditions, the algorithm is optimized using vectorized routines to achieve a 100 times better runtime performance in some areas.
Committee
John Femiani, PhD (Advisor)
Philippe Giabbanelli, PhD (Committee Member)
Daniela Inclezan, PhD (Committee Member)
Pages
61 p.
Subject Headings
Computer Science
Keywords
mines
;
landmines
;
minelines
;
mine detection
;
cobra
;
usnavy
;
markov theory
;
dynamic programming
;
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Hubbard, J. (2021).
Detecting Curvilinear Arrangements of Objects Surrounded By Clutter
[Master's thesis, Miami University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=miami1619183709358661
APA Style (7th edition)
Hubbard, Jacob.
Detecting Curvilinear Arrangements of Objects Surrounded By Clutter .
2021. Miami University, Master's thesis.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=miami1619183709358661.
MLA Style (8th edition)
Hubbard, Jacob. "Detecting Curvilinear Arrangements of Objects Surrounded By Clutter ." Master's thesis, Miami University, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=miami1619183709358661
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
miami1619183709358661
Download Count:
206
Copyright Info
© 2021, all rights reserved.
This open access ETD is published by Miami University and OhioLINK.