Efficient real-time video stabilization for UAVs using only IMU data

Marcin Odelga, Nicholas Kochanek, Heinrich Bulthoff

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

While some unmanned aerial vehicles (UAVs) have the capacity to carry mechanically stabilized camera equipment, weight limits or other problems may make mechanical stabilization impractical. As a result many UAVs rely on fixed cameras to provide a video stream to an operator or observer. With a fixed camera, the video stream is often unsteady due to the multirotor's movement from wind and acceleration. These video streams are often analyzed by both humans and machines, and the unwanted camera movement can cause problems for both. For a human observer, unwanted movement may simply make it harder to follow the video, while for computer algorithms, it may severely impair the algorithm's intended function. There has been significant research on how to stabilize videos using feature tracking to determine camera movement, which in turn is used to manipulate frames and stabilize the camera stream. We believe, however, that this process could be greatly simplified by using data from a UAV's on-board inertial measurement unit (IMU) to stabilize the camera feed. In this paper we present an algorithm for video stabilization based only on IMU data from a UAV platform. Our results show that our algorithm successfully stabilizes the camera stream with the added benefit of requiring less computational power.

Original languageEnglish
Title of host publication2017 Workshop on Research, Education and Development of Unmanned Aerial Systems, RED-UAS 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages210-215
Number of pages6
ISBN (Electronic)9781538609392
DOIs
Publication statusPublished - 2017 Nov 8
Externally publishedYes
Event2017 Workshop on Research, Education and Development of Unmanned Aerial Systems, RED-UAS 2017 - Linkoping, Sweden
Duration: 2017 Oct 32017 Oct 5

Other

Other2017 Workshop on Research, Education and Development of Unmanned Aerial Systems, RED-UAS 2017
CountrySweden
CityLinkoping
Period17/10/317/10/5

Fingerprint

Units of measurement
Unmanned aerial vehicles (UAV)
stabilization
Stabilization
video
Camera
Cameras
Real-time
Unit
Observer
Feature Tracking
time
cause
Movement
Operator

ASJC Scopus subject areas

  • Artificial Intelligence
  • Aerospace Engineering
  • Control and Optimization
  • Modelling and Simulation
  • Education

Cite this

Odelga, M., Kochanek, N., & Bulthoff, H. (2017). Efficient real-time video stabilization for UAVs using only IMU data. In 2017 Workshop on Research, Education and Development of Unmanned Aerial Systems, RED-UAS 2017 (pp. 210-215). [8101668] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RED-UAS.2017.8101668

Efficient real-time video stabilization for UAVs using only IMU data. / Odelga, Marcin; Kochanek, Nicholas; Bulthoff, Heinrich.

2017 Workshop on Research, Education and Development of Unmanned Aerial Systems, RED-UAS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 210-215 8101668.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Odelga, M, Kochanek, N & Bulthoff, H 2017, Efficient real-time video stabilization for UAVs using only IMU data. in 2017 Workshop on Research, Education and Development of Unmanned Aerial Systems, RED-UAS 2017., 8101668, Institute of Electrical and Electronics Engineers Inc., pp. 210-215, 2017 Workshop on Research, Education and Development of Unmanned Aerial Systems, RED-UAS 2017, Linkoping, Sweden, 17/10/3. https://doi.org/10.1109/RED-UAS.2017.8101668
Odelga M, Kochanek N, Bulthoff H. Efficient real-time video stabilization for UAVs using only IMU data. In 2017 Workshop on Research, Education and Development of Unmanned Aerial Systems, RED-UAS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 210-215. 8101668 https://doi.org/10.1109/RED-UAS.2017.8101668
Odelga, Marcin ; Kochanek, Nicholas ; Bulthoff, Heinrich. / Efficient real-time video stabilization for UAVs using only IMU data. 2017 Workshop on Research, Education and Development of Unmanned Aerial Systems, RED-UAS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 210-215
@inproceedings{deb5984593404904a2c9648cc764647f,
title = "Efficient real-time video stabilization for UAVs using only IMU data",
abstract = "While some unmanned aerial vehicles (UAVs) have the capacity to carry mechanically stabilized camera equipment, weight limits or other problems may make mechanical stabilization impractical. As a result many UAVs rely on fixed cameras to provide a video stream to an operator or observer. With a fixed camera, the video stream is often unsteady due to the multirotor's movement from wind and acceleration. These video streams are often analyzed by both humans and machines, and the unwanted camera movement can cause problems for both. For a human observer, unwanted movement may simply make it harder to follow the video, while for computer algorithms, it may severely impair the algorithm's intended function. There has been significant research on how to stabilize videos using feature tracking to determine camera movement, which in turn is used to manipulate frames and stabilize the camera stream. We believe, however, that this process could be greatly simplified by using data from a UAV's on-board inertial measurement unit (IMU) to stabilize the camera feed. In this paper we present an algorithm for video stabilization based only on IMU data from a UAV platform. Our results show that our algorithm successfully stabilizes the camera stream with the added benefit of requiring less computational power.",
author = "Marcin Odelga and Nicholas Kochanek and Heinrich Bulthoff",
year = "2017",
month = "11",
day = "8",
doi = "10.1109/RED-UAS.2017.8101668",
language = "English",
pages = "210--215",
booktitle = "2017 Workshop on Research, Education and Development of Unmanned Aerial Systems, RED-UAS 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Efficient real-time video stabilization for UAVs using only IMU data

AU - Odelga, Marcin

AU - Kochanek, Nicholas

AU - Bulthoff, Heinrich

PY - 2017/11/8

Y1 - 2017/11/8

N2 - While some unmanned aerial vehicles (UAVs) have the capacity to carry mechanically stabilized camera equipment, weight limits or other problems may make mechanical stabilization impractical. As a result many UAVs rely on fixed cameras to provide a video stream to an operator or observer. With a fixed camera, the video stream is often unsteady due to the multirotor's movement from wind and acceleration. These video streams are often analyzed by both humans and machines, and the unwanted camera movement can cause problems for both. For a human observer, unwanted movement may simply make it harder to follow the video, while for computer algorithms, it may severely impair the algorithm's intended function. There has been significant research on how to stabilize videos using feature tracking to determine camera movement, which in turn is used to manipulate frames and stabilize the camera stream. We believe, however, that this process could be greatly simplified by using data from a UAV's on-board inertial measurement unit (IMU) to stabilize the camera feed. In this paper we present an algorithm for video stabilization based only on IMU data from a UAV platform. Our results show that our algorithm successfully stabilizes the camera stream with the added benefit of requiring less computational power.

AB - While some unmanned aerial vehicles (UAVs) have the capacity to carry mechanically stabilized camera equipment, weight limits or other problems may make mechanical stabilization impractical. As a result many UAVs rely on fixed cameras to provide a video stream to an operator or observer. With a fixed camera, the video stream is often unsteady due to the multirotor's movement from wind and acceleration. These video streams are often analyzed by both humans and machines, and the unwanted camera movement can cause problems for both. For a human observer, unwanted movement may simply make it harder to follow the video, while for computer algorithms, it may severely impair the algorithm's intended function. There has been significant research on how to stabilize videos using feature tracking to determine camera movement, which in turn is used to manipulate frames and stabilize the camera stream. We believe, however, that this process could be greatly simplified by using data from a UAV's on-board inertial measurement unit (IMU) to stabilize the camera feed. In this paper we present an algorithm for video stabilization based only on IMU data from a UAV platform. Our results show that our algorithm successfully stabilizes the camera stream with the added benefit of requiring less computational power.

UR - http://www.scopus.com/inward/record.url?scp=85047642966&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047642966&partnerID=8YFLogxK

U2 - 10.1109/RED-UAS.2017.8101668

DO - 10.1109/RED-UAS.2017.8101668

M3 - Conference contribution

AN - SCOPUS:85047642966

SP - 210

EP - 215

BT - 2017 Workshop on Research, Education and Development of Unmanned Aerial Systems, RED-UAS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -