? 基于成员关系直方图描述符的自动跌倒检测
Journal of Computer Science and Technology
Quick Search in JCST
 Advanced Search 
      Home | PrePrint | SiteMap | Contact Us | Help
 
Indexed by   SCIE, EI ...
Bimonthly    Since 1986
Journal of Computer Science and Technology 2017, Vol. 32 Issue (2) :356-367    DOI: 10.1007/s11390-017-1725-z
Artificial Intelligence and Pattern Recognition << Previous Articles | Next Articles >>
基于成员关系直方图描述符的自动跌倒检测
Mohamed Maher Ben Ismail, Ouiem Bchir
College of Computer and Information Sciences, King Saud University, Riyadh 11495, KSA
Automatic Fall Detection Using Membership Based Histogram Descriptors
Mohamed Maher Ben Ismail, Ouiem Bchir
College of Computer and Information Sciences, King Saud University, Riyadh 11495, KSA

摘要
参考文献
相关文章
Download: [PDF 2379KB]  
摘要 我们提出了一个基于视频视觉特征提取的自动跌倒检测方法框架。本文提出的方法依赖于一个编码视频图像视觉特征的成员直方图描述符。此描述符通过使用可能存在的成员关系,将最初的低水平视觉特征映射到一个更有识别性的描述符。在此,此映射可以总结为两个阶段。第一阶段将视频图像的低水平视觉特征分类,并在非监督的情况下生产均匀的集群。第二阶段使用在聚类过程中产生并获取的成员隶属程度,以计算基于成员关系的直方图描述符(MHD)。在检测过程中,本文提出的跌倒检测方法使用一个可能的K-最近邻分类器,将未标记的视频分为跌倒和非跌倒场景两类。我们使用模仿病患跌倒的标准视频数据集对本文提出的方法进行评估。与此同时,我们对比了此方法和目前先进的跌倒检测技术的性能。
关键词跌倒检测   可能性方法   特征提取   聚类     
Abstract: We propose a framework for automatic fall detection based on video visual feature extraction. The proposed approach relies on a membership histogram descriptor that encodes the visual properties of the video frames. This descriptor is obtained by mapping the original low-level visual features to a more discriminative descriptor using possibilistic memberships. This mapping can be summarized in two main phases. The first one consists in categorizing the low-level visual features of the video frames and generating homogeneous clusters in an unsupervised way. The second phase uses the obtained membership degrees generated by the clustering process to compute the membership based histogram descriptor (MHD). For the testing stage, the proposed fall detection approach categorizes unlabeled videos as "Fall" or "Non-Fall" scene using a possibilistic K-nearest neighbors classifier. The proposed approach is assessed using standard videos dataset that simulates patient fall. Also, we compare its performance with that of state-of-the-art fall detection techniques.
Keywordsfall detection   possibilistic approach   feature extraction   clustering     
Received 2016-02-23;
本文基金:

This work was supported by the Research Center of the College of Computer and Information Sciences, King Saud University.

About author: Mohamed Maher Ben Ismail is an assistant professor at the Computer Science Department of the College of Computer and Information Sciences at King Saud University, Riyadh. He received his Ph.D. degree in computer science and engineering from the University of Louisville, KY, USA, in 2011. His research interests include pattern recognition, machine learning, data mining and image processing.
引用本文:   
Mohamed Maher Ben Ismail, Ouiem Bchir.基于成员关系直方图描述符的自动跌倒检测[J]  Journal of Computer Science and Technology , 2017,V32(2): 356-367
Mohamed Maher Ben Ismail, Ouiem Bchir.Automatic Fall Detection Using Membership Based Histogram Descriptors[J]  Journal of Computer Science and Technology, 2017,V32(2): 356-367
链接本文:  
http://jcst.ict.ac.cn:8080/jcst/CN/10.1007/s11390-017-1725-z
Copyright 2010 by Journal of Computer Science and Technology