Natural control of an industrial robot using hand gesture recognition with neural networks
Natural control of an industrial robot using hand gesture recognition with neural networks
复制标题
使用神经网络手势识别对工业机器人进行自然控制
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
O. Gibaru
中科院分区：
文献类型：
--
作者：
M. Simão;P. Neto;O. Gibaru
连续、实时的手势识别是开发新型人机交互方式的关键因素，也是进一步推动机器人在社会中应用的关键因素。在本文中，我们提出了一个手势识别模块的静态和动态手势的大词汇量，有限的培训。识别模块使用通过基于自动运动检测的分割算法获得的特征样本，其是从用于手腕的磁性跟踪器和用于手的数据手套获得的源数据。提出的分类器是一个或两个隐藏层的多层神经网络（感知器）（MLP），25个静态手势（SG）的准确率为98.7%，10个动态手势（DG）的准确率高达99.0%。结果与同类研究相当或更好。
Continuous and real-time gesture spotting is a key factor for the development of novel Human-Robot Interaction (HRI) modalities and further push the use of robots in our society. In this paper we present a hand gesture recognition module for large vocabularies of static and dynamic gestures, with limited training. The recognition module uses feature-samples obtained with an automatic motion detection-based segmentation algorithm, being the source data obtained from a magnetic tracker for the wrist and a data glove for the hand. The classifiers proposed are Multi-Layer Neural Networks (Perceptrons) (MLP) with one or two hidden-layers, with an accuracy of 98.7% for 25 Static Gestures (SGs) and up to 99.0% for 10 Dynamic Gestures (DGs). The results are on par or better than similar studies.