Sensor fusion for ecologically valid obstacle identification: Building a comprehensive assistive technology platform for the visually impaired

John Ross Rizzo, Yubo Pan, Todd Hudson, Edward Wong, Yi Fang

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

Abstract

Sensor fusion represents a robust approach to ecologically valid obstacle identification in building a comprehensive electronic travel aid (ETA) for the blind and visually impaired. A stereoscopic camera system and an infrared sensor with 16 independent elements is proposed to be combined with a multi-scale convolutional neural network for this fusion framework. While object detection and identification can be combined with depth information from a stereo camera system, our experiments demonstrate that depth information may be inconsistent given material surfaces of specific potential collision hazards. This inconsistency can be easily remedied by supplementation with a more reliable depth signal from an alternate sensing modality. The sensing redundancy in this multi-modal strategy, as deployed in this platform, may enhance the situational awareness of a visually impaired end user, permitting more efficient and safer obstacle negotiation.

Original languageEnglish (US)
Title of host publication2017 7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509054541
DOIs
StatePublished - May 26 2017
Event7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017 - Sharjah, United Arab Emirates
Duration: Apr 4 2017Apr 6 2017

Other

Other7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017
CountryUnited Arab Emirates
CitySharjah
Period4/4/174/6/17

Fingerprint

Assistive Technology
Visually Impaired
Sensor Fusion
Fusion reactions
Cameras
Valid
Sensors
Sensing
Camera
Redundancy
Hazards
Infrared Sensor
Situational Awareness
Object Detection
Infrared radiation
Neural networks
Inconsistency
Hazard
Inconsistent
Alternate

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Applied Mathematics
  • Control and Optimization
  • Modeling and Simulation

Cite this

Rizzo, J. R., Pan, Y., Hudson, T., Wong, E., & Fang, Y. (2017). Sensor fusion for ecologically valid obstacle identification: Building a comprehensive assistive technology platform for the visually impaired. In 2017 7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017 [7934891] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMSAO.2017.7934891

Sensor fusion for ecologically valid obstacle identification : Building a comprehensive assistive technology platform for the visually impaired. / Rizzo, John Ross; Pan, Yubo; Hudson, Todd; Wong, Edward; Fang, Yi.

2017 7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 7934891.

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

Rizzo, JR, Pan, Y, Hudson, T, Wong, E & Fang, Y 2017, Sensor fusion for ecologically valid obstacle identification: Building a comprehensive assistive technology platform for the visually impaired. in 2017 7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017., 7934891, Institute of Electrical and Electronics Engineers Inc., 7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017, Sharjah, United Arab Emirates, 4/4/17. https://doi.org/10.1109/ICMSAO.2017.7934891
Rizzo JR, Pan Y, Hudson T, Wong E, Fang Y. Sensor fusion for ecologically valid obstacle identification: Building a comprehensive assistive technology platform for the visually impaired. In 2017 7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017. Institute of Electrical and Electronics Engineers Inc. 2017. 7934891 https://doi.org/10.1109/ICMSAO.2017.7934891
Rizzo, John Ross ; Pan, Yubo ; Hudson, Todd ; Wong, Edward ; Fang, Yi. / Sensor fusion for ecologically valid obstacle identification : Building a comprehensive assistive technology platform for the visually impaired. 2017 7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{e326781c312e46d7a06a0d8e671d930d,
title = "Sensor fusion for ecologically valid obstacle identification: Building a comprehensive assistive technology platform for the visually impaired",
abstract = "Sensor fusion represents a robust approach to ecologically valid obstacle identification in building a comprehensive electronic travel aid (ETA) for the blind and visually impaired. A stereoscopic camera system and an infrared sensor with 16 independent elements is proposed to be combined with a multi-scale convolutional neural network for this fusion framework. While object detection and identification can be combined with depth information from a stereo camera system, our experiments demonstrate that depth information may be inconsistent given material surfaces of specific potential collision hazards. This inconsistency can be easily remedied by supplementation with a more reliable depth signal from an alternate sensing modality. The sensing redundancy in this multi-modal strategy, as deployed in this platform, may enhance the situational awareness of a visually impaired end user, permitting more efficient and safer obstacle negotiation.",
author = "Rizzo, {John Ross} and Yubo Pan and Todd Hudson and Edward Wong and Yi Fang",
year = "2017",
month = "5",
day = "26",
doi = "10.1109/ICMSAO.2017.7934891",
language = "English (US)",
booktitle = "2017 7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Sensor fusion for ecologically valid obstacle identification

T2 - Building a comprehensive assistive technology platform for the visually impaired

AU - Rizzo, John Ross

AU - Pan, Yubo

AU - Hudson, Todd

AU - Wong, Edward

AU - Fang, Yi

PY - 2017/5/26

Y1 - 2017/5/26

N2 - Sensor fusion represents a robust approach to ecologically valid obstacle identification in building a comprehensive electronic travel aid (ETA) for the blind and visually impaired. A stereoscopic camera system and an infrared sensor with 16 independent elements is proposed to be combined with a multi-scale convolutional neural network for this fusion framework. While object detection and identification can be combined with depth information from a stereo camera system, our experiments demonstrate that depth information may be inconsistent given material surfaces of specific potential collision hazards. This inconsistency can be easily remedied by supplementation with a more reliable depth signal from an alternate sensing modality. The sensing redundancy in this multi-modal strategy, as deployed in this platform, may enhance the situational awareness of a visually impaired end user, permitting more efficient and safer obstacle negotiation.

AB - Sensor fusion represents a robust approach to ecologically valid obstacle identification in building a comprehensive electronic travel aid (ETA) for the blind and visually impaired. A stereoscopic camera system and an infrared sensor with 16 independent elements is proposed to be combined with a multi-scale convolutional neural network for this fusion framework. While object detection and identification can be combined with depth information from a stereo camera system, our experiments demonstrate that depth information may be inconsistent given material surfaces of specific potential collision hazards. This inconsistency can be easily remedied by supplementation with a more reliable depth signal from an alternate sensing modality. The sensing redundancy in this multi-modal strategy, as deployed in this platform, may enhance the situational awareness of a visually impaired end user, permitting more efficient and safer obstacle negotiation.

UR - http://www.scopus.com/inward/record.url?scp=85021427754&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021427754&partnerID=8YFLogxK

U2 - 10.1109/ICMSAO.2017.7934891

DO - 10.1109/ICMSAO.2017.7934891

M3 - Conference contribution

AN - SCOPUS:85021427754

BT - 2017 7th International Conference on Modeling, Simulation, and Applied Optimization, ICMSAO 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -