Department of Physical Education, China University of Petroleum (East China), Qingdao, Shandong 266580, China.
ZUGO Intelligence Technology (Shen Zhen) Co. Ltd., ZUGO Digital Energy Building Keji First Road High-Tech Zone, Zhuhai, Guandong 519080, China.
Comput Intell Neurosci. 2022 Jun 28;2022:6988525. doi: 10.1155/2022/6988525. eCollection 2022.
With the rapid development of the Internet, various electronic products based on computer vision play an increasingly important role in people's daily lives. As one of the important topics of computer vision, human action recognition has become the main research hotspot in this field in recent years. The human motion recognition algorithm based on the convolutional neural network can realize the automatic extraction and learning of human motion features and achieve good classification performance. However, deep convolutional neural networks usually have a large number of layers, a large number of parameters, and a large memory footprint, while embedded wearable devices have limited memory space. Based on the traditional cross-entropy error-based training mode, the parameters of all hidden layers must be kept in memory and cannot be released until the end of forward and reverse error propagation. As a result, the memory used to store the parameters of the hidden layer cannot be released and reused, and the memory utilization efficiency is low, which leads to the backhaul locking problem, limiting the deployment and execution of deep convolutional neural networks on wearable sensor devices. Based on this, this topic designs a local error convolutional neural network model for human motion recognition tasks. Compared with the traditional global error, the local error constructed in this paper can train the convolutional neural network layer by layer, and the parameters of each layer can be trained independently according to the local error and does not depend on the gradient propagation of adjacent upper and lower layers. As a result, the memory used to store all hidden layer parameters can be released in advance without waiting for the end of forward and backward propagation, avoiding the problem of backhaul locking, and improving the memory utilization of convolutional neural networks deployed on embedded wearable devices.
随着互联网的飞速发展，基于计算机视觉的各种电子产品在人们的日常生活中发挥着越来越重要的作用。作为计算机视觉的重要课题之一，人体动作识别近年来已成为该领域的主要研究热点。基于卷积神经网络的人体动作识别算法可以实现人体动作特征的自动提取和学习，达到良好的分类性能。然而，深度卷积神经网络通常具有大量的层、大量的参数和较大的内存占用，而嵌入式可穿戴设备的内存空间有限。基于传统的基于交叉熵误差的训练模式，所有隐藏层的参数都必须保存在内存中，并且在正向和反向误差传播结束之前不能释放。因此，用于存储隐藏层参数的内存无法释放和重用，内存利用率低，导致回传锁定问题，限制了深度卷积神经网络在可穿戴传感器设备上的部署和执行。基于此，本课题设计了一种用于人体运动识别任务的局部误差卷积神经网络模型。与传统的全局误差相比，本文构建的局部误差可以逐层训练卷积神经网络，并且可以根据局部误差独立训练每个层的参数，而不依赖于相邻上下层的梯度传播。因此，可以提前释放用于存储所有隐藏层参数的内存，而无需等待正向和反向传播结束，从而避免回传锁定问题，并提高部署在嵌入式可穿戴设备上的卷积神经网络的内存利用率。
