Recognition of ascending stairs from 2D images for control of powered lower limb prostheses

Nili E. Krausz; Levi J. Hargrove

doi:10.1109/NER.2015.7146698

Recognition of ascending stairs from 2D images for control of powered lower limb prostheses

Nili E. Krausz^*, Levi J. Hargrove

^*Corresponding author for this work

Physical Medicine and Rehabilitation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

12 Scopus citations

Abstract

Intent recognition is essential for effective control of powered assistive devices, such as powered lower limb prostheses, exoskeletons, or wheelchairs. Currently, EMG and mechanical sensors are used for intent recognition of powered lower limb prostheses. We propose the addition of vision for improved intent recognition control, with this work focused on determining the best method for recognizing of ascending stair edges from 2D images. In this work different image processing methods were tested to determine which method produces the best line extraction. The best results were obtained using Canny, Sobel, Prewitt, and Roberts Cross edge detectors for four colorspace components. Finally, a convex/concave line decision system was developed to produce preliminary results about the presence or absence of stairs in a given image.

Original language	English (US)
Title of host publication	2015 7th International IEEE/EMBS Conference on Neural Engineering, NER 2015
Publisher	IEEE Computer Society
Pages	615-618
Number of pages	4
Volume	2015-July
ISBN (Electronic)	9781467363891
DOIs	https://doi.org/10.1109/NER.2015.7146698
State	Published - Jan 1 2015
Event	7th International IEEE/EMBS Conference on Neural Engineering, NER 2015 - Montpellier, France Duration: Apr 22 2015 → Apr 24 2015

Other

Other	7th International IEEE/EMBS Conference on Neural Engineering, NER 2015
Country/Territory	France
City	Montpellier
Period	4/22/15 → 4/24/15

ASJC Scopus subject areas

Artificial Intelligence
Mechanical Engineering

Access to Document

10.1109/NER.2015.7146698

Cite this

@inproceedings{41dd1c1f72b048969dbcd939cdd56e29,

title = "Recognition of ascending stairs from 2D images for control of powered lower limb prostheses",

abstract = "Intent recognition is essential for effective control of powered assistive devices, such as powered lower limb prostheses, exoskeletons, or wheelchairs. Currently, EMG and mechanical sensors are used for intent recognition of powered lower limb prostheses. We propose the addition of vision for improved intent recognition control, with this work focused on determining the best method for recognizing of ascending stair edges from 2D images. In this work different image processing methods were tested to determine which method produces the best line extraction. The best results were obtained using Canny, Sobel, Prewitt, and Roberts Cross edge detectors for four colorspace components. Finally, a convex/concave line decision system was developed to produce preliminary results about the presence or absence of stairs in a given image.",

author = "Krausz, {Nili E.} and Hargrove, {Levi J.}",

year = "2015",

month = jan,

day = "1",

doi = "10.1109/NER.2015.7146698",

language = "English (US)",

volume = "2015-July",

pages = "615--618",

booktitle = "2015 7th International IEEE/EMBS Conference on Neural Engineering, NER 2015",

publisher = "IEEE Computer Society",

address = "United States",

note = "7th International IEEE/EMBS Conference on Neural Engineering, NER 2015 ; Conference date: 22-04-2015 Through 24-04-2015",

}

Krausz, NE & Hargrove, LJ 2015, Recognition of ascending stairs from 2D images for control of powered lower limb prostheses. in 2015 7th International IEEE/EMBS Conference on Neural Engineering, NER 2015. vol. 2015-July, 7146698, IEEE Computer Society, pp. 615-618, 7th International IEEE/EMBS Conference on Neural Engineering, NER 2015, Montpellier, France, 4/22/15. https://doi.org/10.1109/NER.2015.7146698

TY - GEN

T1 - Recognition of ascending stairs from 2D images for control of powered lower limb prostheses

AU - Krausz, Nili E.

AU - Hargrove, Levi J.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Intent recognition is essential for effective control of powered assistive devices, such as powered lower limb prostheses, exoskeletons, or wheelchairs. Currently, EMG and mechanical sensors are used for intent recognition of powered lower limb prostheses. We propose the addition of vision for improved intent recognition control, with this work focused on determining the best method for recognizing of ascending stair edges from 2D images. In this work different image processing methods were tested to determine which method produces the best line extraction. The best results were obtained using Canny, Sobel, Prewitt, and Roberts Cross edge detectors for four colorspace components. Finally, a convex/concave line decision system was developed to produce preliminary results about the presence or absence of stairs in a given image.

AB - Intent recognition is essential for effective control of powered assistive devices, such as powered lower limb prostheses, exoskeletons, or wheelchairs. Currently, EMG and mechanical sensors are used for intent recognition of powered lower limb prostheses. We propose the addition of vision for improved intent recognition control, with this work focused on determining the best method for recognizing of ascending stair edges from 2D images. In this work different image processing methods were tested to determine which method produces the best line extraction. The best results were obtained using Canny, Sobel, Prewitt, and Roberts Cross edge detectors for four colorspace components. Finally, a convex/concave line decision system was developed to produce preliminary results about the presence or absence of stairs in a given image.

UR - http://www.scopus.com/inward/record.url?scp=84940394562&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940394562&partnerID=8YFLogxK

U2 - 10.1109/NER.2015.7146698

DO - 10.1109/NER.2015.7146698

M3 - Conference contribution

AN - SCOPUS:84940394562

VL - 2015-July

SP - 615

EP - 618

BT - 2015 7th International IEEE/EMBS Conference on Neural Engineering, NER 2015

PB - IEEE Computer Society

T2 - 7th International IEEE/EMBS Conference on Neural Engineering, NER 2015

Y2 - 22 April 2015 through 24 April 2015

ER -

Recognition of ascending stairs from 2D images for control of powered lower limb prostheses

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this