DOI:
https://doi.org/10.14483/23448393.20057Published:
2024-03-14Issue:
Vol. 29 No. 1 (2024): January-AprilSection:
Computational IntelligenceEstimating Acceleration from a Single Uniform Linear Motion-Blurred Image using Homomorphic Mapping and Machine Learning
Estimación de la aceleración a partir de una única imagen borrosa de movi-miento lineal uniforme utilizando el enfoque de mapeo homomórfico y apren-dizaje automático
Keywords:
acceleration, computer vision, deep learning, machine learning, motion blur, vision-based measurement (en).Keywords:
aceleración, visión artificial, aprendizaje profundo, aprendizaje automático, desenfoque de movimiento, medición basada en la visión (es).Downloads
Abstract (en)
Context: Vision-based measurement (VBM) systems are becoming popular as an affordable and suitable alternative for scientific and engineering applications. When cameras are used as instruments, motion blur usually emerges as a recurrent and undesirable image degradation, which in fact contains kinematic information that is usually dismissed.
Method: This paper introduces an alternative approach to measure relative acceleration from a real invariant uniformly accelerated linear motion-blurred image. This is done by using homomorphic mapping to extract the characteristic Point Spread Function (PSF) of the blurred image, as well as machine learning regression. A total of 125 uniformly accelerated motion-blurred pictures were taken in a light- and distance-controlled environment, at five different accelerations ranging between 0,64 and 2,4 m/s2. This study evaluated 19 variants such as tree ensembles, Gaussian processes (GPR), and linear, support vector machine (SVM), and tree regression.
Results: The best RMSE result corresponds to GPR (Matern 5/2), with 0,2547 m/s2 and a prediction speed of 530 observations per second (obs/s). Additionally, some novel deep learning methods were used to obtain the best RMSE value (0,4639 m/s2 for Inception ResNet v2, with a prediction speed of 11 obs/s.
Conclusions: The proposed method (homomorphic mapping and machine learning) is a valid alternative for calculating acceleration from invariant motion blur in real-time applications when additive noise is not dominant, even surpassing the deep learning techniques evaluated.
Abstract (es)
Contexto: Los sistemas de medición basados en visión (VBM) están ganando popularidad como una alternativa asequible y apta para aplicaciones científicas y de ingeniería. Cuando se utilizan cámaras como instrumentos, el desenfoque de movimiento suele surgir como una degradación de imagen recurrente e indeseable, que de hecho contiene información cinemática que normalmente se descarta.
Método: Este artículo introduce un enfoque alternativo para medir la aceleración relativa a partir de una imagen borrosa real de movimiento lineal uniformemente acelerado invariante. Esto se hace utilizando mapeo homomórfico para extraer la point spread function (PSF) característica de la imagen borrosa, así como regresión de aprendizaje automático. Se tomaron un total de 125 imágenes borrosas de movimiento uniformemente acelerado en un entorno de luz y distancia controladas, en cinco aceleraciones diferentes en un rango de 0,64 a 2,4 m/s2. Este estudio evaluó 19 variantes tales como ensambles de árboles, procesos Gaussianos (GPR) y regresión lineal, regresión con máquina de vectores de soporte (SVM) y regresión con árboles.
Resultados: El mejor resultado de RMSE corresponde a GPR (Matern 5/2), con 0,2547 m/s2 y una velocidad de predicción de 530 observaciones por segundo (obs/s). Además, se utilizaron algunos métodos novedosos de aprendizaje profundo para obtener el mejor valor de RMSE (0,4639 m/s2 para Inception ResNet v2, con una velocidad de predicción de 11 obs/s.
Conclusiones: El método propuesto (mapeo homomórfico y aprendizaje automático) es una alternativa válida para calcular la aceleración a partir del desenfoque de movimiento invariante en aplicaciones en tiempo real cuando el ruido aditivo no es dominante, incluso superando las técnicas de aprendizaje profundo evaluadas.
References
S. Shirmohammadi and A. Ferrero, “Camera as the instrument: the rising trend of vision based measurement,” IEEE Instrumenta-tion Measurement Magazine, vol. 17, no. 3, pp. 41–47, 2014. https://doi.org/10.1109/MIM.2014.6825388
S. S. Beauchemin, M. A. Bauer, T. Kowsari, and J. Cho, “Portable and scalable vision-based vehicular instrumentation for the analysis of driver intentionality,” IEEE Transactions on Instrumentation and Measurement, vol. 61, no. 2, pp. 391–401, 2012. https://doi.org/10.1109/TIM.2011.2164854
P. Dutkiewicz, M. Kielczewski, K. Kozłowski, and D. Pazderski, “Vision localization system for mobile robot with velocities and acceleration estimator,” Bulletin of the Polish Academy of Sciences: Technical Sciences, vol. 58, no. 1, pp. 29–41, 2010. https://doi.org/10.2478/v10175-010-0003-9
J. Leifer, B. Weems, S. C. Kienle, and A. M. Sims, “Three-dimensional acceleration measurement using videogrammetry tracking data,” Experimental Mechanics, vol. 51, no. 2, pp. 199–217, 2011. https://doi.org/10.1007/s11340-010-9352-4
F. Karimirad, S. Chauhan, and B. Shirinzadeh, “Vision-based force measurement using neural networks for biological cell mi-croinjection,” Journal of Biomechanics, vol. 47, no. 5, pp. 1157–1163, 2014. https://doi.org/10.1016/j.jbiomech.2013.12.007
Y. Fukuda, M. Q. Feng, and M. Shinozuka, “Cost-effective vision-based system for monitoring dynamic response of civil engineer-ing structures,” Structural Control and Health Monitoring, vol. 17, no. 8, pp. 918–936, 2010. https://doi.org/10.1002/stc.360
S. Benameur, M. Mignotte, and F. Lavoie, “An homomorphic filtering and expectation maximization approach for the point spread function estimation in ultrasound imaging,” in Image Processing: Algorithms and Systems X; and Parallel Processing for Imaging Applications II, International Society for Optics and Photonics, vol. 8295, 2012, 82950T. https://doi.org/10.1117/12.903785
O. Mattausch and O. Goksel, “Image-based psf estimation for ultrasound training simulation,” in International Workshop on Simulation and Synthesis in Medical Imaging, Springer, 2016, pp. 23–33. https://doi.org/10.1007/978-3-319-46630-9_3
A. P. Janwale and S. S. Lomte, “Enhancement of cotton leaves images using various filtering techniques,” in Data Management, Analytics and Innovation (ICDMAI), 2017 International Conference on, IEEE, 2017, pp. 303–305. https://doi.org/10.1109/ICDMAI.2017.8073530
J. Kim, K. Kim, and H. Sohn, “Autonomous dynamic displacement estimation from data fusion of acceleration and intermittent displacement measurements,” Mechanical Systems and Signal Processing, vol. 42, no. 1-2, pp. 194–205, 2014. https://doi.org/10.1016/j.ymssp.2013.09.014
F. Zheng, L. Shao, V. Racic, and J. Brownjohn, “Measuring human-induced vibrations of civil engineering structures via vision-based motion tracking,” Measurement, vol. 83, pp. 44–56, 2016. https://doi.org/10.1016/j.measurement.2016.01.015
D. Ribeiro, R. Calçada, J. Ferreira, and T. Martins, “Non-contact measurement of the dynamic displacement of railway bridges using an advanced video-based system,” Engineering Structures, vol. 75, pp. 164–180, 2014. https://doi.org/10.1016/j.engstruct.2014.04.051
D. Béréziat and I. Herlin, “Motion and acceleration from image assimilation with evolution models,” Digital Signal Processing, vol. 83, pp. 45–58, 2018. https://doi.org/10.1016/j.dsp.2018.08.008
A. Y. Sun, D. Wang, and X. Xu, “Monthly streamflow forecasting using gaussian process regression,” Journal of Hydrology, vol. 511, pp. 72–81, 2014. https://doi.org/10.1016/j.jhydrol.2014.01.023
S. Chatterjee and A. S. Hadi, Sensitivity analysis in linear regression. John Wiley Sons, 2009, vol. 327.
A. Girard, C. Rasmussen, J. Q. Candela, and R. Murray-Smith, “Gaussian process priors with uncertain inputs application to multiple-step ahead time series forecasting,” Advances in neural information processing systems, vol. 15, pp. 545–552, 2002.
C. E. Rasmussen, “Gaussian processes in machine learning,” Summer School on Machine Learning, pp. 63–71, 2003. https://doi.org/10.1007/978-3-540-28650-9_4
D. Anguita, A. Ghio, N. Greco, L. Oneto, and S. Ridella, “Model selection for support vector machines: Advantages and disad-vantages of the machine learning theory,” in The 2010 international joint conference on neural networks (IJCNN), IEEE, 2010, pp. 1–8. https://doi.org/10.1109/IJCNN.2010.5596450
T. Chan and J. Shen, Image processing and analysis. Society for Industrial and Applied Mathematics SIAM, 2005, vol. 94.
H. Lin and K. Li, “Motion blur removal and its application to vehicle speed detection,” Electrical Engineering, no. 2, pp. 3407–3410, 2004.
S. Som, “Analysis of the effect of linear smear on photographic images,” JOSA, vol. 61, no. 7, pp. 859–864, 1971. https://doi.org/10.1364/JOSA.61.000859
X. Y. Qi, L. Zhang, and C. L. Tan, “Motion deblurring for optical character recognition,” in Document Analysis and Recognition, 2005. Proceedings. Eighth International Conference on, IEEE, 2005, pp. 389–393.
Y. Yitzhaky and A. Stern, “Restoration of interlaced images degraded by variable velocity motion,” Optical Engineering, vol. 42, no. 12, pp. 3557–3565, 2003. https://doi.org/10.1117/1.1621406
Y. Yitzhaky, I. Mor, A. Lantzman, and N. Kopeika, “Direct method for restoration of motion-blurred images,” Journal of the Optical Society of America, vol. 15, no. 6, pp. 1512–1519, 1998. https://doi.org/10.1364/JOSAA.15.001512
M. Cannon, “Blind deconvolution of spatially invariant image blurs with phase,” Acoustics, Speech and Signal Processing, IEEE Transactions on, vol. 24, no. 1, pp. 58–63, 1976. https://doi.org/10.1109/TASSP.1976.1162770
M. Sakano, N. Suetake, and E. Uchino, “Robust identification of motion blur parameters by using angles of gradient vectors,” in Intelligent Signal Processing and Communications, 2006. ISPACS’06. International Symposium on, IEEE, 2006, pp. 522–525. https://doi.org/10.1109/ISPACS.2006.364711
M. E. Moghaddam and M. Jamzad, “Linear motion blur parameter estimation in noisy images using fuzzy sets and power spec-trum,” EURASIP Journal on Advances in Signal Processing, vol. 2007, no. 1, pp. 1–8, 2007. https://doi.org/10.1155/2007/68985
M. A. Lata, S. Ghosh, F. Bobi, and M. A. Yousuf, “Novel method to assess motion blur kernel parameters and comparative study of restoration techniques using different image layouts,” in 2016 5th International Conference on Informatics, Electronics and Vision (ICIEV), IEEE, 2016, pp. 367–372. https://doi.org/10.1109/ICIEV.2016.7760027
H.-Y. Lin, “Vehicle speed detection and identification from a single motion blurred image,” in Application of Computer Vision, 2005. WACV/MOTIONS’05 Volume 1. Seventh IEEE Workshops on, IEEE, vol. 1, 2005, pp. 461–467.
M. Celestino and O. Horikawa, “Velocity measurement based on image blur,” Computer graphics and image processing, vol. 3, pp. 633–642, 2008.
H. Pazhoumand-Dar, A. M. T. Abolhassani, and E. Saeedi, “Object speed estimation by using fuzzy set,” World Academy of Sci-ence, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineer-ing, vol. 4, no. 4, pp. 688–691, 2010.
S. Rezvankhah, A. A. Bagherzadeh, H. Moradi, and B. N. A. Member, “A Real-time Velocity Estimation using Motion Blur in Air Hockey,” in 2012 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2012, pp. 1767-1772, https://doi.org/10.1109/ROBIO.2012.6491223
J. Mohammadi and A. Taherkhani, “Object Speed Estimation in Frequency Domain of Single Taken Image,” Journal of Basic and Applied Scientific Research, vol. 3, pp. 120-124, 2013.
S. McCloskey, Y. Ding, and J. Yu, “Design and estimation of coded exposure point spread functions,” IEEE transactions on pat-tern analysis and machine intelligence, vol. 34, no. 10, p. 2071, 2012. https://doi.org/10.1109/TPAMI.2012.108
A. Agrawal, Y. Xu, and R. Raskar, “Invertible motion blur in video,” in ACM Transactions on Graphics (TOG), vol. 28, 2009, p. 95. https://doi.org/10.1145/1531326.1531401
M. Lee, K.-S. Kim, and S. Kim, “Measuring vehicle velocity in real time using modulated motion blur of camera image data,” IEEE Transactions on Vehicular Technology, vol. 66, no. 5, pp. 3659–3673, 2016. https://doi.org/10.1109/TVT.2016.2600281
M. Lee, “A study on measuring vehicle velocity in real time using modulated motion blur of camera image data,” Ph.D. disser-tation, Korea Advanced Institute of Science and Technology, 2017. https://doi.org/10.1109/TVT.2016.2600281
M. Lee, K.-S. Kim, J. Cho, and S. Kim, “Development of a vehicle body velocity sensor using modulated motion blur,” in 2017 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), IEEE, 2017, pp. 406–411. https://doi.org/10.1109/AIM.2017.8014051
J. Jing, F. Xiao, L. Yang, S. Wang, and B. Yu, “Measurements of velocity field and diameter distribution of particles in multi-phase flow based on trajectory imaging,” Flow Measurement and Instrumentation, vol. 59, pp. 103–113, 2018. https://doi.org/10.1016/j.flowmeasinst.2017.12.005
K. Matsuo and T. Yakoh, “Position and velocity measurement method from a single image using modulated illumination,” in 2018 IEEE 15th International Workshop on Advanced Motion Control (AMC), IEEE, 2018, pp. 353–359. https://doi.org/10.1109/AMC.2019.8371117
J. A. Dwicahya, N. Ramadijanti, and A. Basuki, “Moving object velocity detection based on motion blur on photos using gray level,” in 2018 International Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC), IEEE, 2018, pp. 192–198. https://doi.org/10.1109/KCIC.2018.8628598
J. A. Cortes-Osorio, J. B. Gomez-Mendoza, and J. C. Riano-Rojas, “Velocity estimation from a single linear motion blurred image using discrete cosine transform,” IEEE Transactions on Instrumentation and Measurement, vol. 68, no. 10, pp. 4038–4050, 2019. https://doi.org/10.1109/TIM.2018.2882261
J. A. Cortes-Osorio, “A contribution to the estimation of kinematic quantities from linear motion blurred images,” Ph.D. disser-tation, Universidad Nacional de Colombia Sede Manizales, 2020.
Q. Guo et al., “Learning to Adversarially Blur Visual Object Tracking,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021. https://doi.org/10.1109/ICCV48922.2021.01066
M. Li, H. Du, Q. Zhang, and J. Wang, “Improved particle image velocimetry through cell segmentation and competitive surviv-al,” IEEE Transactions on Instrumentation and Measurement, vol. 57, no. 6, pp. 1221–1229, 2008. https://doi.org/10.1109/TIM.2007.915443
X. Liu and J. Katz, “Instantaneous pressure and material acceleration measurements using a four-exposure piv system,” Experi-ments in Fluids, vol. 41, no. 2, p. 227, 2006. https://doi.org/10.1007/s00348-006-0152-7
H. Zhou, M. Chen, L. Zhang, N. Ye, and C. Tao, “Measuring shape and motion of a high-speed object with designed features from motion blurred images,” Measurement, vol. 145, pp. 559–567, 2019. https://doi.org/10.1016/j.measurement.2019.05.023
L. Li, T. Martin, and X. Xu, “A novel vision-based real-time method for evaluating postural risk factors associated with musculo-skeletal disorders,” Appl. Ergon., vol. 87, p. 103 138, 2020. https://doi.org/10.1016/j.apergo.2020.103138
C. Yu, X. Bi, and Y. Fan, “Deep learning for fluid velocity field estimation: A review,” Ocean Engineering, vol. 271, p. 113 693, 2023. https://doi.org/10.1016/j.oceaneng.2023.113693
P. Chu, B. T. Wolfe, and Z. Wang, “Measurement of incandescent microparticle acceleration using stereoscopic imaging,” Review of Scientific Instruments, vol. 89, no. 10, 2018. https://doi.org/10.1063/1.5034311
G. Chen, L. Li, C. Zhao, R. Huang, and F. Guo, “Acceleration characteristics of a rockslide using the particle image velocimetry technique,” Journal of Sensors, vol. 2016, 2016. https://doi.org/10.1155/2016/2650871
D. C. Luvizon, B. T. Nassu, and R. Minetto, “A video-based system for vehicle speed measurement in urban roadways,” IEEE Transactions on Intelligent Transportation Systems, vol. 18, no. 6, pp. 1393–1404, 2017. https://doi.org/10.1109/TITS.2016.2600281
J. X. Wang, “Research of vehicle speed detection algorithm in video surveillance,” in Audio, Language and Image Processing (ICALIP), 2016 International Conference on, IEEE, 2016, pp. 349–352. https://doi.org/10.1109/ICALIP.2016.7846482
K. V. K. Kumar, P. Chandrakant, S. Kumar, and K. J. Kushal, “Vehicle speed detection using corner detection,” in 2014 Fifth International Conference on Signal and Image Processing, 2014, pp. 253–258. https://doi.org/10.1109/ICSIP.2014.46
J. Dong, Y. Song, H. Wang, J. Zeng, and Z. Wu, “Predicting flow velocity affected by seaweed resistance using svm regression,” in Computer Application and System Modeling (ICCASM), 2010 International Conference on, vol. 2, 2010, pp. V2–273. https://doi.org/10.1109/ICCASM.2010.5620588
O. Genç and A. Dag˘, “A machine learning-based approach to predict the velocity profiles in small streams,” Water Resources Management, vol. 30, no. 1, pp. 43–61, 2016. https://doi.org/10.1007/s11269-015-1123-7
M. Morimoto, K. Fukami, and K. Fukagata, “Experimental velocity data estimation for imperfect particle images using machine learning,” arXiv preprint arXiv:2005.00756, 2020. https://doi.org/10.1063/5.0060760
P. J. Chun, T. Yamane, S. Izumi, and N. Kuramoto, “Development of a machine learning-based damage identification method using multipoint simultaneous acceleration measurement results,” Sensors, vol. 20, no. 10, p. 2780, 2020. https://doi.org/10.3390/s20102780
W. Kim, M. Tanaka, M. Okutomi, and Y. Sasaki, “Learning-based human segmentation and velocity estimation using automatic labeled lidar sequence for training,” IEEE Access, vol. 8, pp. 88 443–88 452, 2020. https://doi.org/10.1109/ACCESS.2020.2993299
B. Major, D. Fontijne, A. Ansari, et al., “Vehicle detection with automotive radar using deep learning on range-azimuth-doppler tensors,” in 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019, pp. 924–932. https://doi.org/10.1109/ICCVW.2019.00121
C. Guo, Y. Fan, C. Yu, Y. Han, and X. Bi, “Time-resolved particle image velocimetry algorithm based on deep learning,” IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1–13, 2022. https://doi.org/10.1109/TIM.2022.3141750
S. Cai, J. Liang, Q. Gao, C. Xu, and R. Wei, “Particle image velocimetry based on a deep learning motion estimator,” IEEE Trans-actions on Instrumentation and Measurement, vol. 69, no. 6, pp. 3538–3554, 2020. https://doi.org/10.1109/TIM.2019.2932649
A. Oppenheim, R. Schafer, and T. Stockham, “Nonlinear filtering of multiplied and convolved signals,” IEEE Transactions on Audio and Electroacoustics, vol. 16, no. 3, pp. 437–466, 1968. https://doi.org/10.1109/TAU.1968.1161990
I. Pitas and A. N. Venetsanopoulos, “Homomorphic Filters,” in Nonlinear Digital Filters: Principles and Applications, Springer US, 1990, pp. 217–243. https://doi.org/10.1007/978-1-4757-6017-0_7
T. M. Cannon, “Digital image deblurring by nonlinear homomorphic filtering,” Utah University, Salt Lake City School of Compu-ting, Tech. Rep., 1974. https://doi.org/10.21236/ADA002735
Y. Yitzhaky, R. Milberg, S. Yohaev, and N. S. Kopeika, “Comparison of direct blind deconvolution methods for motion-blurred images,” Applied Optics, vol. 38, no. 20, pp. 4325–4332, 1999. https://doi.org/10.1364/AO.38.004325
J. A. Cortes-Osorio, D. A. Muñoz-Acosta, and C. D. López-Robayo, “Design and construction of an electromechanical slider for the kinematic study of linear motion blurred images,” INGE CUC, vol. 16, no. 1, pp. 80–90, 2020. https://doi.org/10.17981/ingecuc.16.1.2020.06
Basler, aca2000-165um-baslerace, https://www.baslerweb.com/en/products/cameras/area- scan- cameras/ace/aca2000- 165um/,
(Accessed on 06/11/2017), Nov. 2017.
Ricoh lens fl-cc0814a-2m, https://www.baslerweb.com/en/products/vision-components/lenses/ricoh-lens-fl-cc0814a-2m-f1-4-f8mm- 2-3/, (Accessed on 06/11/2017), Nov. 2017.
BT.601: Studio encoding parameters of digital television for standard 4:3 and wide screen 16:9 aspect ratios, http://www.itu.int/rec/rrec-bt.601 , 2017.
E. Izquierdo-Verdiguier, L. Gomez-Chova, L. Bruzzone, and G. Camps-Valls, “Semisupervised kernel feature extraction for re-mote sensing image analysis,” IEEE Transactions on Geoscience and Remote Sensing, vol. 52, no. 9, pp. 5567–5578, 2014. https://doi.org/10.1109/TGRS.2013.2290372
T. Bouwmans, S. Javed, H. Zhang, Z. Lin, and R. Otazo, “On the applications of robust PCA in image and video processing,” Proceedings of the IEEE, vol. 106, no. 8, pp. 1427–1457, 2018. https://doi.org/10.1109/JPROC.2018.2853589
P. S. GmbH, Cobra4 sensor unit 3D acceleration, https://repository.curriculab.net/files/bedanl.pdf/12650.00/1265000e.pdf, 2018.
L. Kirkup and R. B. Frenkel, An introduction to uncertainty in measurement: using the GUM (guide to the expression of uncer-tainty in measurement). Cambridge University Press, 2006. https://doi.org/10.1017/CBO9780511755538
R. H. Dieck, Measurement uncertainty: methods and applications. ISA, 2007.
A. J. Sederman, M. D. Mantle, C. Buckley, and L. F. Gladden, “MRI technique for measurement of velocity vectors, accelera-tion, and autocorrelation functions in turbulent flow,” Journal of Magnetic Resonance, vol. 166, no. 2, pp. 182–189, 2004. https://doi.org/10.1016/j.jmr.2003.10.016
K. Komiya, T. Kurihara, and S. Ando, “3D particle image velocimetry using correlation image sensor,” in Proc. SICE Annual Conf. 2011, Sep. 2011, pp. 2774–2778.
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
License
Copyright (c) 2024 Jimy Alexander Cortés-Osorio, Juan Bernardo Gómez-Mendoza, Juan Carlos Riaño-Rojas
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
From the edition of the V23N3 of year 2018 forward, the Creative Commons License "Attribution-Non-Commercial - No Derivative Works " is changed to the following:
Attribution - Non-Commercial - Share the same: this license allows others to distribute, remix, retouch, and create from your work in a non-commercial way, as long as they give you credit and license their new creations under the same conditions.
2.jpg)
