In sports science research, the dynamic non-uniform blur caused by the movement of running athletes is a challenging problem in computer vision, that seriously affects the judgment accuracy of the finish-line photography system. With the rapid development of deep learning technology, image preprocessing, object identification, and object classification have been widely used and studied. This work proposes multi-scale convolutional neural network image deblurring to eliminate dynamic blur generated by the athletes in the shooting process. This network comprises three end-to-end convolutional neural subnetworks of different scales to recover the blurry athlete image caused by various factors on the field. The system effectively extracts the detailed edge of the image on each scale from coarse to fine. Many experiments show that this method can deblur the image captured by the finish-line photography system in real-time and rapidly achieve a better visual effect in the athlete’s dynamic image.
BrownlieL. Aerodynamic drag reduction in winter sports: the quest for “free speed”. Proc IMechE Part P: J Sports Engineering Technology2021; 235(4): 365–404.
2.
AdamsKKieferAPanchukD, et al. From the field of play to the laboratory: recreating the demands of competition with augmented reality simulated sport. J Sports Sci2020; 38(5): 486–493.
3.
ShishidoHKitaharaI. Calibration of multiple sparsely distributed cameras using a mobile camera. Proc IMechE, Part P: J Sports Engineering and Technology2020; 234(1): 37–48.
4.
GaoHTaoXShenX, et al. Dynamic scene deblurring with parameter selective sharing and nested skip connections. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2019, pp.3848–3856. New York: IEEE.
5.
NahSKimTHLeeKM. Deep multi-scale convolutional neural network for dynamic scene deblurring. In: IEEE conference on computer vision and pattern recognition (CVPR), 2017, pp.3848–3856. New York: IEEE.
6.
GuptaAJoshiNZitnickCL, et al. Single image deblurring using motion density functions. In: European conference on computer vision, 2010, pp.171–184. Springer.
7.
AndreB. Telescope: an automatic feature extraction and transformation approach for time series forecasting on a level-playing field. In: IEEE international conference on data engineering, 2020, pp.1902–1905. New York: IEEE.
8.
WangYTaoXQiX, et al. Image inpainting via generative multi-column convolutional neural networks. In: Advances in neural information processing systems, 2018, pp.331–340. MIT Press.
9.
ZhangYLiK. Image super-resolution using very deep residual channel attention networks. In: Proceedings of the European conference on computer vision (ECCV), 2018, pp.286–301. Cham: Springer.
10.
BonfittoATonoliAFeracoS, et al. Pattern recognition neural classifier for fall detection in rock climbing. Proc ImechE, Part P: J Sports Engineering and Technology2019; 233(4): 478–488.
11.
BaninoABarryCUriaB, et al. Vector-based navigation using grid-like representations in artificial agents. Nature2018; 557(7705): 429–433.
12.
TaoXGaoHShenX, et al. Scale-recurrent network for deep image deblurring. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp.8174–8182. New York: IEEE.
13.
MaoXShenCYangYB. Image restoration using very deep convolutional encoder decoder networks with symmetric skip connections. In: Advances in neural information processing systems, 2016, pp.2802–2810 Publishier: MIT Press.
14.
DongWZhangLShiG, et al. Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE Trans Image Process2011; 20(7): 1838–1857.
15.
PanHJingZLeiM, et al. A sparse proximal newton splitting method for constrained image deblurring. Neurocomputing2013; 122: 245–257.
16.
OsherSBurgerMGoldfarbD, et al. An iterative regularization method for total variationbased image restoration. Multiscale Model Simul2005; 4(2): 460–489.
17.
LiLPanJLaiWS, et al. Learning a discriminative prior for blind image deblurring. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp.6616–6625. New York: IEEE.
18.
ZhangXDongHHuZ, et al. Gated fusion network for joint image deblurring and superresolution. arXiv preprint:180710806, 2018.
19.
ZhangDLiangZShaoJ. Joint image deblurring and super-resolution with attention dual supervised network. Neurocomputing2020; 412: 187–196.
20.
NahSHyunKTMuK. Deep multi-scale convolutional neural network for dynamic scene deblurring. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp.3883–3891. New York: IEEE.
21.
WangPZhangQJinY, et al. Studies and simulations on the flight trajectories of spinning table tennis ball via high-speed camera vision tracking system. Proc IMechE, Part P: J Sports Engineering and Technology2019; 233(2): 210–226.
22.
KohlerRHirschMMohlerB, et al. Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database. In: European conference on computer vision, 2012, pp.27–40. Springer.
23.
WenFYingRLiuP, et al. Blind image deblurring using patch-wise minimal pixels regularization. arXiv:190606642, 2019.
