Feature-based Egocentric Grasp Pose Classification for Expanding Human-Object Interactions
Feature-based Egocentric Grasp Pose Classification for Expanding Human-Object Interactions
复制标题
DOI：
10.1109/isie45552.2021.9576369
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Adnan Rachmat;Anom Besari;Azhar Aulia Saputra;W. Chin;N. Kubota
中科院分区：
文献类型：
--
作者：
Adnan Rachmat;Anom Besari;Azhar Aulia Saputra;W. Chin;N. Kubota
本文提出了一种对手势进行分类的框架，特别是在直观地抓取物体时。首先，我们提出了一种基于立体红外图像作为传感器的系统，可以在三维空间中产生手的坐标。我们使用以自我为中心的视觉，因为它只需要一个传感器模块就可以获得统一和自然的数据。其次，我们对位置进行变换，得到手指上每个关节的角度信息。第三，设计了一个基于多层感知器(MLP)的智能系统，对角度数据进行处理，得到符合Cutkosky GRASH分类标准的分类结果。最后，我们对几个相似对象的分类结果进行了比较，并评价了它们的分类精度。在验证阶段，结果得出16种抓取姿势分类的正确率为89.60%。在实时测试中，结果的准确率为81.93%。这一结果表明，基于特征的学习可以降低MLP的复杂度和训练时间。此外，少量的训练数据就足以进行训练和实施。
This paper presents a framework for classifying human hand pose, especially in grasping object intuitively. First, we propose a system based on the stereo infra-red image as a sensor that can produce hand coordinates in 3-dimensional space. We use egocentric vision because it can get uniform and natural data with only a single sensor module. Second, we transformed the position to get the angle information for each joint on the finger. Third, we designed an intelligent system based on Multi-Layer Perceptron (MLP) to process angular data to obtain classification results according to the Cutkosky grasp taxonomy. Finally, we compared the results on several similar objects and evaluated their classification accuracy. In the validation phase, the results yielded an accuracy of 16 grasp pose classification is 89,60%. In real-time testing, the results yielded an accuracy of 81.93%. This result shows feature-based learning can reduce the complexity and training time of the MLP. Furthermore, a small amount of training data is sufficient for the training and implementation.