An Efficient Approach for Shot Boundary Detection in Presence of Illumination Effects using Fusion of Transforms

An Efficient Approach for Shot Boundary Detection in Presence of Illumination Effects using Fusion of Transforms
  IJETT-book-cover           
  
© 2022 by IJETT Journal
Volume-70 Issue-4
Year of Publication : 2022
Authors : Shrikant Chavate, Ravi Mishra
DOI :  10.14445/22315381/IJETT-V70I4P236

How to Cite?

Shrikant Chavate, Ravi Mishra, "An Efficient Approach for Shot Boundary Detection in Presence of Illumination Effects using Fusion of Transforms," International Journal of Engineering Trends and Technology, vol. 70, no. 4, pp. 418-432, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I4P236

Abstract
For video processing applications like indexing, browsing and video retrieval, the video shot boundary detection (SBD) plays a vital role. Video is a popular mode of information sharing and thus, vast database of video is available in cyberspace. The identification of accurate shot boundary is an essential task in video retrieval and indexing. This identification still remains a challenge especially for gradual transitions in video. The proposed approach detects the abrupt and gradual transitions such as fade-in and fade-out with high accuracy. In this paper, the combination of DTCWT-WHT is proposed to extract the features. The preprocessing is applied at an early stage to remove the noise present in the frames. The proposed method implements Deep Belief Network (DBN) for accurate classification of gradual transitions. This method also detects the shots accurately even in presence of illuminations. The experiments are performed on TRECVID datasets of year 2016, 2017, 2018 and 2019. The results of proposed algorithm outperform other SBD techniques with the help of performance metrics such as, precision, recall and F1 score. In addition, under lighting effects, the adoption of early filtering techniques minimizes the number of false alarms.

Keywords
Deep Belief Network, SSDOA, Fast Averaging Peer Group, Gradual transition.

Reference
[1] Sasithradevi A, Mohamed Mansoor Roomi S, A New Pyramidal Opponent Color-Shape Model Based Video Shot Boundary Detection, J Vis Commun Image Represent. 67 (2020) 102754. https://doi.org/10.1016/j.jvcir.2020.10275
[2] Khan MM, Chamnongthai K, Member S, Multi-modal Visual Features Based Video Shot Boundary Detection. 3536 (2017) 1–13. https://doi.org/10.1109/ACCESS.2017.2717998
[3] Hannane R, Elboushaki A, Afdel K, Naghabhushan P, Javed M, An Efficient Method for Video Shot Boundary Detection and Keyframe Extraction Using SIFT-Point Distribution Histogram, Int J Multimed Inf Retr. 5 (2016) 89–104. https://doi.org/10.1007/s13735-016-0095-6
[4] Klerk MG De, Parameter Analysis of the Jensen-Shannon Diver- Gence for Shot Boundary Detection in Streaming Media Applications. 109 (2018) 171– 181
[5] Mishra R, Video Shot Boundary Detection Using Hybrid Dual Tree Complex Wavelet Transform with Walsh Hadamard Transform. (2021).
[6] Hato E, Abdulmunem ME, Fast Algorithm for Video Shot Boundary Detection Using SURF features. SCCS 2019 - 2019 2nd Sci Conf Comput Sci. (2019) 81–86. https://doi.org/10.1109/SCCS.2019.8852603
[7] Lakshmi PGG, Domnic S, Walsh-Hadamard Transform Kernel-Based Feature Vector for Shot Boundary Detection, IEEE Trans Image Process. 23 (2014) 5187–5197. https://doi.org/10.1109/TIP.2014.2362652
[8] 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 (2019) 77268–77276. https://doi.org/10.1109/ACCESS.2019.2922038
[9] Mishra R, Raman C V, Singhai SK, Sharma M, Real Time and Non Real Time Video Shot Boundary Detection Using Dual Tree Complex Wavelet Transform. 2015 Int Conf Ind Instrum Control ICIC. (2015) 1495–1500. https://doi.org/10.1109/IIC.2015.7150986
[10] Gygli M, Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks, arXiv. (2017) 1–4
[11] Chakraborty S, Thounaojam DM, A Novel Shot Boundary Detection System Using Hybrid Optimization Technique, Appl Intell. 49 (2019) 3207–3220. https://doi.org/10.1007/s10489-019-01444-1
[12] Chakraborty S, Thounaojam DM, SBD-Duo: A Dual Stage Shot Boundary Detection Technique Robust to Motion and Illumination Effect, Multimed Tools Appl. 80 (2021) 3071–3087. https://doi.org/10.1007/s11042-020-09683-y
[13] Rashmi BS, Nagendraswamy HS, Video Shot Boundary Detection Using Block Based Cumulative Approach, Multimed Tools Appl. 80 (2021) 641–664. https://doi.org/10.1007/s11042-020-09697-6
[14] Liang R, Zhu Q, Wei H, Liao S, A Video Shot Boundary Detection Approach Based on CNN Feature. Proc - 2017 IEEE Int Symp Multimedia, ISM. (2017) 489–494. https://doi.org/10.1109/ISM.2017.97
[15] Idan ZN, Abdulhussain SH, Mahmmod BM, Al-Utaibi KA, Al-Hadad SAR, Sait SM, Fast Shot Boundary Detection Based on Separable Moments and Support Vector Machine, IEEE Access. 9 (2021) 106412–106427. https://doi.org/10.1109/ACCESS.2021.3100139
[16] Nandini HM, Chethan HK, Rashmi BS, Shot Based Keyframe Extraction Using Edge-LBP Approach, J King Saud Univ - Comput Inf Sci. (2020). https://doi.org/10.1016/j.jksuci.2020.10.031
[17] Zhou S, Wu X, Qi Y, Luo S, Xie X, Video Shot Boundary Detection Based on Multi-Level Features Collaboration, Signal, Image Video Process. 15 (2021) 627–635. https://doi.org/10.1007/s11760-020-01785-2
[18] Shen RK, Lin YN, Juang TTY, Shen VRL, Lim SY, Automatic Detection of Video Shot Boundary in Social Media Using a Hybrid Approach of HLFPN and Keypoint Matching, IEEE Trans Comput Soc Syst. 5 (2018) 210–219. https://doi.org/10.1109/TCSS.2017.2780882
[19] Sulaiman AK, Mahmood SA, Shot Boundaries Detection Based Video Summary Using Dynamic Time Warping and Mean Shift, Proc Int Conf Comput Sci Softw Eng CSASE. (2020) 278–283 . https://doi.org/10.1109/CSASE48920.2020.9142116
[20] Singh A, Meitei D, Saptarshi T, A Novel Automatic Shot Boundary Detection Algorithm?: Robust to Illumination and Motion Effect. Signal, Image Video Process. (2019). https://doi.org/10.1007/s11760-019-01593-3
[21] Malinski L, Smolka B, Fast Averaging Peer Group Filter for the Impulsive Noise Removal in Color Images, J Real-Time Image Process. (2015). https://doi.org/10.1007/s11554-015-0500-z
[22] Prabavathy AK, Shree JD, Histogram Difference with Fuzzy Rule Base Modeling for Gradual Shot Boundary Detection in Video Cloud Applications, Cluster Comput. (2017). https://doi.org/10.1007/s10586-017-1201-0
[23] Liu F, Wan Y, Improving the Video Shot Boundary Detection Using the HSV Color Space and Image Subsampling. 30 (2015) 351–354
[24] Bi C, Yuan Y, Zhang J, Shi Y, Xiang Y, Wang Y, Zhang R, Dynamic Mode Decomposition Based Video Shot Detection, IEEE Access 6. (2018) 21397– 21407. https://doi.org/10.1109/ACCESS.2018.2825106
[25] Selesnick IW, Baraniuk RG, Kingsbury NG, The Dual-Tree Complex Wavelet Transform ©. 123–151
[26] Prathiba T, Kumari RSS, Eagle Eye CBVR Based on Unique Key Frame Extraction and Deep Belief Neural Network. Wirel Pers Commun. 116 (2021) 411–441. https://doi.org/10.1007/s11277-020-07721-4
[27] Tharwat A, Gabel T, Parameters Optimization of Support Vector Machines for Imbalanced Data Using Social Ski Driver Algorithm, Neural Comput Appl. 32 (2020) 6925–6938. https://doi.org/10.1007/s00521-019-04159-z
[28] Birinci M, Kiranyaz S (2014) A perceptual scheme for fully automatic video shot boundary detection. Signal Process Image Commun 29:410–423 . https://doi.org/10.1016/j.image.2013.12.003
[29] Fan J, Zhou S, Siddique MA, Fuzzy Color Distribution Chart -Based Shot Boundary Detection, Multimed Tools Appl. 76 (2017) 10169–10190. https://doi.org/10.1007/s11042-016-3604-y
[30] Bendraou Y, Essannouni F, Aboutajdine D, Salam A, Shot boundary Detection via Adaptive Low Rank and SVD-Updating, Comput Vis Image Underst. 161 (2017) 20–28. https://doi.org/10.1016/j.cviu.2017.06.003
[31] S. Chavate, R. Mishra and P. Yadav, A Comparative Analysis of Video Shot Boundary Detection using Different Approaches, 10th International Conference on System Modeling & Advancement in Research Trends (SMART). (2021) 1-7. Doi: 10.1109/SMART52563.2021.9676246.