Motion retrieval based on Dynamic Bayesian Network and Canonical Time Warping

作者：Xiao, Qinkun^*; Liu Siqi

来源：Soft Computing, 2017, 21(1): 267-280.

DOI：10.1007/s00500-015-1889-9

• Motion retrieval
• ACA
• DBN
• CTW matching

A novel graph-based motion retrieval method is proposed. The method includes the two main stages: (1) in stage of learning, firstly, for each of motion in database, using Aligned Cluster Analysis to get key frames, extracting body gesture and joint state features as observation signal of graph model, based on graph model theory and statistical learning of key frame, a new Dynamic Bayesian Network (DBN) frame is constructed, which is combination of the Switching Kalman Filtering Model and the Hidden Markov Model. The next, a graph-based motion descriptor is built based on DBN inference, and graph-based motion feature database is constructed. (2) In stage of motion retrieval, according to above steps, the graph-based query motion feature is obtained, we can recognize motion category based on Canonical Time Warping matching. The experiments results show proposed method is effectiveness.

• 出版日期2017-1
• 单位西安工业大学