[1]石爱辉,程勇,曹雪虹.结合码本优化和特征融合的人体行为识别方法[J].计算机技术与发展,2018,28(02):107-117.[doi:10．3969/j．issn．1673－629X．2018．02．024]
　SHI Ai-hui,CHENG Yong,CAO Xue-hong.A Human Action Ｒecognition Method Combined with Codebook Optimization and Feature Fusion[J].,2018,28(02):107-117.[doi:10．3969/j．issn．1673－629X．2018．02．024]
点击复制

结合码本优化和特征融合的人体行为识别方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年02期
页码:
107-117
栏目:
智能、算法、系统工程
出版日期:
2018-02-10

文章信息/Info

Title:
A Human Action Ｒecognition Method Combined with Codebook Optimization and Feature Fusion
文章编号:
1673－629X(2018)02－0107－05
作者:
石爱辉1; 程勇2 ;  曹雪虹1  2
1．南京邮电大学 通信与信息工程学院，江苏 南京 210003;
2．南京工程学院 通信工程学院，江苏 南京 211167
Author(s):
SHI Ai-hui 1 ; CHENG Yong 2 ; CAO Xue-hong 1   2
1．School of Communications and Information Technology，Nanjing University of Posts and Telecommunications，Nanjing 210003，China;
2．School of Communication Engineering，Nanjing Institute of Technology，Nanjing 211167，China
关键词:
词袋模型; 两层 K－means 聚类; 视频表达级特征融合; 行为识别
Keywords:
 ; bag of word model; two－level K－means clustering; video representation－level feature fusion; action recognition
分类号:
TP391
DOI:
10．3969/j．issn．1673－629X．2018．02．024
文献标志码:
A
摘要:
为了提高视频序列中人体行为识别的正确率，提出了一种结合两层 K－means 聚类优化码本和视频表达级特征融合的行为识别方法。首先对训练集视频提取出的时空兴趣点利用梯度方向直方图(HOG)和光流直方图(HOF)进行描述，并对属于不同视频以及不同种类动作视频的描述子使用两层 K－means 聚类形成各自更具有代表性的视觉词汇，从而提高码本的表达能力。然后将表示每个视频的 HOG 和 HOF 描述子分别作为码本优化后的词袋模型的输入，得到两种不同的视频全局表达并进行特征融合，由于 HOG 和 HOF 描述子在形成视频表达级特征时相关性较大，融合后的特征更具区分性和分类鲁棒性。最后采用支持向量机对融合后的特征进行分类识别。实验结果表明，该方法能够有效地提高识别率。
Abstract:
In order to improve the accuracy of human actions recognition in video sequence，we present an actions recognition method which combines two－level K－means clustering with video－level descriptor feature fusion．Firstly the space－time interest points extracted by video in training set are described by histogram of oriented gradient (HOG) and histograms optical flow (HOF)，and the descriptors of different video and different kinds of motion video are formed their representative visual vocabulary respectively through K－means clustering with two
levels，thus improving the expression of the codebook．Taking the descriptors of HOF and HOG as the input of the bag of word model respectively，the two different global expressions of video are obtained and fused in features．Due to the high correlation when the descriptors of HOG and HOF forming the characteristics of the video expression level，the fused features are distinguishing and robust in classification．Finally，the support vector machine (SVM) is adopted for classification and recognition to characteristics of fusion．The experiments show that
the proposed method can improve the accuracy of recognition effectively．

相似文献/References:

[1]金壮壮,曹江涛,姬晓飞.多源信息融合的双人交互行为识别算法研究[J].计算机技术与发展,2018,28(10):32.[doi:10.3969/ j. issn.1673-629X.2018.10.007]
　JIN Zhuang-zhuang,CAO Jiang-tao,JI Xiao-fei.Research on Human Interaction Recognition Algorithm Based on Multi-source Information Fusion[J].,2018,28(02):32.[doi:10.3969/ j. issn.1673-629X.2018.10.007]
[2]苏子旸,张 策*,张 茹,等.视觉同步定位与建图系统中回环检测研究进展[J].计算机技术与发展,2023,33(04):1.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 001]
　SU Zi-yang,ZHANG Ce*,ZHANG Ru,et al.Research Progress of Loop-closure Detection in Visual SLAM System[J].,2023,33(02):1.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 001]

更新日期/Last Update: 2018-03-29