结合SIFT算法的视频场景突变检测

李枫; 赵岩; 王世刚; 陈贺新

doi:doi:10.3788/co.20160901.0074

中国光学, 2016, 9 (1): 74, 网络出版: 2016-03-22

结合SIFT算法的视频场景突变检测

Video scene mutation change detection combined with SIFT algorithm

论文大纲

李枫赵岩王世刚陈贺新

作者单位

吉林大学通信工程学院, 吉林长春 130012

特征点匹配场景变化检测 SIFT SIFT feature point matching scene change detection

摘要

视频场景变化检测对于视频的标注以及语义检索具有非常重要的作用。本文提出了一种结合SIFT(Scale Invariant Feature Transformation)特征点提取的场景变化检测算法。首先利用SIFT 算法分别提取出视频前后帧的特征点并分别统计其数量, 然后对视频前后帧进行图像匹配, 统计匹配上的特征点数量, 最后将该帧的匹配特征点数量与该帧前一帧的特征点数量做比值, 从而通过该比值判断场景变化情况。实验结果表明, 视频场景突变检测率平均可以达到9579％。本算法可以在视频帧进行图像匹配的过程中对场景的变化情况进行判断, 因此该算法不仅应用范围较广, 还可以保证场景变化检测的精度, 仿真结果证明了算法的有效性。

Abstract

Video scene change detection has a very important role for video annotation and semantic search. This paper proposes a scene mutation change detection algorithm combined with SIFT(Scale Invariant Feature Transformation) feature point extraction. Firstly, the feature points of two adjacent video frames are extracted respectively using SIFT algorithm and the number of them is counted respectively. Then image matching of the two adjacent frames of the video is performed and the number of matching feature points is counted. Finally, the ratio between the number of matching feature points of the current frame and the number of matching feature points of its previous frame is calculated, so as to judge the scene change by this ratio. The average scene mutation change detection rate in the experimental results can reach 9579%. The proposed algorithm can judge scene change during image matching. Therefore, the algorithm can not only be applied widely, but also guarantee the accuracy of scene change detection. Experimental results show the effectiveness of the proposed algorithm.

参考文献

[1] 邹晓燕.基于H.264压缩域的视频检索研究[D].山东: 山东大学,2011.

ZOU X Y. Video retrieval based H.264 compressed domain[D]. Shandong: Shandong University,2011.(in Chinese)

[2] 薛立勤,张秀娟.基于运动分析的视频检索方法[J].计算机工程与应用,2008,44(25): 152-154.

XUE L Q,ZHANG X J. Video retrieval method based on motion analysis[J]. Computer Engineering and Applications,2008,44(25): 152-154.(in Chinese)

[3] 朱耀麟, 李倩.视频检索常用的镜头分割方法的研究[J].电视技术, 2014, 38(3): 178-181.

ZHU Y L,LI Q .Survey of used methods for partitioning video into shots in video indexing[J]. Ideo Engineering, 2014, 38(3): 178-181.(in Chinese)

[4] 魏玮, 刘静,王丹丹.视频镜头分割方法综述[J].计算机系统应用,2013,22(1): 5-8.

WEI W,LIU J,WANG D D. Survey of methods for partitioning video into shots in video[J]. Computer System & Applications,2013,22(1): 5-8.(in Chinese)

[5] 刘艳红.视频镜头分割算法综述[J].科技创新与应用,2014(16): 49-50.

LIU Y H. Survey of methods for partitioning video into shots in video[J]. Scientific and Technological Innovation and Application,2014(16): 49-50.(in Chinese)

[6] VLACHOS T. Cut detection in video sequences using phase correlation[J]. IEEE Signal Processing Letters,2000,7(7): 173-175.

[7] EOM Y,PARK S,YOO S,et al.. An analysis of Scene Change Detection[M]. Anaheim,California,USA: International Conference on Semantic Computing,2015: 470-474.

[8] HONG S,CHO B,CHOE Y. Adaptive Thresholding for Scene Change Detection[M]. Berlin: International Conference on Consumer Electronics,2013: 75-78.

[9] LEE M H,YOO H W,JANG D S. Video scene change detection using neural network: improved ART2[J]. Expert Systems with Applications,2006,31(1): 13-25.

[10] 唐剑琪,谢林江,袁庆生,等.基于ORB的镜头边界检测算法[J].通信学报,2013,34(11): 184-190.

TANG J Q,XIE L J,YUAN Q SH,et al.. ORB-based shot boundary detection algorithm[J]. Communications,2013,34(11): 184-190.(in Chinese)

[11] 吴伟交.基于SIFT特征点的图像匹配算法[D].武汉: 华中科技大学,2013.

WU W J. Image matching algorithm based on SIFT feature points[D]. Wuhan: Huazhong University of Science and Technology,2013.(in Chinese)

[12] 许佳佳.结合Harris与SIFT算子的图像快速配准算法[J].中国光学,2015,8(4): 574-581.

XU J J. Fast image registration method based on Harris and SIFT algorithm[J]. Chinese Optics,2015,8(4): 574-581.(in Chinese)

[13] 高文,朱明,贺柏根,等.目标跟踪技术综述[J].中国光学,2014,7(3): 365-375.

GAO W,ZHU M,HE B G,et al.. Overview of target tracking technology[J]. Chinese Optics,2014,7(3): 365-375.(in Chinese)

[14] 聂海涛,龙科慧,马军,等.采用改进尺度不变特征变换在多变背景下实现快速目标识别[J].光学精密工程,2015,23(8): 2349-2356.

NIE H T,LONG K H,MA J,et al.. Fast object recognition under multiple varying background using improved SIFT method[J]. Opt. Precision Eng.,2015,23(8): 2349-2356.(in Chinese)

[15] 王睿,朱正丹.融合全局-颜色信息的尺度不变特征变换[J].光学精密工程,2015,23(1): 295-301.

WANG R,ZHU ZH D. SIFT matching with color invariant characteristics and global context[J]. Opt. Precision Eng.,2015,23(1): 295-301.(in Chinese)

[16] 刘志文,刘定生,刘鹏.应用尺度不变特征变换的多源遥感影像特征点匹配[J].光学精密工程,2013,21(8): 2146-2153.

LIU ZH W,LIU D SH,LIU P. SIFT feature matching algorithm of multi-source remote image[J]. Opt. Precision Eng.,2013,21(8): 2146-2153.(in Chinese)

[17] 马彦卓,常义林,杨海涛.应用于视频编码的实时多测度联合突变场景切换检测算法[J].光子学报,2010,39(6): 1058-1063.

MA Y ZH, CHANG Y L, YANG H T. Used in video coding mutations in real-time multi measure joint scene change detection algorithm[J]. Acta Photonica Sinica,2010,39(6): 1058-1063.(in Chinese)

[18] 易璨.基于信息熵和运动信息的视频镜头检测[D].湘潭: 湘潭大学,2006.

YI C. Shot detection based on information entropy and motion information[D]. Xiangtan: Xiangtan University,2006.(in Chinese)

李枫, 赵岩, 王世刚, 陈贺新. 结合SIFT算法的视频场景突变检测[J]. 中国光学, 2016, 9(1): 74. LI Feng, ZHAO Yan, WANG Shi-gang, CHEN He-xin. Video scene mutation change detection combined with SIFT algorithm[J]. Chinese Optics, 2016, 9(1): 74.

结合SIFT算法的视频场景突变检测

关于本站 Cookie 的使用提示

全站搜索

结合SIFT算法的视频场景突变检测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索