Detecting Flying Objects Using a Single Moving Camera

Artem Rozantsev, Vincent Lepetit, Pascal Fua

Research output: Contribution to journalArticleResearchpeer-review

Abstract

We propose an approach for detecting flying objects such as Unmanned Aerial Vehicles (UAVs) and aircrafts when they occupy a small portion of the field of view, possibly moving against complex backgrounds, and are filmed by a camera that itself moves. We argue that solving such a difficult problem requires combining both appearance and motion cues. To this end we propose a regression-based approach for object-centric motion stabilization of image patches that allows us to achieve effective classification on spatio-temporal image cubes and outperform state-of-the-art techniques. As this problem has not yet been extensively studied, no test datasets are publicly available. We therefore built our own, both for UAVs and aircrafts, and will make them publicly available so they can be used to benchmark future flying object detection and collision avoidance algorithms.

Original languageEnglish
Article number7466125
Pages (from-to)879-892
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume39
Issue number5
DOIs
Publication statusPublished - 1 May 2017

Fingerprint

Unmanned aerial vehicles (UAV)
Aircraft
Camera
Cameras
Motion
Collision Avoidance
Object Detection
Collision avoidance
Field of View
Regular hexahedron
Patch
Stabilization
Regression
Benchmark
Object
Background
Object detection

Keywords

  • Motion compensation
  • object detection

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Cite this

Detecting Flying Objects Using a Single Moving Camera. / Rozantsev, Artem; Lepetit, Vincent; Fua, Pascal.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, No. 5, 7466125, 01.05.2017, p. 879-892.

Research output: Contribution to journalArticleResearchpeer-review

@article{526039051ca142739ec667281a4d4b17,
title = "Detecting Flying Objects Using a Single Moving Camera",
abstract = "We propose an approach for detecting flying objects such as Unmanned Aerial Vehicles (UAVs) and aircrafts when they occupy a small portion of the field of view, possibly moving against complex backgrounds, and are filmed by a camera that itself moves. We argue that solving such a difficult problem requires combining both appearance and motion cues. To this end we propose a regression-based approach for object-centric motion stabilization of image patches that allows us to achieve effective classification on spatio-temporal image cubes and outperform state-of-the-art techniques. As this problem has not yet been extensively studied, no test datasets are publicly available. We therefore built our own, both for UAVs and aircrafts, and will make them publicly available so they can be used to benchmark future flying object detection and collision avoidance algorithms.",
keywords = "Motion compensation, object detection",
author = "Artem Rozantsev and Vincent Lepetit and Pascal Fua",
year = "2017",
month = "5",
day = "1",
doi = "10.1109/TPAMI.2016.2564408",
language = "English",
volume = "39",
pages = "879--892",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "5",

}

TY - JOUR

T1 - Detecting Flying Objects Using a Single Moving Camera

AU - Rozantsev, Artem

AU - Lepetit, Vincent

AU - Fua, Pascal

PY - 2017/5/1

Y1 - 2017/5/1

N2 - We propose an approach for detecting flying objects such as Unmanned Aerial Vehicles (UAVs) and aircrafts when they occupy a small portion of the field of view, possibly moving against complex backgrounds, and are filmed by a camera that itself moves. We argue that solving such a difficult problem requires combining both appearance and motion cues. To this end we propose a regression-based approach for object-centric motion stabilization of image patches that allows us to achieve effective classification on spatio-temporal image cubes and outperform state-of-the-art techniques. As this problem has not yet been extensively studied, no test datasets are publicly available. We therefore built our own, both for UAVs and aircrafts, and will make them publicly available so they can be used to benchmark future flying object detection and collision avoidance algorithms.

AB - We propose an approach for detecting flying objects such as Unmanned Aerial Vehicles (UAVs) and aircrafts when they occupy a small portion of the field of view, possibly moving against complex backgrounds, and are filmed by a camera that itself moves. We argue that solving such a difficult problem requires combining both appearance and motion cues. To this end we propose a regression-based approach for object-centric motion stabilization of image patches that allows us to achieve effective classification on spatio-temporal image cubes and outperform state-of-the-art techniques. As this problem has not yet been extensively studied, no test datasets are publicly available. We therefore built our own, both for UAVs and aircrafts, and will make them publicly available so they can be used to benchmark future flying object detection and collision avoidance algorithms.

KW - Motion compensation

KW - object detection

UR - http://www.scopus.com/inward/record.url?scp=85018518748&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2016.2564408

DO - 10.1109/TPAMI.2016.2564408

M3 - Article

VL - 39

SP - 879

EP - 892

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 5

M1 - 7466125

ER -