首页> 外文期刊>Journal of visual communication & image representation >Modeling and recognizing action contexts in persons using sparse representation
【24h】

Modeling and recognizing action contexts in persons using sparse representation

机译:使用稀疏表示建模和识别人员的动作上下文

获取原文
获取原文并翻译 | 示例
           

摘要

This paper proposes a novel dynamic sparsity-based classification scheme to analyze various interaction actions between persons. To address the occlusion problem, this paper represents an action in an over-complete dictionary to makes errors (caused by lighting changes or occlusions) sparsely appear in the training library if the error cases are well collected. Because of this sparsity, it is robust to occlusions and lighting changes. In addition, a novel Hamming distance classification (HDC) scheme is proposed to classify action events to various types. Because the nature of Hamming code is highly tolerant to noise, the HDC scheme is also robust to environmental changes. The difficulty of complicated action modeling can be easily tackled by adding more examples to the over-complete dictionary. More importantly, the HDC scheme is very efficient and suitable for real-time applications because no minimization process is involved to calculate the reconstruction error. (C) 2015 Elsevier Inc. All rights reserved.
机译:本文提出了一种新颖的基于动态稀疏性的分类方案,以分析人与人之间的各种交互作用。为了解决遮挡问题,本文提出了一种过完备的字典中的动作,如果错误案例得到了很好的收集,则会使错误(由光照变化或遮挡引起)稀疏地出现在训练库中。由于这种稀疏性,因此对于遮挡和照明更改非常健壮。另外,提出了一种新颖的汉明距离分类(HDC)方案来将动作事件分类为各种类型。由于汉明码的性质高度容忍噪声,因此HDC方案对于环境变化也很健壮。通过向过度完成的字典中添加更多示例,可以轻松解决复杂的动作建模难题。更重要的是,由于不涉及最小化过程来计算重构误差,因此HDC方案非常有效且适用于实时应用。 (C)2015 Elsevier Inc.保留所有权利。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号