Comparison of feature extraction and matching techniques applied to monocular UAV images with low-quality and land cover variations

被引：0

作者：

Xavier, Nathan A. Z. ^{[1
]}

Lapa, Jonathan de A. ^{[2
]}

Honorio, Douglas D. de C. ^{[3
]}

de Oliveira, Rafael C. ^{[2
]}

Shiguemori, Elcio H. ^{[3
]}

Maximo, Marcos R. O. A. ^{[3
,4
]}

Domiciano, Marco A. P.

机构：

[1] Fed Univ Minas Gerais UFMG, Tech Coll UFMG, Belo Horizonte, MG, Brazil

[2] Aeronaut Inst Technol ITA, Sao Jose Dos Campos, SP, Brazil

[3] Inst Adv Studies IEAv, C4ISR, Sao Jose Dos Campos, SP, Brazil

[4] Aeronaut Inst Technol ITA, Comp Sci Div, Sao Jose Dos Campos, SP, Brazil

来源：

2023 LATIN AMERICAN ROBOTICS SYMPOSIUM, LARS, 2023 BRAZILIAN SYMPOSIUM ON ROBOTICS, SBR, AND 2023 WORKSHOP ON ROBOTICS IN EDUCATION, WRE | 2023年

关键词：

Feature extraction; Feature matching; Computer vision; KDD; UAVs; Visual odometry;

D O I：

10.1109/LARS/SBR/WRE59448.2023.10333064

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Extracting features from images is a recurring task in applications highly dependent on cameras, mainly on UAV visual navigation. By using sequential images, on different land covers and low-quality images, variable performance is expected based on both modification characteristics. This study applies the techniques GFTT, SIFT, MSER, FAST, BRISK, ORB, AKAZE, and SuperGlue on the dataset KDD-BR 2022, which contains multiple UAV images of various land covers and low-quality images. The performance of each technique on feature extracting and matching is presented while verifying the methods that better generalize this process.

引用

页码：47 / 52

页数：6

共 6 条

[1] The study on low-quality images Geometric Facial Feature Extraction
Liu, Xueping
Li, Yibo
PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON LOGISTICS, ENGINEERING, MANAGEMENT AND COMPUTER SCIENCE, 2014, 101 : 290 - 293
[2] Magnetic energy-based feature extraction for low-quality fingerprint images
Hassanat, Ahmad B. A.
Prasath, V. B. Surya
Al-kasassbeh, Mouhammd
Tarawneh, Ahmad S.
Al-shamailh, Ahmad J.
SIGNAL IMAGE AND VIDEO PROCESSING, 2018, 12 (08) : 1471 - 1478
[3] Magnetic energy-based feature extraction for low-quality fingerprint images
Ahmad B. A. Hassanat
V. B. Surya Prasath
Mouhammd Al-kasassbeh
Ahmad S. Tarawneh
Ahmad J. Al-shamailh
Signal, Image and Video Processing, 2018, 12 : 1471 - 1478
[4] Enhancement of feature extraction for low-quality fingerprint images using stochastic resonance
Ryu, Choonwoo
Kong, Seong G.
Kim, Hakil
PATTERN RECOGNITION LETTERS, 2011, 32 (02) : 107 - 113
[5] Comparison of feature extraction techniques for face verification using elastic graph matching on low-power mobile devices
Nagel, JL
Stadelmann, P
Ansorge, M
Pellandini, F
IEEE REGION 8 EUROCON 2003, VOL B, PROCEEDINGS: COMPUTER AS A TOOL, 2003, : 365 - 369
[6] Comparison of feature extraction techniques for face verification using elastic graph matching on low-power mobile devices
Electrotechnical Association of Slovenia; et al.; IEEE Region 8; IEEE Slovenia Section; Ministry of Education, Science and Sport of the Republic of Slovenia; University of Ljubljana (Institute of Electrical and Electronics Engineers Inc., United States):

← 1 →