Multispectral camera design and algorithms for python snake detection in the Florida Everglades

Gonzalo Vaca-Castano; Ronald Driggers; Orges Furxhi; Carl Arvidson; Frank Mazzotti

doi:10.1117/12.2519109

Multispectral camera design and algorithms for python snake detection in the Florida Everglades

Gonzalo Vaca-Castano, Ronald Driggers, Orges Furxhi, Carl Arvidson, Frank Mazzotti

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

The Burmese Python has invaded the Florida Everglades where the estimate of pythons is around 150,000 and rapidly growing. Pythons were released as unwanted pets in South Florida and now they are an apex invasive species. As a result, the local fauna population has been largely decimated, and there is an increasing concern about python migration to northern latitudes. Working with a team interested in developing a python detection camera, we have taken hyperspectral and multispectral reflectivity measurements of Brumese Pythons in the visible and near infrared bands (VisNIR). The results show that some VisNIR reflectivity bands can be used to automatically discriminate pythons in the wild. This paper discusses the results of our data collections and provides a camera design process that includes a band selection algorithm and pixel-level classification using machine learning. Additionally, we show a visual enhancement alternative that helps to identify pythons in realistic conditions.

Original language	English (US)
Title of host publication	Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV
Editors	Miguel Velez-Reyes, David W. Messinger
Publisher	SPIE
ISBN (Electronic)	9781510626379
DOIs	https://doi.org/10.1117/12.2519109
State	Published - 2019
Externally published	Yes
Event	Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV 2019 - Baltimore, United States Duration: Apr 16 2019 → Apr 18 2019

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	10986
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV 2019
Country/Territory	United States
City	Baltimore
Period	4/16/19 → 4/18/19

Keywords

Burmese Python
Detection
Everglades
Machine learning
Multispectral

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.2519109

Cite this

Vaca-Castano, G., Driggers, R., Furxhi, O., Arvidson, C., & Mazzotti, F. (2019). Multispectral camera design and algorithms for python snake detection in the Florida Everglades. In M. Velez-Reyes, & D. W. Messinger (Eds.), Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV Article 109860Y (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10986). SPIE. https://doi.org/10.1117/12.2519109

Multispectral camera design and algorithms for python snake detection in the Florida Everglades. / Vaca-Castano, Gonzalo; Driggers, Ronald; Furxhi, Orges et al.
Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV. ed. / Miguel Velez-Reyes; David W. Messinger. SPIE, 2019. 109860Y (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10986).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Vaca-Castano, G, Driggers, R, Furxhi, O, Arvidson, C & Mazzotti, F 2019, Multispectral camera design and algorithms for python snake detection in the Florida Everglades. in M Velez-Reyes & DW Messinger (eds), Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV., 109860Y, Proceedings of SPIE - The International Society for Optical Engineering, vol. 10986, SPIE, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV 2019, Baltimore, United States, 4/16/19. https://doi.org/10.1117/12.2519109

Vaca-Castano G, Driggers R, Furxhi O, Arvidson C, Mazzotti F. Multispectral camera design and algorithms for python snake detection in the Florida Everglades. In Velez-Reyes M, Messinger DW, editors, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV. SPIE. 2019. 109860Y. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.2519109

Vaca-Castano, Gonzalo ; Driggers, Ronald ; Furxhi, Orges et al. / Multispectral camera design and algorithms for python snake detection in the Florida Everglades. Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV. editor / Miguel Velez-Reyes ; David W. Messinger. SPIE, 2019. (Proceedings of SPIE - The International Society for Optical Engineering).

@inproceedings{23c1586153044516902468041f54bf2c,

title = "Multispectral camera design and algorithms for python snake detection in the Florida Everglades",

abstract = "The Burmese Python has invaded the Florida Everglades where the estimate of pythons is around 150,000 and rapidly growing. Pythons were released as unwanted pets in South Florida and now they are an apex invasive species. As a result, the local fauna population has been largely decimated, and there is an increasing concern about python migration to northern latitudes. Working with a team interested in developing a python detection camera, we have taken hyperspectral and multispectral reflectivity measurements of Brumese Pythons in the visible and near infrared bands (VisNIR). The results show that some VisNIR reflectivity bands can be used to automatically discriminate pythons in the wild. This paper discusses the results of our data collections and provides a camera design process that includes a band selection algorithm and pixel-level classification using machine learning. Additionally, we show a visual enhancement alternative that helps to identify pythons in realistic conditions.",

keywords = "Burmese Python, Detection, Everglades, Machine learning, Multispectral",

author = "Gonzalo Vaca-Castano and Ronald Driggers and Orges Furxhi and Carl Arvidson and Frank Mazzotti",

note = "Publisher Copyright: {\textcopyright} 2019 SPIE.; Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV 2019 ; Conference date: 16-04-2019 Through 18-04-2019",

year = "2019",

doi = "10.1117/12.2519109",

language = "English (US)",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Miguel Velez-Reyes and Messinger, {David W.}",

booktitle = "Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV",

}

TY - GEN

T1 - Multispectral camera design and algorithms for python snake detection in the Florida Everglades

AU - Vaca-Castano, Gonzalo

AU - Driggers, Ronald

AU - Furxhi, Orges

AU - Arvidson, Carl

AU - Mazzotti, Frank

PY - 2019

Y1 - 2019

N2 - The Burmese Python has invaded the Florida Everglades where the estimate of pythons is around 150,000 and rapidly growing. Pythons were released as unwanted pets in South Florida and now they are an apex invasive species. As a result, the local fauna population has been largely decimated, and there is an increasing concern about python migration to northern latitudes. Working with a team interested in developing a python detection camera, we have taken hyperspectral and multispectral reflectivity measurements of Brumese Pythons in the visible and near infrared bands (VisNIR). The results show that some VisNIR reflectivity bands can be used to automatically discriminate pythons in the wild. This paper discusses the results of our data collections and provides a camera design process that includes a band selection algorithm and pixel-level classification using machine learning. Additionally, we show a visual enhancement alternative that helps to identify pythons in realistic conditions.

AB - The Burmese Python has invaded the Florida Everglades where the estimate of pythons is around 150,000 and rapidly growing. Pythons were released as unwanted pets in South Florida and now they are an apex invasive species. As a result, the local fauna population has been largely decimated, and there is an increasing concern about python migration to northern latitudes. Working with a team interested in developing a python detection camera, we have taken hyperspectral and multispectral reflectivity measurements of Brumese Pythons in the visible and near infrared bands (VisNIR). The results show that some VisNIR reflectivity bands can be used to automatically discriminate pythons in the wild. This paper discusses the results of our data collections and provides a camera design process that includes a band selection algorithm and pixel-level classification using machine learning. Additionally, we show a visual enhancement alternative that helps to identify pythons in realistic conditions.

KW - Burmese Python

KW - Detection

KW - Everglades

KW - Machine learning

KW - Multispectral

UR - http://www.scopus.com/inward/record.url?scp=85072585418&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072585418&partnerID=8YFLogxK

U2 - 10.1117/12.2519109

DO - 10.1117/12.2519109

M3 - Conference contribution

AN - SCOPUS:85072585418

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV

A2 - Velez-Reyes, Miguel

A2 - Messinger, David W.

PB - SPIE

T2 - Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV 2019

Y2 - 16 April 2019 through 18 April 2019

ER -

Multispectral camera design and algorithms for python snake detection in the Florida Everglades

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this