...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Frontiers in Neurorobotics >Self-organizing neural integration of pose-motion features for human action recognition
【24h】

Self-organizing neural integration of pose-motion features for human action recognition

机译：人体动作识别的自组织姿势运动特征神经集成

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The visual recognition of complex, articulated human movements is fundamental for a wide range of artificial systems oriented toward human-robot communication, action classification, and action-driven perception. These challenging tasks may generally involve the processing of a huge amount of visual information and learning-based mechanisms for generalizing a set of training actions and classifying new samples. To operate in natural environments, a crucial property is the efficient and robust recognition of actions, also under noisy conditions caused by, for instance, systematic sensor errors and temporarily occluded persons. Studies of the mammalian visual system and its outperforming ability to process biological motion information suggest separate neural pathways for the distinct processing of pose and motion features at multiple levels and the subsequent integration of these visual cues for action perception. We present a neurobiologically-motivated approach to achieve noise-tolerant action recognition in real time. Our model consists of self-organizing Growing When Required (GWR) networks that obtain progressively generalized representations of sensory inputs and learn inherent spatio-temporal dependencies. During the training, the GWR networks dynamically change their topological structure to better match the input space. We first extract pose and motion features from video sequences and then cluster actions in terms of prototypical pose-motion trajectories. Multi-cue trajectories from matching action frames are subsequently combined to provide action dynamics in the joint feature space. Reported experiments show that our approach outperforms previous results on a dataset of full-body actions captured with a depth sensor, and ranks among the best results for a public benchmark of domestic daily actions.
机译：视觉识别复杂的，有关节的人体运动对于面向人机交互，动作分类和动作驱动感知的各种人造系统至关重要。这些具有挑战性的任务通常可能涉及处理大量的视觉信息和基于学习的机制，以概括一组训练动作并对新样本进行分类。为了在自然环境中运行，至关重要的特性是对动作的有效和鲁棒性识别，例如在系统性传感器错误和临时人员被遮盖的嘈杂条件下，这种动作也是有效的。对哺乳动物视觉系统及其处理生物运动信息的出色能力的研究表明，在多个层面上，姿势和运动特征的独特处理具有独立的神经通路，并且这些视觉线索随后被整合用于动作感知。我们提出了一种以神经生物学为动机的方法，可以实时实现耐噪声的动作识别。我们的模型由自组织的“按需增长”（GWR）网络组成，该网络获得感官输入的逐步概括表示并了解固有的时空依赖性。在训练期间，GWR网络会动态更改其拓扑结构，以更好地匹配输入空间。我们首先从视频序列中提取姿势和运动特征，然后根据典型的姿势运动轨迹对动作进行聚类。随后将来自匹配动作帧的多线索轨迹进行组合，以在联合特征空间中提供动作动态。报道的实验表明，我们的方法在用深度传感器捕获的全身动作数据集上的表现优于先前的结果，并且在国内日常行动的公开基准测试中名列前茅。

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