Robust estimation of simulated urinary volume from camera images under bathroom illumination

Chizuru Honda, Md Shoaib Bhuiyan, Haruki Kawanaka, Eiichi Watanabe, Koji Oguri

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

Abstract

General uroflowmetry method involves the risk of nosocomial infections or time and effort of the recording. Medical institutions, therefore, need to measure voided volume simply and hygienically. Multiple cylindrical model that can estimate the fluid flow rate from the photographed image using camera has been proposed in an earlier study. This study implemented a flow rate estimation by using a general-purpose camera system (Raspberry Pi Camera Module) and the multiple cylindrical model. However, large amounts of noise in extracting liquid region are generated by the variation of the illumination when performing measurements in the bathroom. So the estimation error gets very large. In other words, the specifications of the previous study's camera setup regarding the shutter type and the frame rate was too strict. In this study, we relax the specifications to achieve a flow rate estimation using a general-purpose camera. In order to determine the appropriate approximate curve, we propose a binarizing method using background subtraction at each scanning row and a curve approximation method using RANSAC. Finally, by evaluating the estimation accuracy of our experiment and by comparing it with the earlier study's results, we show the effectiveness of our proposed method for flow rate estimation.

Original languageEnglish
Title of host publication2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages415-418
Number of pages4
Volume2016-October
ISBN (Electronic)9781457702204
DOIs
Publication statusPublished - 13-10-2016
Event38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 - Orlando, United States
Duration: 16-08-201620-08-2016

Other

Other38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
CountryUnited States
CityOrlando
Period16-08-1620-08-16

Fingerprint

Toilet Facilities
Lighting
Cameras
Flow rate
Camera shutters
Specifications
Cross Infection
Noise
Error analysis
Flow of fluids
Scanning
Liquids
Experiments

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Honda, C., Bhuiyan, M. S., Kawanaka, H., Watanabe, E., & Oguri, K. (2016). Robust estimation of simulated urinary volume from camera images under bathroom illumination. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 (Vol. 2016-October, pp. 415-418). [7590728] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2016.7590728
Honda, Chizuru ; Bhuiyan, Md Shoaib ; Kawanaka, Haruki ; Watanabe, Eiichi ; Oguri, Koji. / Robust estimation of simulated urinary volume from camera images under bathroom illumination. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. pp. 415-418
@inproceedings{84a3043cf45c41f484718087637b68f1,
title = "Robust estimation of simulated urinary volume from camera images under bathroom illumination",
abstract = "General uroflowmetry method involves the risk of nosocomial infections or time and effort of the recording. Medical institutions, therefore, need to measure voided volume simply and hygienically. Multiple cylindrical model that can estimate the fluid flow rate from the photographed image using camera has been proposed in an earlier study. This study implemented a flow rate estimation by using a general-purpose camera system (Raspberry Pi Camera Module) and the multiple cylindrical model. However, large amounts of noise in extracting liquid region are generated by the variation of the illumination when performing measurements in the bathroom. So the estimation error gets very large. In other words, the specifications of the previous study's camera setup regarding the shutter type and the frame rate was too strict. In this study, we relax the specifications to achieve a flow rate estimation using a general-purpose camera. In order to determine the appropriate approximate curve, we propose a binarizing method using background subtraction at each scanning row and a curve approximation method using RANSAC. Finally, by evaluating the estimation accuracy of our experiment and by comparing it with the earlier study's results, we show the effectiveness of our proposed method for flow rate estimation.",
author = "Chizuru Honda and Bhuiyan, {Md Shoaib} and Haruki Kawanaka and Eiichi Watanabe and Koji Oguri",
year = "2016",
month = "10",
day = "13",
doi = "10.1109/EMBC.2016.7590728",
language = "English",
volume = "2016-October",
pages = "415--418",
booktitle = "2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Honda, C, Bhuiyan, MS, Kawanaka, H, Watanabe, E & Oguri, K 2016, Robust estimation of simulated urinary volume from camera images under bathroom illumination. in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. vol. 2016-October, 7590728, Institute of Electrical and Electronics Engineers Inc., pp. 415-418, 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016, Orlando, United States, 16-08-16. https://doi.org/10.1109/EMBC.2016.7590728

Robust estimation of simulated urinary volume from camera images under bathroom illumination. / Honda, Chizuru; Bhuiyan, Md Shoaib; Kawanaka, Haruki; Watanabe, Eiichi; Oguri, Koji.

2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. p. 415-418 7590728.

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

TY - GEN

T1 - Robust estimation of simulated urinary volume from camera images under bathroom illumination

AU - Honda, Chizuru

AU - Bhuiyan, Md Shoaib

AU - Kawanaka, Haruki

AU - Watanabe, Eiichi

AU - Oguri, Koji

PY - 2016/10/13

Y1 - 2016/10/13

N2 - General uroflowmetry method involves the risk of nosocomial infections or time and effort of the recording. Medical institutions, therefore, need to measure voided volume simply and hygienically. Multiple cylindrical model that can estimate the fluid flow rate from the photographed image using camera has been proposed in an earlier study. This study implemented a flow rate estimation by using a general-purpose camera system (Raspberry Pi Camera Module) and the multiple cylindrical model. However, large amounts of noise in extracting liquid region are generated by the variation of the illumination when performing measurements in the bathroom. So the estimation error gets very large. In other words, the specifications of the previous study's camera setup regarding the shutter type and the frame rate was too strict. In this study, we relax the specifications to achieve a flow rate estimation using a general-purpose camera. In order to determine the appropriate approximate curve, we propose a binarizing method using background subtraction at each scanning row and a curve approximation method using RANSAC. Finally, by evaluating the estimation accuracy of our experiment and by comparing it with the earlier study's results, we show the effectiveness of our proposed method for flow rate estimation.

AB - General uroflowmetry method involves the risk of nosocomial infections or time and effort of the recording. Medical institutions, therefore, need to measure voided volume simply and hygienically. Multiple cylindrical model that can estimate the fluid flow rate from the photographed image using camera has been proposed in an earlier study. This study implemented a flow rate estimation by using a general-purpose camera system (Raspberry Pi Camera Module) and the multiple cylindrical model. However, large amounts of noise in extracting liquid region are generated by the variation of the illumination when performing measurements in the bathroom. So the estimation error gets very large. In other words, the specifications of the previous study's camera setup regarding the shutter type and the frame rate was too strict. In this study, we relax the specifications to achieve a flow rate estimation using a general-purpose camera. In order to determine the appropriate approximate curve, we propose a binarizing method using background subtraction at each scanning row and a curve approximation method using RANSAC. Finally, by evaluating the estimation accuracy of our experiment and by comparing it with the earlier study's results, we show the effectiveness of our proposed method for flow rate estimation.

UR - http://www.scopus.com/inward/record.url?scp=85009110339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009110339&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2016.7590728

DO - 10.1109/EMBC.2016.7590728

M3 - Conference contribution

VL - 2016-October

SP - 415

EP - 418

BT - 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Honda C, Bhuiyan MS, Kawanaka H, Watanabe E, Oguri K. Robust estimation of simulated urinary volume from camera images under bathroom illumination. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Vol. 2016-October. Institute of Electrical and Electronics Engineers Inc. 2016. p. 415-418. 7590728 https://doi.org/10.1109/EMBC.2016.7590728