arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.14870cs.CVcs.AIcs.HCcs.LGcs.RO
收藏

行动在心中:一个神经网络方法的行动识别和分割

Action in Mind: A Neural Network Approach to Action Recognition and Segmentation

Lund University(隆德大学)

Zahra Gharaee

摘要:

识别和分类人类行为是一项重要的任务,在各种领域,如人机交互,视频分析,监控,视频检索,医疗保健系统和娱乐行业的应用。本文提出了一种新的基于人工神经网络多层结构的人体动作识别方法。每个系统级开发旨在解决动作识别问题的不同方面,包括在线实时处理,动作分割和对象的参与。实验结果的分析在六篇文章中进行了说明和描述。本文提出的动作识别体系结构由预处理层、有序向量表示层和三层神经网络组成。它利用自组织神经网络,如Kohonen特征映射和生长网格作为主要的神经网络层。因此,该架构提出了一种生物学上合理的方法,具有某些特征,如神经元的拓扑组织、横向相互作用、半监督学习和在低维映射中表示高维输入空间的能力。对于每个开发水平,系统用由连续3D身体姿势组成的输入数据训练,并用系统以前从未遇到过的一般化输入数据测试。不同系统级开发的实验结果表明,该系统性能良好,具有相当高的准确率识别人的行动。

英文摘要:

Recognizing and categorizing human actions is an important task with applications in various fields such as human-robot interaction, video analysis, surveillance, video retrieval, health care system and entertainment industry. This thesis presents a novel computational approach for human action recognition through different implementations of multi-layer architectures based on artificial neural networks. Each system level development is designed to solve different aspects of the action recognition problem including online real-time processing, action segmentation and the involvement of objects. The analysis of the experimental results are illustrated and described in six articles. The proposed action recognition architecture of this thesis is composed of several processing layers including a preprocessing layer, an ordered vector representation layer and three layers of neural networks. It utilizes self-organizing neural networks such as Kohonen feature maps and growing grids as the main neural network layers. Thus the architecture presents a biological plausible approach with certain features such as topographic organization of the neurons, lateral interactions, semi-supervised learning and the ability to represent high dimensional input space in lower dimensional maps. For each level of development the system is trained with the input data consisting of consecutive 3D body postures and tested with generalized input data that the system has never met before. The experimental results of different system level developments show that the system performs well with quite high accuracy for recognizing human actions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑