Local histogram matching for efficient optical flow computation applied to velocity estimation on pocket drones

Kimberly Mcguire; Guido de Croon; Christophe de Wagter; Bart Remes; K. Tuyls; H. Kappen

doi:10.1109/ICRA.2016.7487496

Local histogram matching for efficient optical flow computation applied to velocity estimation on pocket drones

Kimberly Mcguire, Guido de Croon, Christophe de Wagter, Bart Remes, K. Tuyls, H. Kappen

Control & Simulation

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

20 Citations (Scopus)

69 Downloads (Pure)

Abstract

Autonomous flight of pocket drones is challenging due to the severe limitations on on-board energy, sensing, and processing power. However, tiny drones have great potential as their small size allows maneuvering through narrow spaces while their small weight provides significant safety advantages. This paper presents a computationally efficient algorithm for determining optical flow, which can be run on an STM32F4 microprocessor (168 MHz) of a 4 gram stereo-camera. The optical flow algorithm is based on edge histograms. We propose a matching scheme to determine local optical flow. Moreover, the method allows for sub-pixel flow determination based on time horizon adaptation. We demonstrate velocity measurements in flight and use it within a velocity control-loop on a pocket drone.

Original language	English
Title of host publication	2016 IEEE International Conference on Robotics and Automation (ICRA)
Editors	A. Okamura
Publisher	IEEE
Pages	3255-3260
ISBN (Electronic)	978-1-4673-8026-3
ISBN (Print)	978-1-4673-8027-0
DOIs	https://doi.org/10.1109/ICRA.2016.7487496
Publication status	Published - 2016
Event	2016 IEEE International Conference on Robotics and Automation - Stockholm Waterfront Congress Centre, Stockholm, Sweden Duration: 16 May 2016 → 21 May 2016 https://www.icra2016.org/

Conference

Conference	2016 IEEE International Conference on Robotics and Automation
Abbreviated title	ICRA 2016
Country/Territory	Sweden
City	Stockholm
Period	16/05/16 → 21/05/16
Internet address	https://www.icra2016.org/

Access to Document

10.1109/ICRA.2016.7487496

rootAccepted author manuscript, 1.56 MB

Cite this

@inproceedings{3a72f841156c46e29393ce4798684f9e,

title = "Local histogram matching for efficient optical flow computation applied to velocity estimation on pocket drones",

abstract = "Autonomous flight of pocket drones is challenging due to the severe limitations on on-board energy, sensing, and processing power. However, tiny drones have great potential as their small size allows maneuvering through narrow spaces while their small weight provides significant safety advantages. This paper presents a computationally efficient algorithm for determining optical flow, which can be run on an STM32F4 microprocessor (168 MHz) of a 4 gram stereo-camera. The optical flow algorithm is based on edge histograms. We propose a matching scheme to determine local optical flow. Moreover, the method allows for sub-pixel flow determination based on time horizon adaptation. We demonstrate velocity measurements in flight and use it within a velocity control-loop on a pocket drone.",

author = "Kimberly Mcguire and {de Croon}, Guido and {de Wagter}, Christophe and Bart Remes and K. Tuyls and H. Kappen",

year = "2016",

doi = "10.1109/ICRA.2016.7487496",

language = "English",

isbn = "978-1-4673-8027-0",

pages = "3255--3260",

editor = "A. Okamura",

booktitle = "2016 IEEE International Conference on Robotics and Automation (ICRA)",

publisher = "IEEE",

address = "United States",

note = "2016 IEEE International Conference on Robotics and Automation, ICRA 2016 ; Conference date: 16-05-2016 Through 21-05-2016",

url = "https://www.icra2016.org/",

}

Mcguire, K, de Croon, G , de Wagter, C , Remes, B, Tuyls, K & Kappen , H 2016, Local histogram matching for efficient optical flow computation applied to velocity estimation on pocket drones. in A Okamura (ed.), 2016 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 3255-3260, 2016 IEEE International Conference on Robotics and Automation, Stockholm, Sweden, 16/05/16. https://doi.org/10.1109/ICRA.2016.7487496

Local histogram matching for efficient optical flow computation applied to velocity estimation on pocket drones. / Mcguire, Kimberly; de Croon, Guido ; de Wagter, Christophe et al.
2016 IEEE International Conference on Robotics and Automation (ICRA). ed. / A. Okamura. IEEE, 2016. p. 3255-3260.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Local histogram matching for efficient optical flow computation applied to velocity estimation on pocket drones

AU - Mcguire, Kimberly

AU - de Croon, Guido

AU - de Wagter, Christophe

AU - Remes, Bart

AU - Tuyls, K.

AU - Kappen , H.

PY - 2016

Y1 - 2016

N2 - Autonomous flight of pocket drones is challenging due to the severe limitations on on-board energy, sensing, and processing power. However, tiny drones have great potential as their small size allows maneuvering through narrow spaces while their small weight provides significant safety advantages. This paper presents a computationally efficient algorithm for determining optical flow, which can be run on an STM32F4 microprocessor (168 MHz) of a 4 gram stereo-camera. The optical flow algorithm is based on edge histograms. We propose a matching scheme to determine local optical flow. Moreover, the method allows for sub-pixel flow determination based on time horizon adaptation. We demonstrate velocity measurements in flight and use it within a velocity control-loop on a pocket drone.

AB - Autonomous flight of pocket drones is challenging due to the severe limitations on on-board energy, sensing, and processing power. However, tiny drones have great potential as their small size allows maneuvering through narrow spaces while their small weight provides significant safety advantages. This paper presents a computationally efficient algorithm for determining optical flow, which can be run on an STM32F4 microprocessor (168 MHz) of a 4 gram stereo-camera. The optical flow algorithm is based on edge histograms. We propose a matching scheme to determine local optical flow. Moreover, the method allows for sub-pixel flow determination based on time horizon adaptation. We demonstrate velocity measurements in flight and use it within a velocity control-loop on a pocket drone.

U2 - 10.1109/ICRA.2016.7487496

DO - 10.1109/ICRA.2016.7487496

M3 - Conference contribution

SN - 978-1-4673-8027-0

SP - 3255

EP - 3260

BT - 2016 IEEE International Conference on Robotics and Automation (ICRA)

A2 - Okamura, A.

PB - IEEE

T2 - 2016 IEEE International Conference on Robotics and Automation

Y2 - 16 May 2016 through 21 May 2016

ER -

Local histogram matching for efficient optical flow computation applied to velocity estimation on pocket drones

Abstract

Conference

Access to Document

Fingerprint

Cite this