Abstract
The aim of this work is to investigate the use of shadow videos for daily sports activity detection and to contribute to the emerging field of shadow-based classification in machine learning. A novel deep feature engineering model is proposed, and a new shadow video dataset is collected to validate the proposed model. Furthermore, the use of shadow videos ensures privacy protection for individuals. To evaluate the proposed system, a dataset comprising five sports activities (i.e., squat, steady run, standing butterfly, overhead side bend, and knee lift) recorded from 33 participants is used. The proposed model works in the following way: (i) videos are divided into frames and aggregated into non-overlap** blocks of six frames to create images, (ii) deep features are extracted from three fully connected layers of the pre-trained AlexNet, resulting in 4096, 4096, and 1000 features from fc6, fc7, and fc8 layers, respectively. These three feature vectors are then merged to generate a final feature vector with a length of 9192 (= 4096 + 4096 + 1000). (iii) The Chi2 selector is employed to select the most distinctive 1000 features in the feature selection phase, and (iv) the support vector machine (SVM) with leave-one-subject-out (LOSO) validation is used to classify the five sports activities. The proposed deep features coupled with Chi2 based model achieved a classification accuracy of 88.49% using the SVM classifier with LOSO cross-validation (CV) on our collected dataset.
Similar content being viewed by others
Data availability
The authors are committed to making the data available if requested by the journal.
References
Dunn AL, Andersen RE, Jakicic JM (1998) Lifestyle physical activity interventions: History, short-and long-term effects, and recommendations. Am J Prev Med 15(4):398–412
Booth FW, Roberts CK, Laye MJ (2012) Lack of exercise is a major cause of chronic diseases. Compr Physiol 2(2):1143
Knight JA (2012) Physical inactivity: associated diseases and disorders. Ann Clin Lab Sci 42(3):320–337
Nieman DC (2020) Coronavirus disease-2019: A tocsin to our aging, unfit, corpulent, and immunodeficient society. J Sport Health Sci 9(4):293–301
Mofijur M, Fattah IR, Alam MA, Islam AS, Ong HC, Rahman SA, Najafi G, Ahmed SF, Uddin MA, Mahlia TMI (2021) Impact of COVID-19 on the social, economic, environmental and energy domains: Lessons learnt from a global pandemic. Sustain Prod Consum 26:343–359
Caspersen CJ, Powell KE, Christenson GM (1985) Physical activity, exercise, and physical fitness: definitions and distinctions for health-related research. Public Health Rep 100(2):126
Haskell WL, Montoye HJ, Orenstein D (1985) Physical activity and exercise to achieve health-related physical fitness components. Public Health Rep 100(2):202
Becker M, Diamond R, Sainfort F (1993) A new patient focused index for measuring quality of life in persons with severe and persistent mental illness. Qual Life Res 2(4):239–251
Avci A, Bosch S, Marin-Perianu M, Marin-Perianu R, Havinga P (2010) Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: A survey. In: 23th International conference on architecture of computing systems 2010. VDE, Hannover, Germany, pp 1–10
Nadeem A, Jalal A, Kim K (2021) Automatic human posture estimation for sport activity recognition with robust body parts detection and entropy markov model. Multimedia Tools Appl 80(14):21465–21498
Zdravevski E, Risteska Stojkoska B, Standl M, Schulz H (2017) Automatic machine-learning based identification of jogging periods from accelerometer measurements of adolescents under field conditions. PLoS ONE 12(9):e0184216
Taborri J, Palermo E, Rossi S (2019) Automatic detection of faults in race walking: A comparative analysis of machine-learning algorithms fed with inertial sensor data. Sensors 19(6):1461
Ji R (2020) Research on basketball shooting action based on image feature extraction and machine learning. IEEE Access 8:138743–138751
Yan C, Li X, Li G (2021) A new action recognition framework for video highlights summarization in sporting events. In: 2021 16th International Conference on Computer Science & Education (ICCSE). Lancaster, United Kingdom, pp 653–666. https://doi.org/10.1109/ICCSE51940.2021.9569708
Sharma P, Aittala M, Schechner YY, Torralba A, Wornell GW, Freeman WT, Durand F (2021) What you can learn by staring at a blank wall. In: Proceedings of the IEEE/CVF International conference on computer vision. Montreal, BC, Canada, pp 2330–2339
Tiwari A, Chaturvedi A (2021) A novel channel selection method for BCI classification using dynamic channel relevance. IEEE Access 9:126698–126716
Tiwari A, Chaturvedi A (2019) A multiclass EEG signal classification model using spatial feature extraction and XGBoost algorithm. In: 2019 IEEE/RSJ International conference on intelligent robots and systems (IROS). Macau, China, pp 4169–4175. https://doi.org/10.1109/IROS40897.2019.8967868
Tiwari A, Chaturvedi A (2022) Automatic channel selection using multiobjective X-shaped binary butterfly algorithm for motor imagery classification. Expert Syst Appl 206:117757
Tiwari A, Chaturvedi A (2023) Automatic EEG channel selection for multiclass brain-computer interface classification using multiobjective improved firefly algorithm. Multimedia Tools Appl 82(4):5405–5433
Tiwari A, Chaturvedi A (2022) A hybrid feature selection approach based on information theory and dynamic butterfly optimization algorithm for data classification. Expert Syst Appl 196:116621
Tiwari A, Mishra S (2022) Higher-order dynamic mode decomposition and multichannel singular spectrum decomposition hybridization for bci feature extraction. In: 2022 International Conference for Advancement in Technology (ICONAT). Goa, India, pp 1–6. https://doi.org/10.1109/ICONAT53423.2022.9726019
Verma P, Srivastava R (2022) Two-stage multi-view deep network for 3D human pose reconstruction using images and its 2D joint heatmaps through enhanced stack-hourglass approach. Vis Comput 38(7):2417–2430
Verma P, Srivastava R (2021) Reconsideration of multi-stage deep network for human pose estimation. Comput Methods Biomech Biomed Eng: Imaging Vis 9(6):600–612
Tuncer T, Ertam F, Dogan S, Subasi A (2020) An automated daily sports activities and gender recognition method based on novel multikernel local diamond pattern using sensor signals. IEEE Trans Instrum Meas 69(12):9441–9448
Altun K, Barshan B (2010) Human activity recognition using inertial/magnetic sensor units. International workshop on human behavior understanding. Springer, pp 38–51
Altun K, Barshan B, Tunçel O (2010) Comparative study on classifying human activities with miniature inertial and magnetic sensors. Pattern Recogn 43(10):3605–3620
Ermes M, Pärkkä J, Mäntyjärvi J, Korhonen I (2008) Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions. IEEE Trans Inf Technol Biomed 12(1):20–26
Joshi K, Tripathi V, Bose C, Bhardwaj C (2020) Robust sports image classification using InceptionV3 and neural networks. Procedia Comput Sci 167:2374–2381
Taylor K, Abdulla UA, Helmer RJ, Lee J, Blanchonette I (2011) Activity classification with smart phones for sports activities. Procedia Eng 13:428–433
Barshan B, Yüksek MC (2014) Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units. Comput J 57(11):1649–1667
Willetts M, Hollowell S, Aslett L, Holmes C, Doherty A (2018) Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96,220 UK Biobank participants. Sci Rep 8(1):1–10
Kuncan F, Kaya Y, Tekin R, Kuncan M (2022) A new approach for physical human activity recognition based on co-occurrence matrices. J Supercomput 78:1048–1070. https://doi.org/10.1007/s11227-021-03921-2
Yang W (2019) Analysis of sports image detection technology based on machine learning. EURASIP J Image and Video Proc 2019(1):1–8
Host K, Ivašić-Kos M (2022) An overview of Human Action Recognition in sports based on Computer Vision. Heliyon 8(6):e09633
Lin B-Y, Lin Y-D (2022) A clustering-based feature selection for automatic labeling in human activity recognition. In: 2022 IEEE 4th global conference on life sciences and technologies (LifeTech). Osaka, Japan, pp 308–309. https://doi.org/10.1109/LifeTech53646.2022.9754929
Huszár VD, Adhikarla VK (2021) Live spoofing detection for automatic human activity recognition applications. Sensors 21(21):7339
Zeng B, Sanz-Prieto I, Luhach AK (2023) Deep learning approach to Automated data collection and processing of video surveillance in sports activity prediction. Ann Oper Res 326(1):57. https://doi.org/10.1007/s10479-021-04348-x
Rani S, Babbar H, Coleman S, Singh A, Aljahdali HM (2021) An efficient and lightweight deep learning model for human activity recognition using smartphones. Sensors 21(11):3845
Webber J, Mehbodniya A, Arafa A, Alwakeel A (2022) Improved Human Activity Recognition Using Majority Combining of Reduced-Complexity Sensor Branch Classifiers. Electronics 11(3):392
Akter T, Zeba Z, Hosen I, Al-Mamun F, Mamun MA (2022) Impact of the COVID-19 pandemic on BMI: Its changes in relation to socio-demographic and physical activity patterns based on a short period. PLoS ONE 17(3):e0266024
Zhu S, Guo Z (2012) Ma L (2012) Shadow removal with background difference method based on shadow position and edges attributes. EURASIP J Image Video Proc 1:1–15
Zhang L, Zhu Y, Liao B, **ao C (2017) Video shadow removal using spatio-temporal illumination transfer. Comput Graph Forum 36(7):125–134
Sestino A, De Mauro A (2021) Leveraging artificial intelligence in business: implications, applications and methods. Tech Anal Strat Manag 34(1):16–29. https://doi.org/10.1080/09537325.2021.1883583
Alhayani B, Mohammed HJ, Chaloob IZ, Ahmed JS (2021) Effectiveness of artificial intelligence techniques against cyber security risks apply of IT industry. Materials Today: Proceedings. https://doi.org/10.1016/j.matpr.2021.02.531
Shaheen MY (2021) Applications of artificial intelligence (AI) in healthcare: A review. ScienceOpen Preprints. https://doi.org/10.14293/S2199-1006.1.SOR-.PPVRY8K.v1
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105
Liu H (2015) Setiono R Chi2: Feature selection and discretization of numeric attributes. J Cyber Secur Mobil 4(1):65–88
Abomhara M, Køien GM (2015) Cyber security and the internet of things: vulnerabilities, threats, intruders and attacks. J Cyber Secur Mobil 4(1):65–88
Vapnik V (1998) The support vector method of function estimation. In: Nonlinear Modeling. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-5703-6_3
Vapnik V (1999) The nature of statistical learning theory. Springer science & business media. Springer, New York, NY. https://doi.org/10.1007/978-1-4757-3264-1
Funding
This study was supported by Firat University Scientific Research Projects with project number TEKF.22.06.
Author information
Authors and Affiliations
Contributions
All authors contributed equally to the study.
Corresponding author
Ethics declarations
Ethical approval
Ethics approval was not required for this research.
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Barua, P.D., Tuncer, T., Dogan, S. et al. Novel automated detection of sports activities using shadow videos. Multimed Tools Appl 83, 44933–44954 (2024). https://doi.org/10.1007/s11042-023-17407-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-17407-1