基于时序上下文的视频场景分类  

Video classification based on time series contextual information

作　　者：彭太乐[1,2] 张文俊[3] 丁友东[3] 郭桂芳[2] 

机构地区：[1]上海大学通信与信息工程学院,上海200072 [2]淮北师范大学计算机科学与技术学院,安徽淮北235000 [3]上海大学影视艺术技术学院,上海200072

出　　处：《计算机工程与应用》2014年第9期103-106,149,共5页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61303093);安徽省高校自然科学研究重点项目(No.KJ2010A304)

摘　　要：以传统的词袋模型为基础,根据相邻镜头关键帧之间具有相关性的特点提出了一种用于视频场景分类的模型。将视频片段进行分割,提取关键帧,对关键帧图像归一化。将关键帧图像作为图像块以时序关系合成新图像,提取新图像的SIFT特征及HSV颜色特征,将图像的SIFT特征及HSV颜色特征数据映射到希尔伯特空间。通过多核学习,选取合适的核函数组对每个图像进行训练,得到分类模型。通过对多种视频进行实验,实验结果表明,该方法在视频场景分类中能取得很好的效果。On the basis of traditional bag of word model, according to the spatial and semantic similarity between the key frames of adjacent lens, this paper brings a new video scene classification model. It divides video clips into many shots and extracts their key frames and makes the key frames a gauge. The next thing is that the key frames as an image block produces an image on time sequence. SIFT features and HSV feature are extracted. This paper embeds the SIFT features and HSV feature data into Hilbert space. Through multi kernel learning, the algorithm selects the appropriate kernel func-tions to train each image, and gets the classification model. Experiments show that the proposed algorithm for video classi-fication can achieve better performance.

关 键 词：时序上下文特征 尺度不变特征变换(SIFT)特征 HSV颜色特征 多核学习 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]