Reading circular analogue gauges using digital image processing

Jakob S. Lauridsen, Julius A. G. Graasmé, Malte Pedersen, David Getreuer Jensen, Søren Holm Andersen, Thomas B. Moeslund

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

This paper presents an image processing based pipeline for automated recognition and translation of pointer movement in analogue circular gauges. The proposed method processes an input video frame-wise in a module based manner. Noise is minimized in each image using a bilateral filter before a Gaussian mean adaptive threshold is applied to segment objects. Subsequently, the objects are described by a set of proposed features and classified using a naive Bayes classifier trained by Expectation Maximization. The pointer is classified by the Mahalanobis distance and the angle of the pointer is determined using PCA. The output is a low pass filtered digital time series based on the temporal estimations of the pointer angle. Seven test videos have been processed by the algorithm showing promising results. Both source code and video data are publicly available.
Keywords: Computer Vision, Circular Analogue Gauge, Gauge Reading Principal Component Analysis, Expectation Maximization, Digital Time Series, Parametric Object Classification.
Original languageEnglish
Title of host publicationProceedings of the 14th International Conference on Computer Vision Theory and Applications
Publication statusAccepted/In press - 2019

Fingerprint

Gages
Image processing
Time series
Principal component analysis
Computer vision
Classifiers
Pipelines

Cite this

Lauridsen, J. S., Graasmé, J. A. G., Pedersen, M., Jensen, D. G., Andersen, S. H., & Moeslund, T. B. (Accepted/In press). Reading circular analogue gauges using digital image processing. In Proceedings of the 14th International Conference on Computer Vision Theory and Applications
Lauridsen, Jakob S. ; Graasmé, Julius A. G. ; Pedersen, Malte ; Jensen, David Getreuer ; Andersen, Søren Holm ; Moeslund, Thomas B. / Reading circular analogue gauges using digital image processing. Proceedings of the 14th International Conference on Computer Vision Theory and Applications. 2019.
@inproceedings{051d4f2ee4d342f3a39d36314e878549,
title = "Reading circular analogue gauges using digital image processing",
abstract = "This paper presents an image processing based pipeline for automated recognition and translation of pointer movement in analogue circular gauges. The proposed method processes an input video frame-wise in a module based manner. Noise is minimized in each image using a bilateral filter before a Gaussian mean adaptive threshold is applied to segment objects. Subsequently, the objects are described by a set of proposed features and classified using a naive Bayes classifier trained by Expectation Maximization. The pointer is classified by the Mahalanobis distance and the angle of the pointer is determined using PCA. The output is a low pass filtered digital time series based on the temporal estimations of the pointer angle. Seven test videos have been processed by the algorithm showing promising results. Both source code and video data are publicly available.Keywords: Computer Vision, Circular Analogue Gauge, Gauge Reading Principal Component Analysis, Expectation Maximization, Digital Time Series, Parametric Object Classification.",
author = "Lauridsen, {Jakob S.} and Graasm{\'e}, {Julius A. G.} and Malte Pedersen and Jensen, {David Getreuer} and Andersen, {S{\o}ren Holm} and Moeslund, {Thomas B.}",
year = "2019",
language = "English",
booktitle = "Proceedings of the 14th International Conference on Computer Vision Theory and Applications",

}

Lauridsen, JS, Graasmé, JAG, Pedersen, M, Jensen, DG, Andersen, SH & Moeslund, TB 2019, Reading circular analogue gauges using digital image processing. in Proceedings of the 14th International Conference on Computer Vision Theory and Applications.

Reading circular analogue gauges using digital image processing. / Lauridsen, Jakob S.; Graasmé, Julius A. G.; Pedersen, Malte; Jensen, David Getreuer; Andersen, Søren Holm; Moeslund, Thomas B.

Proceedings of the 14th International Conference on Computer Vision Theory and Applications. 2019.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Reading circular analogue gauges using digital image processing

AU - Lauridsen, Jakob S.

AU - Graasmé, Julius A. G.

AU - Pedersen, Malte

AU - Jensen, David Getreuer

AU - Andersen, Søren Holm

AU - Moeslund, Thomas B.

PY - 2019

Y1 - 2019

N2 - This paper presents an image processing based pipeline for automated recognition and translation of pointer movement in analogue circular gauges. The proposed method processes an input video frame-wise in a module based manner. Noise is minimized in each image using a bilateral filter before a Gaussian mean adaptive threshold is applied to segment objects. Subsequently, the objects are described by a set of proposed features and classified using a naive Bayes classifier trained by Expectation Maximization. The pointer is classified by the Mahalanobis distance and the angle of the pointer is determined using PCA. The output is a low pass filtered digital time series based on the temporal estimations of the pointer angle. Seven test videos have been processed by the algorithm showing promising results. Both source code and video data are publicly available.Keywords: Computer Vision, Circular Analogue Gauge, Gauge Reading Principal Component Analysis, Expectation Maximization, Digital Time Series, Parametric Object Classification.

AB - This paper presents an image processing based pipeline for automated recognition and translation of pointer movement in analogue circular gauges. The proposed method processes an input video frame-wise in a module based manner. Noise is minimized in each image using a bilateral filter before a Gaussian mean adaptive threshold is applied to segment objects. Subsequently, the objects are described by a set of proposed features and classified using a naive Bayes classifier trained by Expectation Maximization. The pointer is classified by the Mahalanobis distance and the angle of the pointer is determined using PCA. The output is a low pass filtered digital time series based on the temporal estimations of the pointer angle. Seven test videos have been processed by the algorithm showing promising results. Both source code and video data are publicly available.Keywords: Computer Vision, Circular Analogue Gauge, Gauge Reading Principal Component Analysis, Expectation Maximization, Digital Time Series, Parametric Object Classification.

M3 - Article in proceeding

BT - Proceedings of the 14th International Conference on Computer Vision Theory and Applications

ER -

Lauridsen JS, Graasmé JAG, Pedersen M, Jensen DG, Andersen SH, Moeslund TB. Reading circular analogue gauges using digital image processing. In Proceedings of the 14th International Conference on Computer Vision Theory and Applications. 2019