空间时间变压器与科尔莫戈罗夫-阿诺德网络用于基于骨架的手势识别
Pengcheng Han1, Xin He1, Takafumi Matsumaru1
1Graduate School of Information, Production and System, Waseda University, Kitakyushu 808-0135, Japan.
Sensors (Basel, Switzerland)
|February 13, 2025
概括
本研究介绍了基于骨架的手势识别的ST-KT框架,使用时空图形卷积和Kolmogorov-Arnold网络 (KAN) 的变压器来捕捉复杂的关节动态,以提高准确性.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 人与计算机的交互
背景情况:
- 手动功能工程用于手势识别是主观的,缺乏稳定性.
- 现有的深度学习模型往往忽略了关键的时空和结构手关节信息.
- 捕捉非相邻的手关节之间的远程依赖关系对于准确的识别至关重要.
研究的目的:
- 提出基于骨的高级手势识别框架,ST-KT.
- 为了有效地建模人手关节数据中的空间和时间依赖关系.
- 利用图形卷积网络和转换器架构的优势,并使用Kolmogorov-Arnold网络 (KAN) 进行增强.
主要方法:
- 该ST-KT框架集成了时空图形卷积网络 (ST-GCN) 模块和基于KAN的变压器.
- ST-GCN模块 (包括空间图卷积网络和时间卷积网络) 提取初始骨架序列特征.
- 一种时空位置嵌入方法以身份和时间上下文丰富了节点表示,而KAN-Transformers捕捉了复杂的关联关系.
主要成果:
- 拟议的ST-KT方法在具有挑战性的数据集上实现了高精度:97.5%的SHREC'17和94.3%的DHG-14/28.
- 该框架有效地捕捉了动态骨架变化和复杂的关节间关系.
- 将KAN集成到变压器中,增强了非线性建模功能,以获得更丰富的特征提取.
结论:
- 在基于骨架的动态手势识别中,ST-KT框架表现出卓越的性能.
- 该方法通过结合时空动态和远程联合依赖,成功地解决了以前方法的局限性.
- 这项研究为先进的人机交互应用提供了强大而准确的解决方案.
关键词:
注意力机制注意力机制连续的手动手势识别.深度学习是一种深度学习.功能提取 特性提取图表 卷积网络 卷积网络手的手势识别手势识别人与计算机的交互 (HCI)基于骨架的骨架.变压器的变压器是一个变压器.更多相关视频
相关概念视频
Sequence Networks of Rotating Machines
91
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
91
Relative Motion Analysis using Rotating Axes-Problem Solving
382
Consider a crane whose telescopic boom rotates with an angular velocity of 0.04 rad/s and angular acceleration of 0.02 rad/s2. Along with the rotation, the boom also extends linearly with a uniform speed of 5 m/s. The extension of the boom is measured at point D, which is measured with respect to the fixed point C on the other end of the boom. For the given instant, the distance between points C and D is 60 meters.
Here, in order to determine the magnitude of velocity and acceleration for point...
Here, in order to determine the magnitude of velocity and acceleration for point...
382
Relative Motion Analysis using Rotating Axes
442
Consider a component AB undergoing a linear motion. Along with a linear motion, point B also rotates around point A. To comprehend this complex movement, position vectors for both points A and B are established using a stationary reference frame.
However, to express the relative position of point B relative to point A, an additional frame of reference, denoted as x'y', is necessary. This additional frame not only translates but also rotates relative to the fixed frame, making it...
However, to express the relative position of point B relative to point A, an additional frame of reference, denoted as x'y', is necessary. This additional frame not only translates but also rotates relative to the fixed frame, making it...
442
Kinematic Equations for Rotation
304
In mechanics, when one observes a rigid body in rotational motion with constant angular acceleration, it is possible to establish equations for its rotational kinematics. This process resembles how linear kinematics are dealt with in simpler motion studies.
For instance, imagine a point A on a rigid body engaged in circular motion. The translational velocity of this particular point can be calculated by taking the time derivatives of the displacement equation, which essentially measures the...
For instance, imagine a point A on a rigid body engaged in circular motion. The translational velocity of this particular point can be calculated by taking the time derivatives of the displacement equation, which essentially measures the...
304


