GWO-ATDL-SBD: A GREY WOLF OPTIMIZED ADAPTIVE TEMPORAL DEEP LEARNING FRAMEWORK FOR ROBUST SHOT BOUNDARY DETECTION
DOI:
https://doi.org/10.29121/shodhkosh.v7.i1.2026.8167Keywords:
Shot Boundary Detection, Grey Wolf Optimizer, Bi-Lstm, Video Analysis, Temporal Deep LearningAbstract [English]
Shot Boundary Detection (SBD) is an essential task in video content analysis but accurately detecting both abrupt and gradual scene changes is still a problem due to different lightings, camera motions, and varied scene contents. This paper introduces a hybrid framework named GWO-ATDL-SBD that combines Grey Wolf Optimizer (GWO) with adaptive temporal deep learning for performing robust shot boundary detection. At first, multi-cue features such as edge energy difference, motion vector entropy, and color histogram distance are extracted to represent different visual characteristics in combination. These features are combined dynamically using weights obtained by GWO and passed to a Bi-directional Long Short-Term Memory (Bi-LSTM) network to capture the frame-wise temporal dependencies. In contrast to the traditional methods having fixed thresholds, our method uses GWO not only to find the optimal feature fusion weights and classifier parameters but also decision thresholds for adaptive and accurate recognition of both cuts and transitions. Extensive experiments on standard video datasets show that the proposed method substantially surpasses the existing SBD methods in terms of precision, recall, and F1-score. The findings reveal the potential of marrying evolutionary optimization with temporal deep learning for tackling complex video transition detection problems.
References
Anthwal, S., Ganotra, D.: An overview of optical flow-based approaches for motion segmentation. The Imaging Science Journal 67(5), 284–294 (2019) DOI: https://doi.org/10.1080/13682199.2019.1641316
Benoughidene, A., Titouna, F.: A novel method for video shot boundary detection using cnn-lstm approach. International Journal of Multimedia Information Retrieval 11(4), 653–667 (2022) DOI: https://doi.org/10.1007/s13735-022-00251-8
Chakraborty, D., Chiracharit, W., Chamnongthai, K.: Video shot boundary detection using principal component analysis (pca) and deep learning. In: 2021, 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), pp. 272–275 (2021). IEEE. DOI: https://doi.org/10.1109/ECTI-CON51831.2021.9454775
Chakraborty, S., Singh, A., Thounaojam, D.M.: A novel bifold-stage shot bound- ary detection algorithm: invariant to motion and illumination. The Visual Computer 38(2), 445–456 (2022) DOI: https://doi.org/10.1007/s00371-020-02027-9
Chakraborty, S., Thounaojam, D.M.: A novel shot boundary detection system using hybrid optimization technique. Applied Intelligence 49(9), 3207–3220(2019) DOI: https://doi.org/10.1007/s10489-019-01444-1
Chan, C., Wong, A.: Shot boundary detection using genetic algorithm optimization. In: 2011 IEEE International Symposium on Multimedia, pp. 327–332 (2011). IEEE DOI: https://doi.org/10.1109/ISM.2011.58
Dubey, A. K., & Dubey, A. (2026). Digitalization in Teaching and Learning: Impact on Student Engagement and Academic Achievement. ShodhAI: Journal of Artificial Intelligence, 3(1), 37–42. https://doi.org/10.29121/shodhai.v3.i1.2026.73 DOI: https://doi.org/10.29121/shodhai.v3.i1.2026.73
Gawande, U., Hajari, K., Golhar, Y., Fulzele, P.: A novel gray wolf optimization based key frame extraction method for video classification using convlstm. Neural Computing and Applications 36(32), 20355–20385 (2024) DOI: https://doi.org/10.1007/s00521-024-10266-3
GG, L.P., Domnic, S.: Walsh–hadamard transform kernel-based feature vector for shot boundary detection. IEEE Transactions on Image Processing 23(12), 5187–5197 (2014) DOI: https://doi.org/10.1109/TIP.2014.2362652
Goswami, B., Boers, N., Rheinwalt, A., Marwan, N., Heitzig, J., Breitenbach, S.F., Kurths, J.: Abrupt transitions in time series with uncertainties. Nature communications 9(1), 48 (2018). DOI: https://doi.org/10.1038/s41467-017-02456-6
Guo, H., Liu, J., Xiao, Z., Xiao, L.: Deep cnn-based hyperspectral image classification using discriminative multiple spatial-spectral feature fusion. Remote Sensing Letters 11(9), 827–836 (2020) DOI: https://doi.org/10.1080/2150704X.2020.1779374
Hassanien, A., Elgharib, M., Selim, A., Bae, S.-H., Hefeeda, M., Matusik, W.: Large-scale, fast and accurate shot boundary detection through spatio-temporal convolutional neural networks. arXiv preprint arXiv:1705.03281 (2017)
Idan, Z.N., Abdulhussain, S.H., Mahmmod, B.M., Al-Utaibi, K.A., Al-Hadad, S.A.R., Sait, S.M.: Fast shot boundary detection based on separable moments and support vector machine. IEEe Access 9, 106412–106427 (2021) DOI: https://doi.org/10.1109/ACCESS.2021.3100139
Kar, T., Kanungo, P., Mohanty, S.N., Groppe, S., Groppe, J.: Video shot-boundary detection: issues, challenges and solutions. Artificial Intelligence Review 57(4), 104 (2024) DOI: https://doi.org/10.1007/s10462-024-10742-1
Kar, T., Kanungo, P.: A motion and illumination resilient framework for automatic shot boundary detection. Signal, Image and Video Processing 11,1237–1244 (2017) DOI: https://doi.org/10.1007/s11760-017-1080-0
Li, H., Wei, M.: Fuzzy clustering based on feature weights for multivariate time series. Knowledge-Based Systems 197, 105907 (2020) DOI: https://doi.org/10.1016/j.knosys.2020.105907
Li, Y., Li, C., Li, X., Wang, K., Rahaman, M.M., Sun, C., Chen, H., Wu, X., Zhang, H., Wang, Q.: A comprehensive review of markov random field and conditional random field approaches in pathology image analysis. Archives of Computational Methods in Engineering 29(1), 609–639 (2022) DOI: https://doi.org/10.1007/s11831-021-09591-w
Li, Y.-N., Lu, Z.-M., Niu, X.-M.: Fast video shot boundary detection framework employing pre-processing techniques. IET image processing 3(3), 121–134 (2009) DOI: https://doi.org/10.1049/iet-ipr.2007.0193
Liu, S., Liu, G., Zhou, H.: A robust parallel object tracking method for illumination variations. Mobile Networks and Applications 24(1), 5–17 (2019) DOI: https://doi.org/10.1007/s11036-018-1134-8
Mei, S., Ji, J., Hou, J., Li, X., Du, Q.: Learning sensor-specific spatial-spectral features of hyperspectral images via convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing 55(8), 4520–4533 (2017) DOI: https://doi.org/10.1109/TGRS.2017.2693346
Mirjalili, S., Mirjalili, S.M., Lewis, A.: Grey wolf optimizer. Advances in engineering software 69, 46–61 (2014) DOI: https://doi.org/10.1016/j.advengsoft.2013.12.007
Mondal, J., Kundu, M.K., Das, S., Chowdhury, M.: Video shot boundary detec- tion using multiscale geometric analysis of nsct and least squares support vector machine. Multimedia Tools and Applications 77(7), 8139–8161 (2018) DOI: https://doi.org/10.1007/s11042-017-4707-9
Navin, K., Krishnan, M., et al.: Fuzzy rule based classifier model for evidence based clinical decision support systems. Intelligent systems with applications 22,200393 (2024) DOI: https://doi.org/10.1016/j.iswa.2024.200393
Park, S., Sch¨ops, T., Pollefeys, M.: Illumination change robustness in direct visual slam. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 4523–4530 (2017). IEEE DOI: https://doi.org/10.1109/ICRA.2017.7989525
Peralta, B., Tirapegui, V., Pieringer, C., Caro, L.: A simple proposal for sentiment analysis on movies reviews with hidden markov models. In: Iberoamerican Congress on Pattern Recognition, pp. 152–162 (2019). Springer DOI: https://doi.org/10.1007/978-3-030-33904-3_14
Prasanna, C.S., Rahman, M.Z.U., Bayleyegn, M.D.: Brain epileptic seizure detection using joint cnn and exhaustive feature selection with rnn-blstm classifier. IEEE Access 11, 97990–98004 (2023) DOI: https://doi.org/10.1109/ACCESS.2023.3312187
Ray, P.P.: A review on tinyml: State-of-the-art and prospects. Journal of King Saud University-Computer and Information Sciences 34(4), 1595–1623 (2022) DOI: https://doi.org/10.1016/j.jksuci.2021.11.019
Sharma, D.M., Shandilya, S.K.: An efficient cyber-physical system using hybridized enhanced support-vector machine with ada-boost classification algorithm. Concurrency and Computation: Practice and Experience 34(21), 7134(2022) DOI: https://doi.org/10.1002/cpe.7134
Shinde, T., Shrivastava, M.: Development of an ant colony optimisation-based edge detection framework. African Journal of Applied Research 11(5), 573–595 (2025) DOI: https://doi.org/10.26437/m29ams60
Singh, A., Thounaojam, D.M., Chakraborty, S.: A novel automatic shot boundary detection algorithm: robust to illumination and motion effect. Signal, Image and Video Processing 14(4), 645–653 (2020) DOI: https://doi.org/10.1007/s11760-019-01593-3
Thounaojam, D., Khelchandra, T., Jayshree, T., Roy, S., Singh, K.: Colour histogram and modified multi-layer perceptron neural network based video shot boundary detection. International Arab Journal of Information Technology 16(4),686–693 (2019)
Warhade, K.K., Merchant, S., Desai, U.B.: Shot boundary detection in the presence of fire flicker and explosion using stationary wavelet transform. Signal, Image and Video Processing 5, 507–515 (2011) DOI: https://doi.org/10.1007/s11760-010-0163-y
Wu, L., Zhang, S., Jian, M., Lu, Z., Wang, D.: Two stage shot boundary detection via feature fusion and spatial-temporal convolutional neural networks. IEEE Access 7, 77268–77276 (2019) DOI: https://doi.org/10.1109/ACCESS.2019.2922038
Youssef, B., Fedwa, E., Driss, A., Ahmed, S.: Shot boundary detection via adaptive low rank and svd-updating. Computer Vision and Image Understanding161,20–28 (2017) DOI: https://doi.org/10.1016/j.cviu.2017.06.003
Zhao, L., Sun, X.M., Zhang, M.W.: A shot boundary detection method based on pso-svm. Applied Mechanics and Materials 130, 3821–3825 (2012) DOI: https://doi.org/10.4028/www.scientific.net/AMM.130-134.3821
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Tushar Banik, Saptarshi Chakraborty, Dalton Meitei Thounaojam, Sapam Jitu Singh, Raju Rajkumar
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
