RANDOM FOREST FOR INTERMEDIATE DESCRIPTOR FUSION IN SHOT BOUNDARY DETECTION

作     者：Zhang Lei Chang Anqi Xiang Xuezhi 

作者机构：College of Information and Communication Engineering Harbin Engineering University 

出 版 物：《Journal of Electronics(China)》 (电子科学学刊（英文版）)

年 卷 期：2014年第31卷第5期

页      面：465-472页

学科分类：0711[理学-系统科学] 0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 07[理学] 08[工学] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 

基　　金：Supported by the Young Teacher Support Plan by Heilongjiang Province and Harbin Engineering University in China(No.1155G17) partially by the Fundamental Research Funds for the Central Universities Grant to X.Xiang 

主　　题：Shot boundary detection Intermediate descriptor Random forest ~sion Gist (GIST) Local Binary Pattern (LBP) 

摘      要：Shot boundary detection is the fundamental part in many real applications as video retrieval and so on. This paper tackles the problem of video segment obtaining in complex movie videos. Firstly, intermediate descriptor is proposed to depict the variation of both abrupt and gradual change in shot boundaries, which is formed by distance vector on Local Binary Pattern(LBP), GIST(GIST) or their fusion. Instead of just using the adjacent frames distance, intermediate descriptor keeps the distances between current frame and consecutive frames. It comprehensively characterizes local temporal structure, which is especially important for gradual change. For the excellent ability for feature fusion in random forests, it is adopted here to verify the fusion effect of intermediate descriptor on LBP and GIST. The whole experiments are designed on the subset of TRECVid 2013 INS(INstance Search) task to verify the effectiveness of proposed intermediate descriptor and the fusion ability for random forest. Compared with static and adaptive thresholds approaches, the best performance can be achieved by post-fusion of intermediate descriptor on LBP and GIST.