中文摘要：

针对视频中连续的未分割人体动作识别存在的一些问题,提出一种基于隐动态条件神经域模型（latent-dynamic conditional neural fields,LDCNF）的在线行为识别方法。LDCNF模型含有两个隐层,在潜动态条件随机场（LDCRF）的基础上,增加一层神经网络层,即门层,提取输入数据和输出标签间的非线性关系;增加一种新规则项训练该模型,辨别动作序列隐状态间的差异性。在仿真实验中,针对10种连续的行为动作,将该算法与条件随机场（CRF）、HCRF、LDCRF进行识别效果的对比。实验结果表明,对于联机处理行为序列,该算法相比于CRF、HCRF、LDCRF模型具有更好的识别率。

英文摘要：

In view of the continuous unsegmented human behavior recognition in video,a kind of online behavior recognition algorithm based on latent-dynamic conditional neural field（LDCNF）was introduced.LDCNF model contained two hidden layers,on the basis of latent-dynamic conditional random field（LDCRF）,a layer of neural network was added,i.e.gating layer,to extract non-linear relationships between input data and output labels.A new regularization term was added for the training of this model,encouraging action sequences＇ diversity between hidden-states.In the simulation experiment,ten kinds of behavior recognition results for conditional random field（CRF）,HCRF,LDCRF and LDCNF were compared.For the online processing behavior sequence,the results show that the proposed algorithm,compared to CRF,HCRF,LDCRF,has better recognition rate.