...
首页> 外文期刊>Pattern Recognition: The Journal of the Pattern Recognition Society >Deep ensemble network using distance maps and body part features for skeleton based action recognition
【24h】

Deep ensemble network using distance maps and body part features for skeleton based action recognition

机译:深合奏网络使用距离图和基于骨架的动作识别的距离图和身体部位特征

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       

摘要

Human action recognition is a hot research topic in the field of computer vision. The availability of low cost depth sensors in the market made the extraction of reliable skeleton maps of human objects easier. This paper proposes three subnets, referred to as SNet, TNet, and BodyNet to capture diverse spatiotemporal dynamics for action recognition task. Specifically, SNet is used to capture pose dynamics from the distance maps in the spatial domain. The second subnet (TNet) captures the temporal dynamics along the sequence. The third net (BodyNet) extracts distinct features from the fine-grained body parts in the temporal domain. With the motivation of ensemble learning, a hybrid network, referred to as HNet, is modeled using two subnets (TNet and BodyNet) to capture robust temporal dynamics. Finally, SNet and HNet are fused as one ensemble network for action classification task. Our method achieves competitive results on three widely used datasets: UTD MHAD, UT Kinect and NTU RGB+D. (C) 2019 Elsevier Ltd. All rights reserved.
机译:人类行动认可是计算机愿景领域的热门研究课题。市场中低成本深度传感器的可用性使得人对物体的可靠骨架地图的提取更容易。本文提出了三个子网,称为SNET,TNET和BOARTNET,以捕获用于行动识别任务的不同的时空动态。具体地,SNET用于从空间域中的距离图捕获姿势动态。第二个子网(TNET)沿序列捕获时间动态。第三栏(BOARYNET)从颞域域中的细粒体部件提取不同的特征。随着集合学习的动机,使用两个子网(TNET和BOARTNET)建模了一个混合网络,以捕获强大的时间动态。最后,SNET和HNET融合为Action Classification任务的一个集合网络。我们的方法在三种广泛使用的数据集中实现了竞争结果:UTD MHAD,UT Kinect和NTU RGB + D. (c)2019年elestvier有限公司保留所有权利。

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