Athletes have a large amount of video information, so how to capture effective information is the key to improving athletes’ training efficiency and improving the quality of the game. From the perspective of deep learning, this study analyzes and improves traditional algorithm models based actual needs, and jointly learns multi-scale features. At the same time, in view of the problem of over-fitting in the model training process, this study uses the sparse pyramid pool strategy to adjust the pool parameterization process and reduce the complexity of feature description. In addition, the research designs experiment to analyze the performance of the improved algorithm model and select the appropriate database to analyze the recognition effect of the algorithm model. The research shows that the algorithm of this research has a certain improvement in the recognition effect of athletes, and the recognition effect matching the artificial design features can be obtained, and it can provide theoretical reference for subsequent related research.
JiS., XuW., YangM., et al., 3D Convolutional Neural Networks for Human Action Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence35(1) (2013), 221–231.
2.
ChenC., JafariR., KehtarnavazN., Improving Human Action Recognition Using Fusion of Depth Camera and Inertial Sensors, IEEE Transactions on Human-Machine Systems45(1) (2015), 51–61.
3.
DevanneM., WannousH., BerrettiS., et al., 3-D Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold, IEEE Transactions on Cybernetics45(7) (2015), 1340–1352.
4.
GuoG., LaiA., A survey on still image based human action recognition, Pattern Recognition47(10) (2014), 3343–3361.
5.
ChaaraouiA.A., Padilla-López, JoséRamón, Climent-Pérez, Pau, et al., Evolutionary joint selection to improve human action recognition with RGB-D devices, Expert Systems with Applications41(3) (2014), 786–794.
6.
ChenC., LiuK., KehtarnavazN., Real-time human action recognition based on depth motion maps, Journal of Real-Time Image Processing12(1) (2013), 155–163.
7.
BarnachonM., BouakazS., BoufamaB., et al., Ongoing human action recognition with motion capture, Pattern Recognition47(1) (2014), 238–247.
8.
EvertsI., Van GemertJ.C., and GeversT., Evaluation of Color Spatio-Temporal Interest Points for Human Action Recognition, IEEE Transactions on Image Processing23(4) (2014), 1569–1580.
9.
TheodorakopoulosI., KastaniotisD., EconomouG., et al., Pose-based human action recognition via sparse representation in dissimilarity space, Journal of Visual Communication and Image Representation25(1) (2014), 12–23.
10.
Ben AounN, MejdoubM. and Ben AmarC., Graph-based approach for human action recognition using spatio-temporal features, Journal of Visual Communication and Image Representation25(2) (2014), 329–338.
11.
ParisiG.I., CorneliusW., and StefanW. Self-organizing neural integration of pose-motion features for human action recognition, Frontiers in Neurorobotics9 (2015).
12.
LiuA.A., SuY.T., JiaP.P., et al., Multiple/Single-View Human Action Recognition via Part-Induced Multitask Structural Learning, IEEE Transactions on Cybernetics45(6) (2015), 1194–1208.
13.
Waqas SultaniI.S., Human Action Recognition across Datasets by Foreground-weighted, Histogram Decomposition Physics Letters B690(2) (2014), 764–771.
14.
LiuA.A., NieW.Z., SuY.T., et al., Coupled hidden conditional random fields for RGB-D human action recognition, Signal Processing112 (2015), 74–82.
15.
ChenC., JafariR., KehtarnavazN., A Real-Time Human Action Recognition System Using Depth and Inertial Sensor Fusion, IEEE Sensors Journal16(3) (2016), 773–781.
16.
RamanathanM., YauW.Y., TeohE.K., Human Action Recognition With Video Data: Research and Evaluation Challenges, IEEE Transactions on Human-Machine Systems44(5) (2014), 650–663.
17.
NasiriJ.A., CharkariN.M., MozafariK., Energy-based model of least squares twin Support Vector Machines for human action recognition, Signal Processing104(6) (2014), 248–257.
18.
ChenC., JafariR., KehtarnavazN., A survey of depth and inertial sensor fusion for human action recognition, Multimedia Tools and Applications (2015), 1–21.
19.
VrigkasM., KaravasilisV., NikouC., et al., Matching mixtures of curves for human action recognition, Computer Vision and Image Understanding119 (2014), 27–40.
20.
MoghaddamZ., PiccardiM., Training Initialization of Hidden Markov Models in Human Action Recognition, IEEE Transactions on Automation Science & Engineering11(2) (2014), 394–408.
21.
ManuelJ. Marín-Jiménez, NicolásPérez de la Blanca and Ángeles MendozaM.. Human action recognition from simple feature pooling, Pattern Analysis & Applications17(1) (2014), 17–36.
22.
GuangmingZ., LiangZ., PeiyiS., et al., An Online Continuous Human Action Recognition Algorithm, Based on the Kinect Sensor Sensors16(2) (2016), 161.
23.
ChaaraouiA.A., Florez-RevueltaF., Adaptive Human Action Recognition With an Evolving Bag of Key Poses, IEEE Transactions on Autonomous Mental Development6(2) (2014), 139–152.
24.
BenmokhtarR. Robust human action recognition scheme based on high-level feature fusion, Multimedia Tools and Applications69(2) (2014), 253–275.
25.
JiangY.G., DaiQ., LiuW., et al., Human Action Recognition in Unconstrained Videos by Explicit Motion Modeling, IEEE Transactions on Image Processing24(11) (2015), 1–1.
