系统仿真学报 ›› 2019, Vol. 31 ›› Issue (2): 346-352.doi: 10.16182/j.issn1004731x.joss.17-0089

• 论文 • 上一篇    下一篇

基于多特征融合的指挥手势识别方法研究

王远明1, 张珺1, 秦远辉1, 柴秀娟2   

  1. 1.中国船舶工业系统工程研究院,北京 100094;
    2.中国科学院计算技术研究所智能信息处理重点实验室,北京 100190
  • 收稿日期:2017-02-27 修回日期:2017-05-09 出版日期:2019-02-15 发布日期:2019-02-15
  • 作者简介:王远明(1984-),男,江西井冈山,硕士,高工,研究方向为系统仿真、人机交互;张珺(1973-),男,黑龙江,硕士,研究员,研究方向为航空保障; 秦远辉(1981-),男,黑龙江,硕士,高工,研究方向为计算机仿真。

Gesture Recognition Method Based on Multi-feature Fusion

Wang Yuanming1, Zhang Jun1, Qin Yuanhui1, Chai Xiujuan2   

  1. 1.China State Shipbuilding Corporation System Engineering Research Institute, Beijing 100094, China;
    2. Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, The Chinese Academy of Sciences, Beijing 100190, China
  • Received:2017-02-27 Revised:2017-05-09 Online:2019-02-15 Published:2019-02-15

摘要: 针对飞行甲板指挥手势识别特定应用需求,提出一种基于多特征融合的手势识别方法。利用深度摄像头采集到的视觉信息,从轨迹和手形两方面特征入手,建立了三维轨迹特征向量和手形稀疏表示。一方面基于轨迹特征通过轨迹归一化、重采样、对齐等处理进行识别,另一方面基于HOG(Histogramof Oriented Gradients)特征通过稀疏观察对齐进行手形识别,将识别结果进行有效融合。实验结果表明,提出的基于多特征融合的指挥手势识别方法在准确率上有较大提升,同时具有较好的鲁棒性。

关键词: 飞行甲板, 手势识别, 深度信息, 稀疏表示, 特征融合

Abstract: Aiming at the specific application requirements of command gesture for flight deck, a gesture recognition method based on multi-feature fusion is proposed. The 3D trajectory feature vector and hand sparse representation are established from two aspects of the trajectory and posture based on the visual information collected by depth camera. On the one hand, the gesture is recognized through normalization resampling and alignment based on the trajectory feature. On the other hand, the gesture is recognized through sparse representation alignment based on the HOG feature. The recognition results are fused effectively. The experimental results indicate that our methods greatly enhance accuracy, and have better robustness.

Key words: flight deck, gesture recognition, depth information, sparse representation, feature fusion

中图分类号: