电子测量与仪器学报

罗冬梅,左金水,余文森.基于双特征融合与自适应提升机制的图像动作识别算法[J].电子测量与仪器学报,2017,31(12):1929-1936

基于双特征融合与自适应提升机制的图像动作识别算法

Motion recognition algorithm based on double feature fusion and adaptive boosting mechanism

DOI：10.13382/j.jemi.2017.12.007

中文关键词: 图像动作识别时空上下文双特征融合卷积神经网络主成分分析自适应提升算法

英文关键词:image motion recognition temporal and spatial context double feature fusion convolution neural network principal component analysis adaptive lifting algorithm

基金项目:教育部科学青年基金(13YJC630253)、福建省自然科学基金(2015J01668)、福建省中青年教师教育科研项目(JB14103)资助

作者	单位
罗冬梅	武夷学院信息技术与实验室管理中心武夷山354300
左金水	浙江工商大学管理学院杭州310018
余文森	武夷学院数学与计算机学院武夷山354300

Author	Institution
Luo Dongmei	Information Technology and Laboratory Management Center, Wuyi University, Wuyishan 354300, China
Zuo Jinshui	College of Management, Zhejiang Gongshang University, Hangzhou 310018, China
Yu Wensen	College of Mathematics and Computer, Wuyi University, Wuyishan 354300, China

摘要点击次数: 2421

全文下载次数: 8068

中文摘要:

针对复杂环境中动作识别易受到光照变化、目标旋转，遮挡等导致目标位置不精确，目标漂移以及识别错误等问题，提出了一种基于双特征融合与自适应提升的动作识别算法。首先，基于时空上下文（spatio temporal context，STC）机制，通过时空上下文关系与视觉系统特性来提取图像序列特征，降低光照变化、遮挡对行为动作的影响；同时，利用卷积神经网络（convolution neural network, CNN）来处理图像序列，分别获得STC特征与CNN特征；其次，引入主成分分析算子，定义双特征融合规则，对获得STC特征与CNN特征进行组合，形成一种更准确、完整的特征表示；然后，通过得到的新特征，利用自适应提升算法（adaptive boosting algorithm，ABA）进行分类训练，完成对行为动作决策判断。在Weizmann、Hollywood数据集上测试表明，相对于当前常用的动作识别方法，所提算法对各种行为动作具有更高的识别精度与鲁棒性，更能适应复杂背景和动作变化。所提算法具有较高的人体动作识别精度，在视频监测、人机交互等领域具有一定的应用价值。

英文摘要:

In order to solve the defects such as inaccurate target location, target drift and recognition error induced by influence of illumination change, target rotation, occlusion in complex environment, a motion recognition algorithm based on double feature fusion and adaptive boosting was proposed. Firstly, in order to reduce the influence of illumination variation and occlusion on behavior, spatio temporal context was used to extract the image sequences feature based on spatiotemporal context and the visual system characteristics. At the same time, the convolution neural network was introduced to operate the image sequence’s features for obtaining the STC and CNN features. Secondly, the principal component analysis operator was introduced to effectively combine the STC features and features to form a more accurate and complete feature representation. Then, by the new features, the adaptive boosting algorithm was used for classification training, the decision making of action was completed. The tests on the current popular data set show that, compared with the current commonly used behavior recognition methods, the proposed algorithm can recognize and understand all kinds of action, recognition rate is greatly improved, able to adapt for complex background and behavioral changes. This algorithm has higher accuracy and practical value in video surveillance and human computer interaction.

查看全文查看/发表评论下载PDF阅读器