ConvNets-based action recognition from skeleton motion maps
ConvNets-based action recognition from skeleton motion maps
复制标题
基于 ConvNets 的骨骼运动图动作识别
DOI：
10.1007/s11042-019-08261-1
复制
发表时间：
2019-11-07
影响因子：
3.6
通讯作者：
Li, Wanqing
中科院分区：
文献类型：
--
作者：
Chen, Yanfang;Wang, Liwei;Li, Wanqing
随着深度学习的发展，基于深度学习的动作识别成为计算机视觉领域的一个重要研究课题。骨架序列通常被编码到图像中，以更好地使用卷积神经网络（ConvNets），如联合轨迹映射（JTM）。然而，这种编码方法不能有效地捕获长时间信息。为了解决这一问题，本文提出了一种有效的方法，将时空信息从骨架序列中编码到彩色纹理图像中，称为时间金字塔骨架运动映射（TPSMMs），并应用卷积神经网络（ConvNets）从TPSMMs中提取判别特征，用于人体动作识别。TPSMM不仅可以捕获短时间信息，还可以嵌入长时间的动态信息。该方法在广泛使用的UTD-MHAD、MSRC-12 Kinect Gesture和SYSU-3D数据集上进行了验证，取得了较好的效果。
With the advance of deep learning, deep learning based action recognition is an important research topic in computer vision. The skeleton sequence is often encoded into an image to better use Convolutional Neural Networks (ConvNets) such as Joint Trajectory Maps (JTM). However, this encoding method cannot effectively capture long temporal information. In order to solve this problem, This paper presents an effective method to encode spatial-temporal information into color texture images from skeleton sequences, referred to as Temporal Pyramid Skeleton Motion Maps (TPSMMs), and Convolutional Neural Networks (ConvNets) are applied to capture the discriminative features from TPSMMs for human action recognition. The TPSMMs not only capture short temporal information, but also embed the long dynamic information over the period of an action. The proposed method has been verified and achieved the state-of-the-art results on the widely used UTD-MHAD, MSRC-12 Kinect Gesture and SYSU-3D datasets.