Real time motion compensation technology based on least square support vector machine prediction

• Autorzy: Song Zhehan , Feng Huajun , Xu Zhihai , Li Qi

Identyfikatory

DOI

10.37190/oa220208

• Języki publikacji: EN

Abstrakty

EN

When cameras are used in aerial photography, satellite imaging or other scenes, the motion of the observational target causes image blur. The corresponding motion compensation systems often present some response delay. Thus, we introduce effective and fast motion prediction for the target to achieve steady real-time motion compensation. We first analyze the target motion states to propose a fast and robust prediction method based on the least square support vector machine algorithm. Then, we evaluate the performance between ours and other state-of-the-art methods through experiments. Experimental results confirm that the proposed method provides a fast and robust prediction for target motion. At last, we embed our method with dual-resolution camera system to perform high-quality motion compensation effect in real time.

Słowa kluczowe

EN

motion compensation; motion prediction; dual-resolution camera system; least square support vector machine

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Optica Applicata
• Rocznik: 2022
• Tom: Vol. 52, nr 2
• Strony: 259--272
• Opis fizyczny: Bibliogr. 22 poz., rys., tab.

Twórcy

autor

Song Zhehan

• College of Optical Science and Engineering, Zhejiang University, Hangzhou 310012, China

autor

Feng Huajun

• College of Optical Science and Engineering, Zhejiang University, Hangzhou 310012, China

autor

Xu Zhihai

• College of Optical Science and Engineering, Zhejiang University, Hangzhou 310012, China

autor

Li Qi

• College of Optical Science and Engineering, Zhejiang University, Hangzhou 310012, China

Bibliografia

• [1] BODENSTORFER E., FURTLER J., BRODERSEN J., MAYER K. J., ECKEL C., GRAVOGL K., NACHTNEBEL H., High-speed line-scan camera with digital time delay integration, Proc. SPIE 6496, Real-Time Image Processing 2007, 64960I (26 February 2007), DOI: 10.1117/12.704516.
• [2] GOLIK B., WUELLER D., Measurement method for image stabilizing systems, Proc. SPIE 6502, Digital Photography III, 65020O (20 February 2007), DOI: 10.1117/12.703485.
• [3] CHIU C.W., CHAO P.C.P., WU D.Y., Optimal design of magnetically actuated optical image stabilizer mechanism for cameras in mobile phones via genetic algorithm, IEEE Transactions on Magnetics 43(6), 2007, pp. 2582–2584, DOI: 10.1109/TMAG.2007.893320.
• [4] DANIILIDIS K., KRAUSS C., HANSEN M., SOMMER G., Real-time tracking of moving objects with an active camera, Real-Time Imaging 4(1), 1998, pp. 3–20, DOI: 10.1006/rtim.1996.0060.
• [5] OIKE H., WU H., HUA C., WADA T., Clear image capture-active cameras system for tracking a high-speed moving object, [In] Proceedings of the Fourth International Conference on Informatics in Control, 2007, pp. 94–102.
• [6] OKUMURA K., OKU H., ISHIKAWA M., High-speed gaze controller for millisecond-order pan/tilt camera, [In] Proceedings of IEEE International Conference on Robotics and Automation, 2011, pp. 6186–6191, DOI: 10.1109/ICRA.2011.5980080.
• [7] HAYAKAWA T., WATANABE T., ISHIKAWA M., Real-time high-speed motion blur compensation system based on back-and-forth motion control of galvanometer mirror, Optics Express 23(25), 2015, pp. 31648–31661, DOI: 10.1364/OE.23.031648.
• [8] YITZHAKY Y., MILBERG R., YOHAEV S., KOPEIKA N.S., Comparison of direct blind deconvolution methods for motion-blurred images, Applied Optics 38(20), 1999, pp. 4325–4332, DOI: 10.1364/AO.38.004325.
• [9] ZHANG J., ZHANG Q., HE G., Blind deconvolution of a noisy degraded image, Applied Optics 48(12), 2009, pp. 2350–2355, DOI: 10.1364/AO.48.002350.
• [10] LEVIN A., SAND P., CHO T.S., DURAND F., FREEMAN W.T., Motion-invariant photography, ACM Transactions on Graphics 27(3), 2008, pp. 1–9, DOI: 10.1145/1360612.1360670.
• [11] ZHONG P., YU Q.Y., JIN G., Motion estimation and motion compensation based on matching technology of feature point, Journal of Optoelectronics Laser 15(1), 2004, pp. 73–77.
• [12] KUMAR S., AZARTASH H., BISWAS M., NGUYEN T., Real-time affine global motion estimation using phase correlation and its application for digital image stabilization, IEEE Transactions on Image Processing 20(12), 2011, pp. 3406–3418, DOI: 10.1109/TIP.2011.2156420.
• [13] PREVOST C.G., DESBIENS A., GAGNON E., Extended Kalman filter for state estimation and trajectory prediction of a moving object detected by an unmanned aerial vehicle, 2007 American Control Conference, IEEE, 2007, DOI: 10.1109/ACC.2007.4282823.
• [14] FU H.X., LIU S., SUN F., Ship motion prediction based on AGA-LSSVM, 2010 IEEE International Conference on Mechatronics and Automation, 2010, DOI: 10.1109/ICMA.2010.5589093.
• [15] ZHAO D., GAO Y., ZHANG Z., ZHANG Y., LUO T., Prediction of vehicle motion based on Markov model, [In] 2017 International Conference on Computer Systems, Electronics and Control (ICCSEC), 2017, pp. 205–209, DOI: 10.1109/ICCSEC.2017.8446749.
• [16] GUO J.Q., HE H.W., SUN C., ARIMA-based road gradient and vehicle velocity prediction for hybrid electric vehicle energy management, IEEE Transactions on Vehicular Technology 68(6), 2019, pp. 5309–5320, DOI: 10.1109/TVT.2019.2912893.
• [17] QIAO S.J., HAN N., ZHU X.W., et al., A dynamic trajectory prediction algorithm based on Kalman filter, Acta Electronica Sinica 46(2), 2018, pp. 418–423.
• [18] SIVANAGARAJA T., VELUVOLU K.C., Respiratory motion prediction using moving window based online training approach for LS-SVM, 2015 2nd International Conference on Signal Processing and Integrated Networks (SPIN), 2015, DOI: 10.1109/SPIN.2015.7095297.
• [19] DHANYA, J., RAGHUKANTH S.T.G., Ground motion prediction model using artificial neural network, Pure and Applied Geophysics 175(3), 2018, pp. 1035–1064, DOI: 10.1007/s00024-017-1751-3.
• [20] CHENG X., CHEN S., DIAO C., LIU M., LI G., ZHANG H., Simplifying neural network based model for ship motion prediction: a comparative study of sensitivity analysis, International Conference on Offshore Mechanics and Arctic Engineering, American Society of Mechanical Engineers, 2017, DOI: 10.1115/OMAE2017-61474.
• [21] FLORENT A., DE LA FORTELLE A., An LSTM network for highway trajectory prediction, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 2017, DOI: 10.1109/ITSC.2017.8317913.
• [22] ZHANG P., OUYANG W., ZHANG P., XUE J., ZHENG N., SR-LSTM: state refinement for LSTM towards pedestrian trajectory prediction, [In] Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019, pp. 12085–12094, DOI: 10.1109/CVPR.2019.01236.