Deep learning system aims to use hierarchical model to learn high-level functions from low-level functions. This study mainly discusses the handball action evaluation method and system based on deep learning. In the process of video data acquisition, the binocular RGB camera system is installed on a fixed iron frame 2.2m above the ground and 3M away from the end of the court in order to capture a wide range of field images including the whole plane of the court. In order to complete a variety of handball recognition in complex background environment, this paper builds a convolutional neural network to accept image input and output image categories, and selects Caffe as an open source, efficient and stable deep learning framework. In handball video processing, convolution neural network is used to detect the position of human body in each frame. Then, the pose of the human body in each bounding box is predicted, and the multi approximate pose of each frame is filtered, and a two-dimensional coordinate estimation of human joint is output. Finally, the 2D coordinates of human joints are used as input to fit the 3D coordinates of human joints. Then CNN is used to process the video data and optical flow data at the same time, and the motion evaluation entrance gives the results by calculating the angle at the joint point. In the experiment, the recognition rate is 88.89%. Among them, the recognition accuracy of other movements is 97% except for push and block. This study is helpful to provide positive guidance for handball training.

Ivay Jacksion. Handball Action Evaluation Method and System Based on Deep Learning. International Journal of Sports Technology (2022), Vol. 3, Issue 1: 63-80. https://doi.org/10.38007/IJST.2022.030106.

[1] Matthew, F, Dixon, et al. Deep learning for spatio‐temporal modeling: Dynamic traffic flows and high frequency trading. Applied Stochastic Models in Business & Industry, 2019, 35(3):788-807. https://doi.org/10.1002/asmb.2399

[2] Levine S , Pastor P , Krizhevsky A , et al. Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection. International Journal of Robotics Research, 2016, 37(4-5):421-436. https://doi.org/10.1177/0278364917710318

[3] He H , Wen C K , Jin S , et al. Deep Learning-based Channel Estimation for Beamspace mmWave Massive MIMO Systems. IEEE Wireless Communications Letters, 2018, 7(5):852-855.

[4] Long M , Wang J , Cao Y , et al. Deep Learning of Transferable Representation for Scalable Domain Adaptation. IEEE Transactions on Knowledge & Data Engineering, 2016, 28(8):2027-2040.

[5] Rojas-Barahona, Maria L . Deep learning for sentiment analysis. Language & Linguistics Compass, 2016, 10(12):205-212. https://doi.org/10.1111/lnc3.12228

[6] Chen L , Qu H , Zhao J , et al. Efficient and robust deep learning with Correntropy-induced loss function. Neural Computing and Applications, 2016, 27(4):1019-1031. https://doi.org/10.1007/s00521-015-1916-x

[7] Niko Sünderhauf, Brock O , Scheirer W , et al. The Limits and Potentials of Deep Learning for Robotics. The International journal of robotics research, 2018, 37(4-5):405-420. https://doi.org/10.1177/0278364918770733

[8] Maulana G M , Arruda S D M . Teacher assessment action in mathematics classes: a study with teachers from the 2nd cycle of Mozambican general high school education. Acta Scientiae, 2020, 22(5):102-121.

[9] Dokhanchi K . Aftermath of the Gulf War: An Assessment of UN Action, by Johnstone Ian. (International Peace Academy, Occasional Paper Series) 84 pages, notes. Boulder & London: Lynne Rienner Publishers, 1994. $7.95 (Paper) ISBN 1-55587-487-8 Crisis in the Arabian Gulf: An Independent Iraqi View, by Ali Omar. 168 pages, bibliography, index. Westport, Connecticut & London: Praeger Publishers, 1993. $49.95 (Cloth) ISBN 0-275-94158. Archives of Microbiology, 2016, 144(1):102-104.

[10] Magee S R , Eidson-Ton W S , Leeman L , et al. Family Medicine Maternity Care Call to Action: Moving Toward National Standards for Training and Competency Assessment. Family medicine, 2017, 49(3):210-217.

[11] Islam M T , Ayatollahi S A , Zihad S M N K , et al. Phytol anti-inflammatory activity: Pre-clinical assessment and possible mechanism of action elucidation. Cellular and Molecular Biology, 2020, 66(4):264-269. https://doi.org/10.14715/cmb/2020.66.4.31

[12] Kumar S , Sahu D , Mehto A , et al. Health Inequalities in Under-Five Mortality: An Assessment of Empowered Action Group (EAG) States of India. Journal of Health Economics and Outcomes Research, 2020, 7(2):189-196. https://doi.org/10.36469/jheor.2020.18224

[13] Muzhikov V , Vershinina E , Muzhikov R , et al. The Method Of Individual Assessment Of The Action Of Insulin And Its Adequate Dose In Diabetes Mellitus *Corresponding Author. World Journal of Pharmaceutical Research, 2019, 8(7):176-205.

[14] Jekabsone A , Kamenders A , Rosa M , et al. Assessment of the Implementation of Sustainable Energy Action Plans at Local Level. Case Study of Latvia. Environmental and Climate Technologies, 2019, 23(2):36-46. https://doi.org/10.2478/rtuect-2019-0053

[15] K, Alysse, Bailey, et al. Applying Action Research in a Mixed Methods Positive Body Image Program Assessment With Older Adults and People With Physical Disability and Chronic Illness:. Journal of Mixed Methods Research, 2019, 14(2):248-267.

[16] Maoxin W . Suboptimal Interobserver Agreement Among Cytopathologists in Assessment of Pancreatic Lesions: A Call for Action. Clinical Gastroenterology & Hepatology, 2018, 16(7):1040-1042. https://doi.org/10.1016/j.cgh.2017.12.043

[17] Maoxin W . Suboptimal Interobserver Agreement Among Cytopathologists in Assessment of Pancreatic Lesions: A Call for Action. Clinical Gastroenterology & Hepatology, 2018, 16(7):1040-1042. https://doi.org/10.1016/j.cgh.2017.12.043

[18] Tsang A , Wong K , Ryan D , et al. Using an Evidence-Informed Framework and a Self-Assessment Tool to Drive Priority Setting and Action toward Senior-Friendly Care. Healthcare quarterly (Toronto, Ont.), 2018, 21(1):25-30.

[19] Ismaidar, Sumarno, Dwintoro, et al. Legal assessment on criminal sanctions in criminal action of corruption based on justice values. International Journal of Civil Engineering and Technology, 2018, 9(11):680-692.

[20] Tofan N , Andrian S , Stoleriu S , et al. The Assessment of the Surface Status Following the Action of Some Acidic Beverages on Indirect Restorative Materials. Materiale Plastice, 2018, 55(1):129-135. https://doi.org/10.37358/MP.18.1.4978

[21] Thomas K H , Mcdaniel J T , Haring E L , et al. Mental health needs of military and veteran women: An assessment conducted by the Service Women's Action Network.. Traumatology, 2018, 24(2):104-112. https://doi.org/10.1037/trm0000132

[22] Mohammed A , Othman M F , Omar R . Ecowas, Good Governance and Collective Military Action in Liberia: A Post Conflict Assessment. International Journal of Humanities and Social Science, 2017, 22(7):82-90.

[23] Ayyoub A A . An Action Research Approach for Using Self/Peer Assessment to Enhance Learning and Teaching Outcomes. Journal of Teaching and Teacher Education, 2017, 5(1):33-42. https://doi.org/10.12785/jtte/050104

[24] Kourosh A , Hasan S , Parsi S , et al. P013 Anaphylaxis recognition and action: needs assessment-quality improvement empowers tertiary care allergy clinic team. Annals of Allergy Asthma & Immunology, 2016, 117(5):S26-S26. https://doi.org/10.1016/j.anai.2016.09.021

[25] Amit R , Pushpa P . Assessment of Mechanism of Action of Antidiabetic Activity o f Calocybe indica by Enzyme Inhibitory Activity. Biosciences Biotechnology Research Asia, 2016, 13(4):2117-2123. https://doi.org/10.13005/bbra/2372

[26] A J C M , B J F , C H E H , et al. An Ecological Assessment of the Northern Yellowstone Range: Synthesis and Call to Action. Rangelands, 2018, 40( 6):224-227. https://doi.org/10.1016/j.rala.2018.10.007