Flexible human motion transition via hybrid deep neural network and quadruple-like structure learning

作     者：Peng, Shu-Juan Zhang, Liang-Yu Liu, Xin 

作者机构：Huaqiao Univ Coll Comp Sci & Technol Xiamen 361021 Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen 361021 Peoples R China Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen 361021 Peoples R China 

出 版 物：《INTERNATIONAL JOURNAL OF COMPUTATIONAL SCIENCE AND ENGINEERING》 (国际计算科学与工程学杂志)

年 卷 期：2021年第24卷第2期

页      面：136-146页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Fundamental Research Funds for the Central Universities of Huaqiao University [ZQN-709] Science and Technology Project of Quanzhou [2018C107R] 

主　　题：skeletal motion transition hybrid deep learning convolutional restricted Boltzmann machine quadruples-like data structure 

摘      要：Skeletal motion transition is of crucial importance to the animation creation. In this paper, we propose a hybrid deep learning framework that allows for efficient human motion transition. First, we integrate a convolutional restricted Boltzmann machine with deep belief network to extract the spatio-temporal features of each motion style, featuring on appropriate detection of transition points. Then, a quadruples-like data structure is exploited for motion graph building, motion splitting and indexing. Accordingly, the similar frames fulfilling the transition segments can be efficiently retrieved. Meanwhile, the transition length is reasonably computed according to the average speed of the motion joints. As a result, different kinds of diverse motions can be well transited with satisfactory performance. The experimental results show that the proposed transition approach brings substantial improvements over the state-of-the-art methods.