UAV downwash dynamic texture features for terrain classification on autonomous navigation

J. P. Matos-Carvalho; José M. Fonseca; André Teixeira Bento Damas Mora

doi:10.15439/2018F185

UAV downwash dynamic texture features for terrain classification on autonomous navigation

J. P. Matos-Carvalho, José M. Fonseca, André Teixeira Bento Damas Mora

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

14 Citations (Scopus)

Abstract

The information generated by a computer vision system capable of labelling a land surface as water, vegetation, soil or other type, can be used for mapping and decision making. For example, an unmanned aerial vehicle (UAV) can use it to find a suitable landing position or to cooperate with other robots to navigate across an unknown region. Previous works on terrain classification from RGB images taken onboard of UAVs shown that only static pixel-based features were tested with a considerable classification error. This paper proposes a robust and efficient computer vision algorithm capable of classifying the terrain from RGB images with improved accuracy. The algorithm complement the static image features with dynamic texture patterns produced by UAVs rotors downwash effect (visible at lower altitudes) and machine learning methods to classify the underlying terrain. The system is validated using videos acquired onboard of a UAV.

Original language	English
Title of host publication	Proceedings of the 2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018
Editors	Maria Ganzha, Leszek Maciaszek, Leszek Maciaszek, Marcin Paprzycki
Place of Publication	New York
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1079-1083
Number of pages	5
ISBN (Electronic)	978-8-3949-4195-6
DOIs	https://doi.org/10.15439/2018F185
Publication status	Published - 26 Oct 2018
Event	2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018 - Poznan, Poland Duration: 9 Sept 2018 → 12 Sept 2018

Publication series

Name	Annals of Computer Science and Information Systems
Publisher	Institute of Electrical and Electronics Engineers Inc.
Volume	15
ISSN (Print)	2325-0348

Conference

Conference	2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018
Country/Territory	Poland
City	Poznan
Period	9/09/18 → 12/09/18

Keywords

Image processing
Machine Learning
Terrain Classification
Texture
UAV

Access to Document

10.15439/2018F185Licence: Unspecified

Cite this

Matos-Carvalho, J. P., Fonseca, J. M., & Mora, A. T. B. D. (2018). UAV downwash dynamic texture features for terrain classification on autonomous navigation. In M. Ganzha, L. Maciaszek, L. Maciaszek, & M. Paprzycki (Eds.), Proceedings of the 2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018 (pp. 1079-1083). Article 8511243 (Annals of Computer Science and Information Systems; Vol. 15). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.15439/2018F185

Matos-Carvalho, J. P. ; Fonseca, José M. ; Mora, André Teixeira Bento Damas. / UAV downwash dynamic texture features for terrain classification on autonomous navigation. Proceedings of the 2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018. editor / Maria Ganzha ; Leszek Maciaszek ; Leszek Maciaszek ; Marcin Paprzycki. New York : Institute of Electrical and Electronics Engineers (IEEE), 2018. pp. 1079-1083 (Annals of Computer Science and Information Systems).

@inproceedings{d887dcd965f64905972f7d41bf122711,

title = "UAV downwash dynamic texture features for terrain classification on autonomous navigation",

abstract = "The information generated by a computer vision system capable of labelling a land surface as water, vegetation, soil or other type, can be used for mapping and decision making. For example, an unmanned aerial vehicle (UAV) can use it to find a suitable landing position or to cooperate with other robots to navigate across an unknown region. Previous works on terrain classification from RGB images taken onboard of UAVs shown that only static pixel-based features were tested with a considerable classification error. This paper proposes a robust and efficient computer vision algorithm capable of classifying the terrain from RGB images with improved accuracy. The algorithm complement the static image features with dynamic texture patterns produced by UAVs rotors downwash effect (visible at lower altitudes) and machine learning methods to classify the underlying terrain. The system is validated using videos acquired onboard of a UAV.",

keywords = "Image processing, Machine Learning, Terrain Classification, Texture, UAV",

author = "Matos-Carvalho, {J. P.} and Fonseca, {Jos{\'e} M.} and Mora, {Andr{\'e} Teixeira Bento Damas}",

note = "Sem PDF conforme despacho. info:eu-repo/grantAgreement/FCT/5876/147324/PT# This work was partially funded by FCT Strategic Program UID/EEA/00066/203 of the Center of Technologies and System (CTS) of UNINOVA - Institute for the Development of new Technologies. In last, this work was not possible without the support and commitment of several fellow colleagues and friends, namely: Ricardo Mendonca, Francisco Marques, Andre Lourenco, Eduardo Pinto and Jose Barata.; 2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018 ; Conference date: 09-09-2018 Through 12-09-2018",

year = "2018",

month = oct,

day = "26",

doi = "10.15439/2018F185",

language = "English",

series = "Annals of Computer Science and Information Systems",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "1079--1083",

editor = "Maria Ganzha and Leszek Maciaszek and Leszek Maciaszek and Marcin Paprzycki",

booktitle = "Proceedings of the 2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018",

address = "United States",

}

Matos-Carvalho, JP , Fonseca, JM & Mora, ATBD 2018, UAV downwash dynamic texture features for terrain classification on autonomous navigation. in M Ganzha, L Maciaszek, L Maciaszek & M Paprzycki (eds), Proceedings of the 2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018., 8511243, Annals of Computer Science and Information Systems, vol. 15, Institute of Electrical and Electronics Engineers (IEEE), New York, pp. 1079-1083, 2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018, Poznan, Poland, 9/09/18. https://doi.org/10.15439/2018F185

UAV downwash dynamic texture features for terrain classification on autonomous navigation. / Matos-Carvalho, J. P.; Fonseca, José M.; Mora, André Teixeira Bento Damas.
Proceedings of the 2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018. ed. / Maria Ganzha; Leszek Maciaszek; Leszek Maciaszek; Marcin Paprzycki. New York: Institute of Electrical and Electronics Engineers (IEEE), 2018. p. 1079-1083 8511243 (Annals of Computer Science and Information Systems; Vol. 15).

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

TY - GEN

T1 - UAV downwash dynamic texture features for terrain classification on autonomous navigation

AU - Matos-Carvalho, J. P.

AU - Fonseca, José M.

AU - Mora, André Teixeira Bento Damas

N1 - Sem PDF conforme despacho. info:eu-repo/grantAgreement/FCT/5876/147324/PT# This work was partially funded by FCT Strategic Program UID/EEA/00066/203 of the Center of Technologies and System (CTS) of UNINOVA - Institute for the Development of new Technologies. In last, this work was not possible without the support and commitment of several fellow colleagues and friends, namely: Ricardo Mendonca, Francisco Marques, Andre Lourenco, Eduardo Pinto and Jose Barata.

PY - 2018/10/26

Y1 - 2018/10/26

N2 - The information generated by a computer vision system capable of labelling a land surface as water, vegetation, soil or other type, can be used for mapping and decision making. For example, an unmanned aerial vehicle (UAV) can use it to find a suitable landing position or to cooperate with other robots to navigate across an unknown region. Previous works on terrain classification from RGB images taken onboard of UAVs shown that only static pixel-based features were tested with a considerable classification error. This paper proposes a robust and efficient computer vision algorithm capable of classifying the terrain from RGB images with improved accuracy. The algorithm complement the static image features with dynamic texture patterns produced by UAVs rotors downwash effect (visible at lower altitudes) and machine learning methods to classify the underlying terrain. The system is validated using videos acquired onboard of a UAV.

AB - The information generated by a computer vision system capable of labelling a land surface as water, vegetation, soil or other type, can be used for mapping and decision making. For example, an unmanned aerial vehicle (UAV) can use it to find a suitable landing position or to cooperate with other robots to navigate across an unknown region. Previous works on terrain classification from RGB images taken onboard of UAVs shown that only static pixel-based features were tested with a considerable classification error. This paper proposes a robust and efficient computer vision algorithm capable of classifying the terrain from RGB images with improved accuracy. The algorithm complement the static image features with dynamic texture patterns produced by UAVs rotors downwash effect (visible at lower altitudes) and machine learning methods to classify the underlying terrain. The system is validated using videos acquired onboard of a UAV.

KW - Image processing

KW - Machine Learning

KW - Terrain Classification

KW - Texture

KW - UAV

UR - http://www.scopus.com/inward/record.url?scp=85057252448&partnerID=8YFLogxK

U2 - 10.15439/2018F185

DO - 10.15439/2018F185

M3 - Conference contribution

AN - SCOPUS:85057252448

T3 - Annals of Computer Science and Information Systems

SP - 1079

EP - 1083

BT - Proceedings of the 2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018

A2 - Ganzha, Maria

A2 - Maciaszek, Leszek

A2 - Paprzycki, Marcin

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - New York

T2 - 2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018

Y2 - 9 September 2018 through 12 September 2018

ER -

Matos-Carvalho JP , Fonseca JM , Mora ATBD. UAV downwash dynamic texture features for terrain classification on autonomous navigation. In Ganzha M, Maciaszek L, Maciaszek L, Paprzycki M, editors, Proceedings of the 2018 Federated Conference on Computer Science and Information Systems, FedCSIS 2018. New York: Institute of Electrical and Electronics Engineers (IEEE). 2018. p. 1079-1083. 8511243. (Annals of Computer Science and Information Systems). doi: 10.15439/2018F185

UAV downwash dynamic texture features for terrain classification on autonomous navigation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this