With the development of deep learning technology and mobile Internet, more and more image-based artificial intelligence applications appear in people's lives. In the image information, the understanding of the characters in the picture has always been the focus of research and application, and it is also the basis of human-computer interaction. The human body key point detection technology can detect the joint point position of the target person in the image, so as to provide basic information for subsequent human-computer interaction applications and functions. The main purpose of this paper is to conduct research on gymnastics AR based on deep convolutional neural networks (CNN). This paper first expounds the mechanism contained in each component of the CNN. Analyzing the characteristics of CNN, compared with the multi-layer BP neural network, the transmission between the CNN neurons is combined with the local receptive field through weight sharing, which reduces the weight parameters while maintaining the network depth. The gradient disappearance problem can be avoided in the training process, and its network structure has good generalization ability. Through performance comparison experiments, it is found that whether using single-stream RGB data, optical flow data, or dual-stream fusion results, the recognition accuracy of deep neural networks is better than that of conventional networks. Illustrating the effectiveness of deep CNNs in gymnastics action recognition (AR).

Lu Xi. Gymnastic Movement Recognition Based on Depth Convolution Neural Network. International Journal of Neural Network (2022), Vol. 3, Issue 2: 9-18. https://doi.org/10.38007/NN.2022.030202.

[1] Malik Z, Shapiai M. Human action interpretation using CNN: a survey. Machine Vision and Applications, 2022, 33(3):1-23. https://doi.org/10.1007/s00138-022-01291-0

[2] Kahaki S, Nordin M J, Ahmad N S, et al. Deep CNN designed for age assessment based on orthopantomography data. Neural Computing and Applications, 2020, 32(13):9357-9368. https://doi.org/10.1007/s00521-019-04449-6

[3] El-Moneim S A, Nassar M A, Dessouky M I, et al. Cancellable template generation for speaker recognition based on spectrogram patch selection and deep CNNs. International Journal of Speech Technology, 2022, 25(3):689-696. https://doi.org/10.1007/s10772-020-09791-y

[4] Martin P E, Benois-Pineau J, R Péteri, et al. Fine grained sport AR with Twin spatio-temporal CNNs. Multimedia Tools and Applications, 2020, 79(27):20429-20447. https://doi.org/10.1007/s11042-020-08917-3

[5] Uppal H, Sepas-Moghaddam A, Greenspan M, et al. Depth as Attention for Face Representation Learning. IEEE Transactions on Information Forensics and Security, 2021, PP(99):1-1. https://doi.org/10.1109/TIFS.2021.3053458

[6] Vesala G T, Ghali V S, Subhani S, et al. Convolution Neural Networks Based Automatic Subsurface Anomaly Detection and Characterization in Quadratic Frequency Modulated Thermal Wave Imaging. SN Computer Science, 2022, 3(3):1-13. https://doi.org/10.1007/s42979-022-01055-7

[7] Memon F A, Khan U A, Shaikh A, et al. Predicting Actions in Videos and Action-Based Segmentation Using Deep Learning. IEEE Access, 2021, PP(99):1-1. https://doi.org/10.1109/ACCESS.2021.3101175

[8] Kumar N, Sukavanam N. A weakly supervised CNN model for spatial localization of human activities in unconstraint environment. Signal, Image and Video Processing, 2020, 14(5):1009-1016. https://doi.org/10.1007/s11760-019-01633-y

[9] Divya R, Peter J D. Smart healthcare system-a brain-like computing approach for analyzing the performance of detectron2 and PoseNet models for anomalous action detection in aged people with movement impairments. Complex & Intelligent Systems, 2022, 8(4):3021-3040. https://doi.org/10.1007/s40747-021-00319-8

[10] Bennett S M, Hindin J S, Mohatt J, et al. Proof of Concept Study of an Oral Orthotic in Reducing Tic Severity in Tourette Syndrome. Child Psychiatry & Human Development, 2021, 53(5):953-963. https://doi.org/10.1007/s10578-021-01178-7

[11] Chuah W, Tennakoon R, Hoseinnezhad R, et al. Deep Learning-Based Incorporation of Planar Constraints for Robust Stereo Depth Estimation in Autonomous Vehicle Applications. IEEE Transactions on Intelligent Transportation Systems, 2021, PP(99):1-12.

[12] Vigneshwaran B, Iruthayarajan M W, Maheswari R V. Recognition of shed damage on 11-kV polymer insulator using Bayesian optimized convolution neural network. Soft Computing, 2022, 26(14):6857-6869. https://doi.org/10.1007/s00500-021-06629-w

[13] Pabitha C, Vanathi B. Densemask RCNN: A Hybrid Model for Skin Burn Image Classification and Severity Grading. Neural Processing Letters, 2021, 53(9):1-19. https://doi.org/10.1007/s11063-020-10387-5

[14] Mohan H M, Rao P V, Kumara H, et al. Non-invasive technique for real-time myocardial infarction detection using faster R-CNN. Multimedia Tools and Applications, 2021, 80(17):26939-26967. https://doi.org/10.1007/s11042-021-10957-2

[15] Sahay A, Amudha J. Integration of Prophet Model and Convolution Neural Network on Wikipedia Trend Data. Journal of Computational and Theoretical Nanoscience, 2020, 17(1):260-266. https://doi.org/10.1166/jctn.2020.8660

[16] Gopi C S, Sivareddy C, Prasad K M, et al. A Proficient Scheme for Detecting Breast Cancer by Classification Techniques. Journal of Computational and Theoretical Nanoscience, 2020, 17(8):3453-3457. https://doi.org/10.1166/jctn.2020.9209

[17] Uppal H, Sepas-Moghaddam A, Greenspan M, et al. Depth as Attention for Face Representation Learning. IEEE Transactions on Information Forensics and Security, 2021, PP(99):1-1. https://doi.org/10.1109/TIFS.2021.3053458

[18] Vesala G T, Ghali V S, Subhani S, et al. Convolution Neural Networks Based Automatic Subsurface Anomaly Detection and Characterization in Quadratic Frequency Modulated Thermal Wave Imaging. SN Computer Science, 2022, 3(3):1-13. https://doi.org/10.1007/s42979-022-01055-7

[19] Jaraut P, Abdelhafiz A, Chenini H, et al. Augmented CNN for Behavioral Modeling and Digital Predistortion of Concurrent Multiband Power Amplifiers. IEEE Transactions on Microwave Theory and Techniques, 2021, PP(99):1-1.

[20] Singh B, Sur A , Mitra P. Steganalysis of Digital Images Using Deep Fractal Network. IEEE Transactions on Computational Social Systems, 2021, PP(99):1-8. https://doi.org/10.1109/TCSS.2021.3052520