Ice and snow sports behavior recognition based on multi-scale features and improved CBAM
Abstract
Accurately identifying and correcting erroneous sports behaviors of athletes or beginners in ice and snow sports can improve the training quality. However, ice and snow sports scenes often have complex motion backgrounds, and the behavioral features during motion are difficult to extract, which affects the recognition accuracy. In order to solve the feature extraction in ice and snow sports behavior recognition, a behavior recognition model based on multi-scale features and improved convolutional block attention module is proposed. The model first utilizes multi-scale features to obtain multi-level features from the collected ice and snow motion images, ensuring that features of different scales in the images can be effectively captured. Then, one-dimensional convolution and spatial random pooling layers are introduced to improve the convolutional attention module, thereby constructing a behavior recognition model. The accuracy of the proposed model in the Ski-Pose dataset was 98.3%, which was 8.2% and 13.7% higher than other recognition models, indicating an obvious gap. The accuracy and F1 value were 89.5% and 91.2%, respectively, and the recognition rate for small targets reached 80%, which verified the effectiveness of the model. The research provides new technological support for intelligent monitoring and analysis systems for ice and snow sports.
References
1. Zhou F, Li J, Dai Y, Liu L, Qin H, Jiang Y, et al. Time-Series Fusion-Based Multicamera Self-Calibration for Free-View Video Generation in Low-Texture Sports Scene. IEEE Sens J. 2023;23(3):2956-2969.
2. Wang G, Pang Z, Wang F, Chen Y, Dai H, Wang B. Urban Fiber Based Laser Interferometry for Traffic Monitoring and Analysis. J Lightwave Technol. 2023;41(1):347-354.
3. Li Y, Wu L. A Wireless Self-Powered Sensor Network Based on Dual-Model Convolutional Neural Network Algorithm for Tennis Sports. IEEE SENS J, 2023;23(18):20745-20755.
4. Wang J, Li W, Gao Y, Zhang M, Tao R, Du Q. Hyperspectral and SAR Image Classification via Multiscale Interactive Fusion Network. IEEE T Neur Net Lear. 2023;34(12):10823-10837.
5. Axi N, Yu Z, Chaoning Z, Jinqiu S, Pei W, Inso K, et al, MS2Net: Multi-Scale and Multi-Stage Feature Fusion for Blurred Image Super-Resolution. IEEE T Circ Syst Vid, 2022;32(8):5137-5150.
6. He J, Ren Z, Zhang W, Jia Y, Guo S, Cui G. Fall Detection Based on Parallel 2DCNN-CBAM With Radar Multidomain Representations. IEEE Sens J, 2023;23(6):6085-6098.
7. Feng Y, Yang X, Qiu D, Zhang H, Wei D, Liu J. PCXRNet: Pneumonia Diagnosis From Chest X-Ray Images Using Condense Attention Block and Multiconvolution Attention Block. IEEE J Biomed Health. 2022;26(4):1484-1495.
8. Deng W, Wang X, Huang Z, Xu Q. Modulation Classifier: A Few-Shot Learning Semi-Supervised Method Based on Multimodal Information and Domain Adversarial Network. IEEE Commun Lett. 2023;27(27):576-580.
9. Jiang Y, Xie S, Xie X, Cui Y, Tang H. Emotion Recognition via Multiscale Feature Fusion Network and Attention Mechanism. IEEE Sens J. 2023;23(10):10790-10800.
10. Chang M, Yao D, Yang J. Intelligent Fault Diagnosis of Rolling Bearings Using Efficient and Lightweight ResNet Networks Based on an Attention Mechanism. IEEE Sens J. 2023;23(9):9136-9145.
11. Pan Z, Chen H, Zhong W, Wang A, Zheng C. A CNN-Based Animal Behavior Recognition Algorithm for Wearable Devices. IEEE Sens J. 2023;23(5):5156-5164.
12. Pang SM, Cao JX, Jian MY, Lai J, Yan ZY. BR-GAN: A Pedestrian Trajectory Prediction Model Combined With Behavior Recognition. IEEE T Intell Transp. 2022;23(12):24609-24620.
13. Huang T, Fu R, Chen Y, Sun Q. Real-Time Driver Behavior Detection Based on Deep Deformable Inverted Residual Network With an Attention Mechanism for Human-Vehicle Co-Driving System. IEEE T Veh Technol. 2022;71(12):12475-12488.
14. Sun H, Tao F, Fu Z, Gao A, Jiao L. Driving-Behavior-Aware Optimal Energy Management Strategy for Multi-Source Fuel Cell Hybrid Electric Vehicles Based on Adaptive Soft Deep-Reinforcement Learning. IEEE T Intell Transp. 2023;24(4):4127-4146.
15. Zheqi Y, Ahmad T, William T, Adnan Z, Khalid R, Hadi H, et al. A Radar-Based Human Activity Recognition Using a Novel 3-D Point Cloud Classifier. IEEE Sens J. 2022;22(19):18218-18227.
16. Meng C, Hui FS, Hsin YL, Yifan L, Ho-Yin C, Yufan W, et al. Phase-Based Quantification of Sports Performance Metrics Using a Smart IoT Sensor. IEEE Internet Things. 2023;10(18):15900-15911.
17. Ergeneci M, Carter D, Kosmas P. sEMG Onset Detection via Bidirectional Recurrent Neural Networks With Applications to Sports Science. IEEE Sens J. 2022;22(19):18751-18761.
18. Tang Y, Zhang L, Min F, He J. Multiscale Deep Feature Learning for Human Activity Recognition Using Wearable Sensors. IEEE T Ind Electron. 2023;70(2):2106-2116.
19. Ye Y, Pan C, Wu Y, Wang S, Xia Y. MFI-Net: Multiscale Feature Interaction Network for Retinal Vessel Segmentation. IEEE J Biomed Health. 2022;26(9):4551-4562.
20. Preethi P, Mamatha HR. Region-Based Convolutional Neural Network for Segmenting Text in Epigraphical Images. Artif. Intell. Appl. 2023;1(2):119-127.
21. Wang G, Peng C, Gu Y, Zhang J, Wang H. Interactive Multi-Scale Fusion of 2D and 3D Features for Multi-Object Vehicle Tracking. IEEE T Intell Transp. 2023;24(10):10618-10627.
22. Bhosle K, Musande V. Evaluation of Deep Learning CNN Model for Recognition of Devanagari Digit. Artif. Intell. Appl. 2023;1(2):114-118.
23. Kunchang L, Yali W, Junhao Z, Peng G, Guanglu S, Yu L. UniFormer: Unifying Convolution and Self-Attention for Visual Recognition. IEEE T Pattern Anal. 2023;45(10):12581-12600.
24. Min S, Jialin S, Qingming Y, Jian W, Zunkai H, Aiwen L. LMFFNet: A Well-Balanced Lightweight Network for Fast and Accurate Semantic Segmentation. IEEE T Neur Net Lear. 2023;34(6): 3205-3219.
25. Lu Z, Bian Y, Yang T, Ge Q, Wang Y. A New Siamese Heterogeneous Convolutional Neural Networks Based on Attention Mechanism and Feature Pyramid. IEEE T Cybernetics. 2024;54(1):13-24.
26. Li G, Fan W, Xie H, Qu X. Detection of Road Objects Based on Camera Sensors for Autonomous Driving in Various Traffic Situations. IEEE Sens J. 2022;22(24):24253-24263.
27. Xu S, Zhang L, Tang Y, Han C, Wu H, Song A. Channel Attention for Sensor-Based Activity Recognition: Embedding Features into all Frequencies in DCT Domain. IEEE T Knowl Data En. 2023;35(12):12497-12512.
28. Li X, Lv C, Wang W, Li G, Yang L, Yang J. Generalized Focal Loss: Towards Efficient Representation Learning for Dense Object Detection. IEEE T Pattern Anal. 2023;45(3):3139-3153.
29. Jian S, Yanan Z, Huajian L, Zeguang Z, Kexin Z, Kun Q. Depression Recognition From EEG Signals Using an Adaptive Channel Fusion Method via Improved Focal Loss. IEEE J BIOMED HEALTH, vol. 27, no. 7, pp. 3234-3245, July 2023, DOI: 10.1109/JBHI.2023.3265805.
30. Tang Y, Xie Y, Zhang W. Affine Subspace Robust Low-Rank Self-Representation: From Matrix to Tensor. IEEE T Pattern Anal. 2023;45(8):9357-9373.
31. Pareek G, Nigam S, Singh R. Modeling transformer architecture with attention layer for human activity recognition. Neural Computing and Applications, 2024, 36(10): 5515-5528.
32. Tang J, Gong S, Wang Y, Liu B, Du C, Gu B. Beyond coordinate attention: spatial-temporal recalibration and channel scaling for skeleton-based action recognition. Signal, Image and Video Processing, 2024, 18(1): 199-206.
33. Ha M H. Top-heavy capsnets based on spatiotemporal non-local for action recognition. Journal of Computing Theories and Applications, 2024, 2(1): 39-50.
Copyright (c) 2024 Chunping Liu
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on all articles published in this journal is retained by the author(s), while the author(s) grant the publisher as the original publisher to publish the article.
Articles published in this journal are licensed under a Creative Commons Attribution 4.0 International, which means they can be shared, adapted and distributed provided that the original published version is cited.
Submit a Paper
