School of Mechanical Engineering, Southeast University, Nanjing 211189, China.
Sensors (Basel). 2021 May 27;21(11):3735. doi: 10.3390/s21113735.
Continuous movements of the hand contain discrete expressions of meaning, forming a variety of semantic gestures. For example, it is generally considered that the bending of the finger includes three semantic states of bending, half bending, and straightening. However, there is still no research on the number of semantic states that can be conveyed by each movement primitive of the hand, especially the interval of each semantic state and the representative movement angle. To clarify these issues, we conducted experiments of perception and expression. Experiments 1 and 2 focused on perceivable semantic levels and boundaries of different motion primitive units from the perspective of visual semantic perception. Experiment 3 verified and optimized the segmentation results obtained above and further determined the typical motion values of each semantic state. Furthermore, in Experiment 4, the empirical application of the above semantic state segmentation was illustrated by using Leap Motion as an example. We ended up with the discrete gesture semantic expression space both in the real world and Leap Motion Digital World, containing the clearly defined number of semantic states of each hand motion primitive unit and boundaries and typical motion angle values of each state. Construction of this quantitative semantic expression will play a role in guiding and advancing research in the fields of gesture coding, gesture recognition, and gesture design.
手的连续运动包含离散的意义表达,形成各种语义手势。例如,通常认为手指的弯曲包括弯曲、半弯曲和伸直三种语义状态。然而,对于手部每个运动基元可以传达的语义状态数量,特别是每个语义状态的间隔和代表性运动角度,仍没有研究。为了阐明这些问题,我们进行了感知和表达实验。实验 1 和 2 从视觉语义感知的角度集中研究了不同运动基元单位可感知的语义层次和边界。实验 3 验证并优化了上述分割结果,并进一步确定了每个语义状态的典型运动值。此外,在实验 4 中,我们以 Leap Motion 为例说明了上述语义状态分割的经验应用。我们最终在现实世界和 Leap Motion 数字世界中得到了离散的手势语义表达空间,其中包含了每个手部运动基元单位的清晰定义的语义状态数量以及每个状态的边界和典型运动角度值。这种定量语义表达的构建将在手势编码、手势识别和手势设计等领域的研究中发挥指导和推动作用。