论文标题
基于内部时钟的时空神经网络，用于运动速度识别
An Internal Clock Based Space-time Neural Network for Motion Speed Recognition
论文作者
论文摘要
在这项工作中，我们提出了一个基于内部时钟的新型时空神经网络，用于运动速度识别。开发的系统具有Spike Train编码器，具有内部时钟行为的尖峰神经网络（SNN），模式转换块和网络动态依赖性可塑性（NDDP）学习块。核心原理是开发的SNN将自动调整其网络模式频率（内部时钟频率），以识别速度域中的人类运动。我们使用动画片和现实世界视频作为培训基准，结果表明，我们的系统不仅可以识别出相当大的速度差异（例如跑步，步行，跳跃，跳跃，奇迹（思维）和停滞）的动作，而且还具有诸如跑步和快速步行之类的细微速度差距的动作。推断准确性可以高达83.3％（卡通视频）和75％（现实世界的视频）。同时，该系统在学习阶段仅需要六个视频数据集，最多需要42个培训试验。硬件性能估计表明，训练时间为0.84-4.35，功耗为33.26-201MW（基于ARM Cortex M4处理器）。因此，我们的系统对小型数据集的需求，快速学习和低功率性能具有独特的学习优势，这对基于边缘或可扩展的应用程序具有巨大的潜力。
In this work we present a novel internal clock based space-time neural network for motion speed recognition. The developed system has a spike train encoder, a Spiking Neural Network (SNN) with internal clocking behaviors, a pattern transformation block and a Network Dynamic Dependent Plasticity (NDDP) learning block. The core principle is that the developed SNN will automatically tune its network pattern frequency (internal clock frequency) to recognize human motions in a speed domain. We employed both cartoons and real-world videos as training benchmarks, results demonstrate that our system can not only recognize motions with considerable speed differences (e.g. run, walk, jump, wonder(think) and standstill), but also motions with subtle speed gaps such as run and fast walk. The inference accuracy can be up to 83.3% (cartoon videos) and 75% (real-world videos). Meanwhile, the system only requires six video datasets in the learning stage and with up to 42 training trials. Hardware performance estimation indicates that the training time is 0.84-4.35s and power consumption is 33.26-201mW (based on an ARM Cortex M4 processor). Therefore, our system takes unique learning advantages of the requirement of the small dataset, quick learning and low power performance, which shows great potentials for edge or scalable AI-based applications.
