| 陈姝琪,曹江涛,赵 挺,姬晓飞.基于关节点数据的双人交互行为识别[J].电子测量与仪器学报,2020,34(6):124-130 |
| 基于关节点数据的双人交互行为识别 |
| Two-person interaction behavior recognition based on joint data |
| |
| DOI： |
| 中文关键词: 关节点数据 HOJ3D 特征 关节距离特征 卷积神经网络 |
| 英文关键词:joint point data HOJ3D characteristic joint distance characteristics convolutional neural network |
| 基金项目:国家自然科学基金(61673199)、辽宁省科学事业公益研究基金(2016002006)资助项目 |
|
|
|
|
| 摘要点击次数: 351 |
| 全文下载次数: 706 |
| 中文摘要: |
| 近年来基于 RGB 视频的双人交互行为识别取得了重大进展,但 RGB 视频数据的问题严重影响双人交互行为识别率。
随着深度传感器(如微软 Kinect)的快速发展,为准确获取人体运动的关节点数据提供了可能,可以大大的弥补 RGB 视频数据
的不足。 提出一种基于关节点数据的双人交互行为识别方法。 首先对关节点数据计算出 HOJ3D 特征和关节距离特征,并将特
征按照时间顺序进行图形化后分别送入的卷积神经网络中,分别提取两种深层次特征并进行拼接,然后使用 Softmax 分类器进
行分类识别。 该方法在 SBU Kinect 动作数据集的测试结果表明,该方法的识别准确率得到了一定的提高,达到了 94. 4%。 该方
法实现简单,且具有实时处理的能力,具有较好的应用前景。 |
| 英文摘要: |
| In recent years, significant progress has been made in two-person interaction recognition based on RGB video, but there are
still many problems in RGB video data that seriously affect the recognition rate of two-person interaction. With the rapid development of
depth sensors (such as the Microsoft Kinect), it is possible to directly obtain a data point that can track human movement, making up
for the lack of RGB video data. Therefore, a two-person interaction behavior recognition method based on node data is proposed. First,
HOJ3D features and joint distance features were calculated from the data of the node, and then were graphically sent into different
convolutional neural networks. Then, the two features were extracted and splicedtogether. Then, Softmax classifier was used for
classification and recognition. The test results of the method on the SBU Kinect action dataset show that the recognition accuracy of the
method has been improved to a certain extent, reaching 94. 4%. The method is simple to implement, has the ability of real-time
processing, and has a good application prospect. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
