A Video Shot Segmentation Method Based on a Two-Stage Support Vector Machine Classifier

Abstract

Abstract:

A video shot segmentation method based on a two-stage support vector machine (SVM) classifier was proposed. In the first stage，the feature vectors were generated by using the segmented video histogram distance, combining the sliding window with the trap method. Then, the subsegments containing shot boundaries were filtered out by using the SVM classifier. In the second stage，the feature vectors were obtained by histogram distance between different spacing of the frames and time window. The shot detection was implemented by binary tree SVM classification strategy. Experimental results show that the detection results can be improved on both abrupt and gradual shot boundary significantly by the proposed method.

Key words: shot segmentation, two-stage classifier, support vector machine (SVM), fragment screening

CLC Number:

TP 391

YU Lu1,2,QIAO Ruiping2,HU Yuping2,ZHAO Jing1,2. A Video Shot Segmentation Method Based on a Two-Stage Support Vector Machine Classifier[J]. Journal of Shanghai Jiaotong University, 2014, 48(05): 668-673.

References

［1］Yuan J, Wang H, Xiao L, et al. A formal study of shot boundary detection ［J］. IEEE Transactions on Circuits and Systems for Video Technology, 2007, 17(2): 168186.

［2］巢娟, 孙锬锋, 蒋兴浩. 基于双重检测模型的视频镜头分割算法［J］. 上海交通大学学报, 2011, 45(10): 15421546.

CHAO Juan, SUN Yanfeng, JIANG Xinghao. A video shot segmentation algorithm based on dual detection model ［J］. Journal of Shanghai Jiaotong University, 2011, 45 (10): 15421546.

［3］Zhu L, Qu J F, Rahman M A, et al. An integrated method for video shot boundary detection［C］//Proceedings of the IEEE Southeast Conference. NJ, USA: IEEE, 2010:151154.

［4］Angadi S A, Naik V. A shot boundary detection technique based on local color moments in YCbCr color space ［C］//International Conference of Advanced Computer Science and Information Technology. NJ, USA: IEEE, 2012: 5765.

［5］Grana C, Cucchiara R. Linear transition detection as a unified shot detection approach ［J］. IEEE Transactions on Circuits and Systems for Video Technology, 2007, 17(4): 483489.

［6］Mohanta P P, Saha S K, Chanda B. A modelbased shot boundary detection technique using frame transition parameters ［J］. IEEE Transactions on Multimedia, 2012, 14(1): 223233.

［7］Zhang C, Wang W Q. A robust and efficient shot boundary detection approach based on fisher criterion ［C］//The 20th ACM International Conference on Multimedia. New York, USA: ACM, 2012:701704.

［8］Vasileios C, Aristidis L, Nikolaos G. Simultaneous detection of abrupt cuts and dissolves in videos using support vector machines ［J］. Pattern Recognition Letters, 2009, 30(1): 5565.

［9］薛玲, 熊璋, 欧阳元新, 等. 一种二级级联分类的镜头边界检测算法［J］. 计算机辅助设计与图形学学报, 2008, 20(5): 665670.

XUE Ling, XIONG Zhang, OUYANG Yuanxin, et al. Shot boundary detection using a cascade classifier ［J］. Journal of ComputerAided Design and Computer Graphics, 2008, 20(5): 665670.

［10］Hsu C W, Lin C J. A comparison of methods for multiclass support vector machines ［J］. IEEE Trans Neural Netw, 2002, 13(2): 415425.

［11］Gao G Y, Ma H D. Accelerating shot boundary detection by reducing spatial and temporal redundant information［C］//IEEE International Conference on Multimedia and Expo. NJ, USA: IEEE, 2011: 16.

［12］Howley T, Madden M G. An evolutionary approach to automatic kernel construction［C］//International Conference on Artificial Neural Networks. Berlin, Germany: SpringerVerlag, 2006: 417426.

[1]	ZHU Dong, JIANG Pingping, YAN Guozheng, WANG Zhiwu, HAN Ding, ZHAO Kai, HUA Fangfang, YAO Shengjian, DING Zifan, ZHOU Zerun. Defecation Perception Reconstruction of an Artificial Anal Sphincter System [J]. Journal of Shanghai Jiaotong University, 2020, 54(8): 771-777.
[2]	WU Jin, MIN Yu, YANG Xiaodie, MA Simin . Micro-Expression Recognition Algorithm Based on Information Entropy Feature [J]. Journal of Shanghai Jiao Tong University(Science), 2020, 25(5): 589-599.
[3]	WANG Jiangzhuo,XU Wencong,LI Jianxun,HE Fengshou,CAO Lanying,MIAO Lifeng. Dot-Track Association Algorithm for Radar Electronic Support Measurement Systems Based on Support Vector Machine [J]. Journal of Shanghai Jiaotong University, 2019, 53(9): 1091-1099.
[4]	MA Zhihong，GONG Liang，LIN Ke，MAO Yuhan，WU Wei，LIU Chengliang. Estimation of Panicle Seed Number Based on Panicle Geometric Pattern Recognition [J]. Journal of Shanghai Jiaotong University, 2019, 53(2): 239-246.
[5]	U Feng,FAN Chunju,XU Xunjian,LI Li,NI Jiayun. Displacement Prediction of Landslide Based on Variational Mode Decomposition and AMPSO-SVM Coupling Model [J]. Journal of Shanghai Jiaotong University, 2018, 52(10): 1388-1395.
[6]	GONG Pengwei1,FEI Yanqiong1, 3, SONG Libo2. Road Recognition Method of WheelTracked Robot Based on#br# Multisensor Information Fusion [J]. Journal of Shanghai Jiaotong University, 2017, 51(4): 398-.
[7]	JIAO Xuejun,ZHANG Zhen,JIANG Jin,WANG Chunhui,YANG Hanjun,XU Fenggang,CAO Yong,FU Jiahao. The Brain-Computer Interface Using Functional Near-Infrared Spectroscopy [J]. Journal of Shanghai Jiaotong University, 2017, 51(12): 1456-1463.
[8]	WANG Xiuqing1,HOU Zengguang2,ZENG Hui3,L Feng1,PAN Shiying1. Fault Diagnosis of Robots Based on Multi-Sensor Information Fusion [J]. Journal of Shanghai Jiaotong University, 2015, 49(06): 793-798.
[9]	KUMAR Manoj1, SAMUI Pijush2*. Analysis of Epimetamorphic Rock Slopes Using Soft Computing [J]. Journal of shanghai Jiaotong University (Science), 2014, 19(3): 274-278.
[10]	WANG Jiajing1,2,ZHANG Zhusheng1,HE Weiping1. Identification of Tools with Failure Barcode Based on Multi-Information Fusion [J]. Journal of Shanghai Jiaotong University, 2014, 48(12): 1675-1680.
[11]	ZHANG Yu-jina (张玉金), LI Sheng-honga* (李生红), WANG Shi-linb (王士林). Detecting Shifted Double JPEG Compression Tampering Utilizing Both Intra-Block and Inter-Block Correlations [J]. Journal of shanghai Jiaotong University (Science), 2013, 18(1): 7-16.
[12]	CHAO Juan-1, SUN Tan-Feng-1, 2 , JIANG Xing-Hao-1, 2 . A Video Shot Segmentation Algorithm Based on Dual-detection Model [J]. Journal of Shanghai Jiaotong University, 2011, 45(10): 1542-1546.
[13]	CHEN Gu-Chun-a, SU Bo-b, WANG Shi-Lin-b, LI Sheng-Hong-a. Blind Detection of Splicing Image Based on Gray Level Co-occurrence Matrix of Image DCT Domain [J]. Journal of Shanghai Jiaotong University, 2011, 45(10): 1547-1551.
[14]	HAN Hua-1, GU Bo-1, REN Neng-2. Fault Diagnosis for Refrigeration Systems Based on Principal Component Analysis and Support Vector Machine [J]. Journal of Shanghai Jiaotong University, 2011, 45(09): 1355-1361.