Maximizing feature detection in aerial unmanned aerial vehicle datasets

Jonathan Byrne, Debra Laefer, Evan O'Keeffe

Research output: Contribution to journalArticle

Abstract

This paper compares several feature detectors applied to imagery from an unmanned aerial vehicle to find the best detection algorithm when applied to datasets that vary in translation and have little or no image overlap. Metrics of inliers and reconstruction accuracy of feature detectors are considered with respect to three-dimensional reconstruction results. The image matching results are tested experimentally, and an approach to detecting false matches is outlined. Results showed that although the detectors varied in the number of keypoints generated, a large number of inliers does not necessarily translate into more points in the final point cloud reconstruction and that the process of comparing a large quantity of redundant keypoints may outweigh the advantage of having the extra points. The results also showed that despite the development of keypoint detectors and descriptors, none of them consistently demonstrated a substantial improvement in the quality of structure from motion reconstruction when applied to a wide range of disparate urban and rural images.

Original languageEnglish (US)
Article number025015
JournalJournal of Applied Remote Sensing
Volume11
Issue number2
DOIs
StatePublished - Apr 1 2017

Fingerprint

imagery
detection
detector
vehicle

Keywords

  • Computer vision
  • Detection
  • Image segmentation
  • Photogrammetry
  • Remote sensing

ASJC Scopus subject areas

  • Earth and Planetary Sciences(all)

Cite this

Maximizing feature detection in aerial unmanned aerial vehicle datasets. / Byrne, Jonathan; Laefer, Debra; O'Keeffe, Evan.

In: Journal of Applied Remote Sensing, Vol. 11, No. 2, 025015, 01.04.2017.

Research output: Contribution to journalArticle

@article{1787e7acaf7644d7a2c6a3b044517dd9,
title = "Maximizing feature detection in aerial unmanned aerial vehicle datasets",
abstract = "This paper compares several feature detectors applied to imagery from an unmanned aerial vehicle to find the best detection algorithm when applied to datasets that vary in translation and have little or no image overlap. Metrics of inliers and reconstruction accuracy of feature detectors are considered with respect to three-dimensional reconstruction results. The image matching results are tested experimentally, and an approach to detecting false matches is outlined. Results showed that although the detectors varied in the number of keypoints generated, a large number of inliers does not necessarily translate into more points in the final point cloud reconstruction and that the process of comparing a large quantity of redundant keypoints may outweigh the advantage of having the extra points. The results also showed that despite the development of keypoint detectors and descriptors, none of them consistently demonstrated a substantial improvement in the quality of structure from motion reconstruction when applied to a wide range of disparate urban and rural images.",
keywords = "Computer vision, Detection, Image segmentation, Photogrammetry, Remote sensing",
author = "Jonathan Byrne and Debra Laefer and Evan O'Keeffe",
year = "2017",
month = "4",
day = "1",
doi = "10.1117/1.JRS.11.025015",
language = "English (US)",
volume = "11",
journal = "Journal of Applied Remote Sensing",
issn = "1931-3195",
publisher = "SPIE",
number = "2",

}

TY - JOUR

T1 - Maximizing feature detection in aerial unmanned aerial vehicle datasets

AU - Byrne, Jonathan

AU - Laefer, Debra

AU - O'Keeffe, Evan

PY - 2017/4/1

Y1 - 2017/4/1

N2 - This paper compares several feature detectors applied to imagery from an unmanned aerial vehicle to find the best detection algorithm when applied to datasets that vary in translation and have little or no image overlap. Metrics of inliers and reconstruction accuracy of feature detectors are considered with respect to three-dimensional reconstruction results. The image matching results are tested experimentally, and an approach to detecting false matches is outlined. Results showed that although the detectors varied in the number of keypoints generated, a large number of inliers does not necessarily translate into more points in the final point cloud reconstruction and that the process of comparing a large quantity of redundant keypoints may outweigh the advantage of having the extra points. The results also showed that despite the development of keypoint detectors and descriptors, none of them consistently demonstrated a substantial improvement in the quality of structure from motion reconstruction when applied to a wide range of disparate urban and rural images.

AB - This paper compares several feature detectors applied to imagery from an unmanned aerial vehicle to find the best detection algorithm when applied to datasets that vary in translation and have little or no image overlap. Metrics of inliers and reconstruction accuracy of feature detectors are considered with respect to three-dimensional reconstruction results. The image matching results are tested experimentally, and an approach to detecting false matches is outlined. Results showed that although the detectors varied in the number of keypoints generated, a large number of inliers does not necessarily translate into more points in the final point cloud reconstruction and that the process of comparing a large quantity of redundant keypoints may outweigh the advantage of having the extra points. The results also showed that despite the development of keypoint detectors and descriptors, none of them consistently demonstrated a substantial improvement in the quality of structure from motion reconstruction when applied to a wide range of disparate urban and rural images.

KW - Computer vision

KW - Detection

KW - Image segmentation

KW - Photogrammetry

KW - Remote sensing

UR - http://www.scopus.com/inward/record.url?scp=85022223838&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85022223838&partnerID=8YFLogxK

U2 - 10.1117/1.JRS.11.025015

DO - 10.1117/1.JRS.11.025015

M3 - Article

VL - 11

JO - Journal of Applied Remote Sensing

JF - Journal of Applied Remote Sensing

SN - 1931-3195

IS - 2

M1 - 025015

ER -