Framework for real-time bounding box detection of Indian dance movements for multiple persons on a 5G multi-access edge computing server
Main Article Content
Abstract
This paper presents a machine learning workflow, run on a 5G multi-access edge computing (MEC) server, for detecting and classifying the Kuchipudi dance movements of multiple dancers. Dance movements in three Kuchipudi videos were annotated with the Computer Vision Annotation Tool (CVAT), and a YOLO11s model was trained to locate them with bounding boxes. For classification, the annotated regions were cropped, downscaled to reduce computation, lowpass filtered using the two-dimensional discrete Fourier transform, and enhanced with contrast limited adaptive histogram equalisation (CLAHE). Because the classes were highly imbalanced, StyleGAN2-ADA was used to generate synthetic images, giving 1500 images in each of seven classes. Two- and three-layer convolutional neural networks (CNNs) were compared with ResNet18 and ResNet50. ResNet50 performed best, with a validation accuracy of 89% and a macro F1-score of 84%. On the CPU-only MEC server, inference took 44.68 ms per frame on average, and the end-to-end throughput was 2 frames per second.
Downloads
Article Details
Issue
Section

This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
Adalarasu, K., Chetty, R.M.K., Begum, K.G., Harini, S. and Janardhanan, M., 2025. An Explainable Machine Learning (XAI) framework for classification of intricate dancing posture among Indian Bharatanatyam dancers. Applied Soft Computing, 171, 112817. Available from: https://doi.org/10.1016/j.asoc.2025.112817. DOI: https://doi.org/10.1016/j.asoc.2025.112817
Arpitha, D., Balasubrahmanyam, M. and Kumar, D.A., 2022. Depth based Indian Classical Dance Mudra’s Recognition using Support Vector Machine. 2022 4th International Conference on Smart Systems and Inventive Technology (ICSSIT). pp.885–888. Available from: https://doi.org/10.1109/ICSSIT53264.2022.9716486. DOI: https://doi.org/10.1109/ICSSIT53264.2022.9716486
Bhuyan, H., Killi, J., Dash, J.K., Das, P.P. and Paul, S., 2022. Motion Recognition in Bharatanatyam Dance. IEEE Access, 10, pp.67128–67139. Available from: https://doi.org/10.1109/ACCESS.2022.3184735. DOI: https://doi.org/10.1109/ACCESS.2022.3184735
Buda, M., Maki, A. and Mazurowski, M.A., 2018. A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks, 106, pp.249–259. Available from: https://doi.org/10.1016/j.neunet.2018.07.011. DOI: https://doi.org/10.1016/j.neunet.2018.07.011
Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M. and Kalinin, A.A., 2020. Albumentations: Fast and Flexible Image Augmentations. Information, 11(2), 125. Available from: https://doi.org/10.3390/info11020125. DOI: https://doi.org/10.3390/info11020125
Cao, Z., Hidalgo, G., Simon, T., Wei, S.E. and Sheikh, Y., 2021. OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(1), pp.172–186. Available from: https://doi.org/10.1109/TPAMI.2019.2929257. DOI: https://doi.org/10.1109/TPAMI.2019.2929257
Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G. and Sun, J., 2018. Cascaded Pyramid Network for Multi-person Pose Estimation. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA, USA: IEEE Computer Society, pp.7103–7112. Available from: https://doi.org/10.1109/CVPR.2018.00742. DOI: https://doi.org/10.1109/CVPR.2018.00742
Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S. and Zhang, L., 2020. HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp.5385–5394. Available from: https://doi.org/10.1109/CVPR42600.2020.00543. DOI: https://doi.org/10.1109/CVPR42600.2020.00543
Classicaldance, 2023. dance Computer Vision Model. Available from: https://universe.roboflow.com/classicaldance/dance-xfru0.
Convertini, V.N., Impedovo, D., Lopez, U., Pirlo, G. and Sterlicchio, G., 2024. Discrete Fourier Transform in Unmasking Deepfake Images: A Comparative Study of StyleGAN Creations. Information, 15(11), 711. Available from: https://doi.org/10.3390/info15110711. DOI: https://doi.org/10.3390/info15110711
Erukude, S.T., Marella, V.C. and Veluru, S.R., 2025. Fourier-Based GAN Fingerprint Detection Using ResNet50. 2025 9th International Conference on Inventive Systems and Control (ICISC). IEEE, pp.971–976. Available from: https://doi.org/10.1109/icisc65841.2025.11187724. DOI: https://doi.org/10.1109/ICISC65841.2025.11187724
Fang, H.S., Xie, S., Tai, Y.W. and Lu, C., 2017. RMPE: Regional Multi-person Pose Estimation. 2017 IEEE International Conference on Computer Vision (ICCV). pp.2353–2362. Available from: https://doi.org/10.1109/ICCV.2017.256. DOI: https://doi.org/10.1109/ICCV.2017.256
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y., 2020. Generative adversarial networks. Communications of the ACM, 63(11), pp.139–144. Available from: https://doi.org/10.1145/3422622. DOI: https://doi.org/10.1145/3422622
Guo, W. and Ouyang, Y., 2020. Robust Learning with Frequency Domain Regularization. arXiv:2007.03244. Available from: https://doi.org/10.48550/arXiv.2007.03244.
Gupta, S. and Singh, S., 2024. Indian dance classification using machine learning techniques: A survey. Entertainment Computing, 50, 100639. Available from: https://doi.org/10.1016/j.entcom.2024.100639. DOI: https://doi.org/10.1016/j.entcom.2024.100639
He, H. and Garcia, E.A., 2009. Learning from Imbalanced Data. IEEE Transactions on Knowledge and Data Engineering, 21(9), pp.1263–1284. Available from: https://doi.org/10.1109/TKDE.2008.239. DOI: https://doi.org/10.1109/TKDE.2008.239
He, K., Zhang, X., Ren, S. and Sun, J., 2016. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp.770–778. Available from: https://doi.org/10.1109/CVPR.2016.90. DOI: https://doi.org/10.1109/CVPR.2016.90
Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M. and Schiele, B., 2016. DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model. In: B. Leibe, J. Matas, N. Sebe and M. Welling, eds. Computer Vision – ECCV 2016, Lecture notes in computer science, vol. 9910. Cham: Springer International Publishing, pp.34–50. Available from: https://doi.org/10.1007/978-3-319-46466-4_3. DOI: https://doi.org/10.1007/978-3-319-46466-4_3
Jiang, W. and Lan, H., 2024. Stereo vision and deep learning-based movement correction for sports dance. International Journal of Information and Communication Technology, 25(9), pp.60–75. Available from: https://doi.org/10.1504/ijict.2024.143329. DOI: https://doi.org/10.1504/IJICT.2024.143329
Jocher, G. and Qiu, J., 2024. Ultralytics YOLO11. Version 11.0.0, AGPL-3.0. Available from: https://github.com/ultralytics/ultralytics.
Kao, H., 2024. Multi-person dance tiered posture recognition with cross progressive multiresolution representation integration. PLOS ONE, 19(6), e0300837. Available from: https://doi.org/10.1371/journal.pone.0300837. DOI: https://doi.org/10.1371/journal.pone.0300837
Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J. and Aila, T., 2020. Training Generative Adversarial Networks with Limited Data. In: H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan and H. Lin, eds. Advances in Neural Information Processing Systems, vol. 33. Curran Associates, Inc., pp.12104–12114. Available from: https://proceedings.neurips.cc/paper_files/paper/2020/hash/8d30aa96e72440759f74bd2306c1fa3d-Abstract.html.
Karras, T., Laine, S. and Aila, T., 2019. A Style-Based Generator Architecture for Generative Adversarial Networks. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp.4396–4405. Available from: https://doi.org/10.1109/CVPR.2019.00453. DOI: https://doi.org/10.1109/CVPR.2019.00453
Kishore Kumar, A.V., Emmadisetty, R., Chandralekha, M. and Saleem, K., 2024. Mediapipe-Powered SVM Model for Real-Time Kuchipudi Mudras Recognition. 2024 2nd International Conference on Advancement in Computation & Computer Technologies (InCACCT). pp.583–588. Available from: https://doi.org/10.1109/InCACCT61598.2024.10551243. DOI: https://doi.org/10.1109/InCACCT61598.2024.10551243
Kreiss, S., Bertoni, L. and Alahi, A., 2019. PifPaf: Composite Fields for Human Pose Estimation. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp.11969–11978. Available from: https://doi.org/10.1109/CVPR.2019.01225. DOI: https://doi.org/10.1109/CVPR.2019.01225
Maini, R. and Aggarwal, H., 2010. A Comprehensive Review of Image Enhancement Techniques. arXiv:1003.4053. Available from: https://doi.org/10.48550/arXiv.1003.4053.
Mallick, T., Das, P.P. and Majumdar, A.K., 2022. Posture and sequence recognition for Bharatanatyam dance performances using machine learning approaches. Journal of Visual Communication and Image Representation, 87, 103548. Available from: https://doi.org/10.1016/j.jvcir.2022.103548. DOI: https://doi.org/10.1016/j.jvcir.2022.103548
Meghana, 2024. Dance Detection Computer Vision Model. Available from: https://universe.roboflow.com/meghana-5flso/dance-detection.
Newell, A., Yang, K. and Deng, J., 2016. Stacked Hourglass Networks for Human Pose Estimation. In: B. Leibe, J. Matas, N. Sebe and M. Welling, eds. Computer Vision – ECCV 2016, Lecture notes in computer science, vol. 9912. Cham: Springer International Publishing, pp.483–499. Available from: https://doi.org/10.1007/978-3-319-46484-8_29. DOI: https://doi.org/10.1007/978-3-319-46484-8_29
Pareek, P. and Thakkar, A., 2021. A survey on video-based Human Action Recognition: recent updates, datasets, challenges, and applications. Artificial Intelligence Review, 54(3), pp.2259–2322. Available from: https://doi.org/10.1007/s10462-020-09904-8. DOI: https://doi.org/10.1007/s10462-020-09904-8
Parthasarathy, N. and Palanichamy, Y., 2023. Novel Video Benchmark Dataset Generation and Real-Time Recognition of Symbolic Hand Gestures in Indian Dance Applying Deep Learning Techniques. Journal on Computing and Cultural Heritage, 16(3), pp.1–19. Available from: https://doi.org/10.1145/3586207. DOI: https://doi.org/10.1145/3586207
Qu, J., 2024. A dance movement quality evaluation model using transformer encoder and convolutional neural network. Scientific Reports, 14, 32058. Available from: https://doi.org/10.1038/s41598-024-83608-9. DOI: https://doi.org/10.1038/s41598-024-83608-9
Raj, R.J., Dharan, S. and Sunil, T.T., 2023. Optimal feature selection and classification of Indian classical dance hand gesture dataset. The Visual Computer, 39(9), pp.4049–4064. Available from: https://doi.org/10.1007/s00371-022-02572-5. DOI: https://doi.org/10.1007/s00371-022-02572-5
Reza, A.M., 2004. Realization of the Contrast Limited Adaptive Histogram Equalization (CLAHE) for Real-Time Image Enhancement. Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology, 38(1), pp.35–44. Available from: https://doi.org/10.1023/B:VLSI.0000028532.53893.82. DOI: https://doi.org/10.1023/B:VLSI.0000028532.53893.82
Sekachev, B., Manovich, N., Zhiltsov, M., Zhavoronkov, A., Kalinin, D. et al., 2020. opencv/cvat: v1.1.0. Zenodo. Available from: https://doi.org/10.5281/zenodo.4009388.
Sun, K., Xiao, B., Liu, D. and Wang, J., 2019. Deep High-Resolution Representation Learning for Human Pose Estimation. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp.5686–5696. Available from: https://doi.org/10.1109/CVPR.2019.00584. DOI: https://doi.org/10.1109/CVPR.2019.00584
Wang, F., Quiles, O.L. and Li, J., 2024. Music-driven generative dance movement teaching game based on a multi-feature fusion strategy. Entertainment Computing, 50, 100646. Available from: https://doi.org/10.1016/j.entcom.2024.100646. DOI: https://doi.org/10.1016/j.entcom.2024.100646
Wang, Z., Yang, Y., Shrivastava, A., Rawal, V. and Ding, Z., 2020. Towards Frequency-Based Explanation for Robust CNN. arXiv:2005.03141. Available from: https://doi.org/10.48550/arXiv.2005.03141.
Zheng, W., 2024. Intelligent e-learning design for art courses based on adaptive learning algorithms and artificial intelligence. Entertainment Computing, 50, 100713. Available from: https://doi.org/10.1016/j.entcom.2024.100713. DOI: https://doi.org/10.1016/j.entcom.2024.100713