Perspective Correcting Visual Odometry for Agile MAVs using a Pixel Processor Array

Colin Greatwood; Laurie Bose; Tom Richardson; Walterio Mayol-Cuevas; Jianing Chen; Stephen J. Carey; Piotr Dudek

doi:10.1109/IROS.2018.8594500

Perspective Correcting Visual Odometry for Agile MAVs using a Pixel Processor Array

Colin Greatwood, Laurie Bose, Tom Richardson, Walterio Mayol-Cuevas, Jianing Chen, Stephen J. Carey, Piotr Dudek

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

1 Citation (Scopus)

197 Downloads (Pure)

Abstract

This paper presents a visual odometry approach using a Pixel Processor Array (PPA) camera, specifically, the SCAMP-5 vision chip. In this device, each pixel is capable of storing data and performing computation, enabling a variety of computer vision tasks to be carried out directly upon the sensor itself. In this work the PPA performs HDR edge detection, perspective correction and image alignment based odometry, allowing the position and heading of a MAV to be tracked at several hundred frames per second.

We evaluate our PPA based approach by direct comparison with a motion capture system for a variety of trajectories. These include rapid accelerations that would incur significant motion blur at low frame rates, and lighting conditions that would typically lead to under or over exposure of image detail. Such challenging conditions would often lead to unusable images when relying on traditional image sensors.

Original language	English
Title of host publication	2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	8
ISBN (Electronic)	9781538680940
ISBN (Print)	9781538680957
DOIs	https://doi.org/10.1109/IROS.2018.8594500
Publication status	E-pub ahead of print - 7 Jan 2019

Publication series

Name	Proceedings of the International Conference on Intelligent Robots and Systems
Publisher	IEEE
ISSN (Print)	2153-0858
ISSN (Electronic)	2153-0866

Access to Document

10.1109/IROS.2018.8594500Licence: Unspecified

Full-text PDF (accepted author manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via IEEE at https://doi.org/10.1109/IROS.2018.8594500 . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 4.63 MBLicence: Other

Fingerprint Dive into the research topics of 'Perspective Correcting Visual Odometry for Agile MAVs using a Pixel Processor Array'. Together they form a unique fingerprint.

1 Finished

Vision Sensors for Agile Autonomous Exploration
Mayol-Cuevas, W. W.
1/08/15 → 31/01/21
Project: Research

Cite this

Greatwood, C., Bose, L., Richardson, T., Mayol-Cuevas, W., Chen, J., Carey, S. J., & Dudek, P. (2019). Perspective Correcting Visual Odometry for Agile MAVs using a Pixel Processor Array. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (Proceedings of the International Conference on Intelligent Robots and Systems). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/IROS.2018.8594500

Greatwood, Colin ; Bose, Laurie ; Richardson, Tom ; Mayol-Cuevas, Walterio ; Chen, Jianing ; Carey, Stephen J. ; Dudek, Piotr. / Perspective Correcting Visual Odometry for Agile MAVs using a Pixel Processor Array. 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Institute of Electrical and Electronics Engineers (IEEE), 2019. (Proceedings of the International Conference on Intelligent Robots and Systems).

@inproceedings{723ac5102a684c4e801e13eab793e331,

title = "Perspective Correcting Visual Odometry for Agile MAVs using a Pixel Processor Array",

abstract = "This paper presents a visual odometry approach using a Pixel Processor Array (PPA) camera, specifically, the SCAMP-5 vision chip. In this device, each pixel is capable of storing data and performing computation, enabling a variety of computer vision tasks to be carried out directly upon the sensor itself. In this work the PPA performs HDR edge detection, perspective correction and image alignment based odometry, allowing the position and heading of a MAV to be tracked at several hundred frames per second. We evaluate our PPA based approach by direct comparison with a motion capture system for a variety of trajectories. These include rapid accelerations that would incur significant motion blur at low frame rates, and lighting conditions that would typically lead to under or over exposure of image detail. Such challenging conditions would often lead to unusable images when relying on traditional image sensors.",

author = "Colin Greatwood and Laurie Bose and Tom Richardson and Walterio Mayol-Cuevas and Jianing Chen and Carey, {Stephen J.} and Piotr Dudek",

year = "2019",

month = jan,

day = "7",

doi = "10.1109/IROS.2018.8594500",

language = "English",

isbn = " 9781538680957",

series = "Proceedings of the International Conference on Intelligent Robots and Systems",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

booktitle = "2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",

address = "United States",

}

Greatwood, C, Bose, L , Richardson, T , Mayol-Cuevas, W, Chen, J, Carey, SJ & Dudek, P 2019, Perspective Correcting Visual Odometry for Agile MAVs using a Pixel Processor Array. in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Proceedings of the International Conference on Intelligent Robots and Systems, Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/IROS.2018.8594500

Perspective Correcting Visual Odometry for Agile MAVs using a Pixel Processor Array. / Greatwood, Colin; Bose, Laurie ; Richardson, Tom ; Mayol-Cuevas, Walterio; Chen, Jianing; Carey, Stephen J.; Dudek, Piotr.

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Institute of Electrical and Electronics Engineers (IEEE), 2019. (Proceedings of the International Conference on Intelligent Robots and Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Perspective Correcting Visual Odometry for Agile MAVs using a Pixel Processor Array

AU - Greatwood, Colin

AU - Bose, Laurie

AU - Richardson, Tom

AU - Mayol-Cuevas, Walterio

AU - Chen, Jianing

AU - Carey, Stephen J.

AU - Dudek, Piotr

PY - 2019/1/7

Y1 - 2019/1/7

N2 - This paper presents a visual odometry approach using a Pixel Processor Array (PPA) camera, specifically, the SCAMP-5 vision chip. In this device, each pixel is capable of storing data and performing computation, enabling a variety of computer vision tasks to be carried out directly upon the sensor itself. In this work the PPA performs HDR edge detection, perspective correction and image alignment based odometry, allowing the position and heading of a MAV to be tracked at several hundred frames per second. We evaluate our PPA based approach by direct comparison with a motion capture system for a variety of trajectories. These include rapid accelerations that would incur significant motion blur at low frame rates, and lighting conditions that would typically lead to under or over exposure of image detail. Such challenging conditions would often lead to unusable images when relying on traditional image sensors.

AB - This paper presents a visual odometry approach using a Pixel Processor Array (PPA) camera, specifically, the SCAMP-5 vision chip. In this device, each pixel is capable of storing data and performing computation, enabling a variety of computer vision tasks to be carried out directly upon the sensor itself. In this work the PPA performs HDR edge detection, perspective correction and image alignment based odometry, allowing the position and heading of a MAV to be tracked at several hundred frames per second. We evaluate our PPA based approach by direct comparison with a motion capture system for a variety of trajectories. These include rapid accelerations that would incur significant motion blur at low frame rates, and lighting conditions that would typically lead to under or over exposure of image detail. Such challenging conditions would often lead to unusable images when relying on traditional image sensors.

U2 - 10.1109/IROS.2018.8594500

DO - 10.1109/IROS.2018.8594500

M3 - Conference Contribution (Conference Proceeding)

SN - 9781538680957

T3 - Proceedings of the International Conference on Intelligent Robots and Systems

BT - 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Greatwood C, Bose L , Richardson T , Mayol-Cuevas W, Chen J, Carey SJ et al. Perspective Correcting Visual Odometry for Agile MAVs using a Pixel Processor Array. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Institute of Electrical and Electronics Engineers (IEEE). 2019. (Proceedings of the International Conference on Intelligent Robots and Systems). https://doi.org/10.1109/IROS.2018.8594500

Perspective Correcting Visual Odometry for Agile MAVs using a Pixel Processor Array

Abstract

Publication series

Access to Document

Vision Sensors for Agile Autonomous Exploration

Cite this