Abstract
Due to the current video key frame extraction algorithm is affected by the lens conversion, the extraction accuracy is poor. For this reason, a precise extraction algorithm of video action key frames for online aerobics teaching is studied. According to the color components of the video color RGB space, in order to ensure that the color distance is suitable for human vision. A non-uniform quantized HSV space method is adopted, and a one-dimensional feature vector is introduced to convert the online teaching video of aerobics into a one-dimensional histogram of 72 bins, which realizes the segmentation of video shots and reduces the impact of shot conversion. Sort the gray values of the histogram pixels of the video after the segmentation is completed, and construct the dynamic frames of the aerobics online teaching video. Sequence search constructs the processing dynamic frame, extracts the feature vector of the video sequence, and uses the multi-layer core aggregation algorithm to extract the key frame of the video action according to the extracted feature vector. Experimental results show that the algorithm can effectively extract the key frames of aerobics video action, the fidelity of the extracted key frames is higher than 0.9, and the precision and recall are both higher than 99%.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aote SS, Potnurwar A (2019) An automatic video annotation framework based on two level keyframe extraction mechanism. Multimed Tools Appl 78(11):14465–14484
Ge H, Chu D (2020) Simulations of Synchronized Restoration of Video Key Frame Loss Based on Digital Media. Computer Simulation 37(05):115–119
Gao P, Li J, Liu S (2021) An Introduction to Key Technology in Artificial Intelligence and big Data Driven e-Learning and e-Education. Mobile Networks & Applications 26(5):2123–2126
Shao J, Cheng X (2021) Sea level height based on big data of internet of things and aerobics teaching in coastal areas. Arab J Geosci 14(15):1–15
Huang L (2021) Research on the application of the function of computer management system in college aerobics teaching. J Phys Conf Ser 1744(3):032148
Liu S, Guo C, Fadi A et al (2020) Reliability of Response Region: A Novel Mechanism in Visual Tracking by Edge Computing for IIoT Environments. Mech Syst Signal Process 138:106537
Kim DH, Anvarov F, Lee JM, Song BC (2021) Metric-based attention feature learning for video action recognition. IEEE Access 9:39218–39228
Kumar G, Reddy V (2020) Detection of shot boundaries and extraction of key frames for video retrieval. Int J Knowledge-Based Intel Eng Syst 24(1):11–17
Zhang Y, Zhu D, Bi H, Zhang G, Leung H (2019) Scattering key-frame extraction for comprehensive videosar summarization: a spatiotemporal background subtraction perspective. IEEE Trans Instrum Meas 69(7):4768–4784
Li L (2021) An Online Arrangement Method of Difficult Actions in Competitive Aerobics Based on Multimedia Technology. Secur Commun Netw. https://doi.org/10.1155/2021/9968401
Ma Y (2019) Research on the arrangement and visual design of aerobics under the new situation. Int Core J Eng 5(9):170–173
Ferraz CT, Barcellos W, Junior OP, Tamiris T, Manzato MG, Gonzaga A et al (2021) A comparison among keyframe extraction techniques for cnn classification based on video periocular images. Multimed Tools Appl 80(8):12843–12856
Gharbi H, Bahroun S, Zagrouba E (2019) Key frame extraction for video summarization using local description and repeatability graph clustering. SIViP 13(11):15–25
Ji Y, Li W, Feng K, Xing B, Pan F (2020) Automatic video mosaicking algorithm via dynamic key-frame. J Syst Eng Electron 31(2):272–278
Li Y, Li S, Chen C, Hao A, Qin H (2020) Accurate and robust video saliency detection via self-paced diffusion. IEEE Trans Multimedia 22(5):1153–1167
Fathy GM, Hassan HA, Sheta W, Omara FA, Nabil E (2021) A novel no-sensors 3d model reconstruction from monocular video frames for a dynamic environment. PeerJ Computer Science 7(7):e529–e534
Liu S, Liu D, Muhammad K et al (2021) Effective Template Update Mechanism in Visual Tracking with Background Clutter. Neurocomputing 458:615–625
Zhou M (2020) Feature extraction of human motion video based on virtual reality technology. IEEE Access PP(99) 1–9
Shuai L, Xinyu L, Shuai W et al (2021) Fuzzy-Aided Solution for Out-of-View Challenge in Visual Tracking under IoT Assisted Complex Environment. Neural Comput Appl 33(4):1055–1065
Mitra A, Mohanty SP, Corcoran P, Kougianos E (2021) A machine learning based approach for deepfake detection in social media through key video frame extraction. SN Computer Science 2(2):158–165
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics
The authors have no relevant financial or non-financial interests to disclose. Yan Gong provided the algorithm and experimental results, wrote the manuscript, Marcin Woźniak revised the paper, supervised and analyzed the experiment. We also declare that data availability and ethics approval is not applicable in this paper.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yan, G., Woźniak, M. Accurate Key Frame Extraction Algorithm of Video Action for Aerobics Online Teaching. Mobile Netw Appl 27, 1252–1261 (2022). https://doi.org/10.1007/s11036-022-01939-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11036-022-01939-1