针对视频情感识别中存在运算复杂度高的缺点,提出一种基于时空局部二值模式矩(Temporal-Spatial Local Binary Pattern Moment,TSLBPM)的双模态情感识别方法。首先对视频进行预处理获得表情和姿态序列;然后对表情和姿态序列分别提取TSL...针对视频情感识别中存在运算复杂度高的缺点,提出一种基于时空局部二值模式矩(Temporal-Spatial Local Binary Pattern Moment,TSLBPM)的双模态情感识别方法。首先对视频进行预处理获得表情和姿态序列;然后对表情和姿态序列分别提取TSLBPM特征,计算测试序列与已标记的情感训练集特征间的最小欧氏距离,并将其作为独立证据来构造基本概率分配(Basic Probability Assignment,BPA);最后使用Dempster-Shafer证据理论联合规则得到情感识别结果。在双模态表情和姿态情感数据库上的实验结果表明,本文提出的时空局部二值模式矩可以快速提取视频图像的时空特征,能有效识别情感状态。与其他方法的对比实验也验证了本文融合方法的优越性。展开更多
In this paper,we propose temporal Dempster-Shafer theory to handle the combination of uncertainty andtime. In temporal Dempster-Shafer theory,the element of the temporal frame of discernment is defined as an eventthat...In this paper,we propose temporal Dempster-Shafer theory to handle the combination of uncertainty andtime. In temporal Dempster-Shafer theory,the element of the temporal frame of discernment is defined as an eventthat associates a hypothesis with corresponding time interval. And the assignment of belief to subset of the temporalframe of discernment is performed by the mass function. It is a representation and reasoning mechanism that combinesuncertainty and time by the basic frame of Dempster-Shafer theory.展开更多
An improvement method for the combining rule of Dempster evidence theory is proposed. Different from Dempster theory, the reliability of evidences isn't identical; and varies with the event. By weight evidence acc...An improvement method for the combining rule of Dempster evidence theory is proposed. Different from Dempster theory, the reliability of evidences isn't identical; and varies with the event. By weight evidence according to their reliability, the effect of unreliable evidence is reduced, and then get the fusion result that is closer to the truth. An example to expand the advantage of this method is given. The example proves that this method is helpful to find a correct result.展开更多
文摘针对视频情感识别中存在运算复杂度高的缺点,提出一种基于时空局部二值模式矩(Temporal-Spatial Local Binary Pattern Moment,TSLBPM)的双模态情感识别方法。首先对视频进行预处理获得表情和姿态序列;然后对表情和姿态序列分别提取TSLBPM特征,计算测试序列与已标记的情感训练集特征间的最小欧氏距离,并将其作为独立证据来构造基本概率分配(Basic Probability Assignment,BPA);最后使用Dempster-Shafer证据理论联合规则得到情感识别结果。在双模态表情和姿态情感数据库上的实验结果表明,本文提出的时空局部二值模式矩可以快速提取视频图像的时空特征,能有效识别情感状态。与其他方法的对比实验也验证了本文融合方法的优越性。
文摘In this paper,we propose temporal Dempster-Shafer theory to handle the combination of uncertainty andtime. In temporal Dempster-Shafer theory,the element of the temporal frame of discernment is defined as an eventthat associates a hypothesis with corresponding time interval. And the assignment of belief to subset of the temporalframe of discernment is performed by the mass function. It is a representation and reasoning mechanism that combinesuncertainty and time by the basic frame of Dempster-Shafer theory.
文摘An improvement method for the combining rule of Dempster evidence theory is proposed. Different from Dempster theory, the reliability of evidences isn't identical; and varies with the event. By weight evidence according to their reliability, the effect of unreliable evidence is reduced, and then get the fusion result that is closer to the truth. An example to expand the advantage of this method is given. The example proves that this method is helpful to find a correct result.
