文献类型：期刊文献

英文题名：Feature fusion based automatic aesthetics evaluation of robotic dance poses

作者：Peng, Hua[1,2,3];Li, Jing[4];Hu, Huosheng[3];Zhao, Liping[1];Feng, Sheng[1];Hu, Keli[1]

机构：[1]Shaoxing Univ, Dept Comp Sci & Engn, Shaoxing, Peoples R China;[2]Jishou Univ, Coll Informat Sci & Engn, Jishou, Peoples R China;[3]Univ Essex, Sch Comp Sci & Elect Engn, Colchester, Essex, England;[4]Shaoxing Univ, Acad Arts, Shaoxing, Peoples R China

年份：2019

卷号：111

起止页码：99

外文期刊名：ROBOTICS AND AUTONOMOUS SYSTEMS

收录：SCI-EXPANDED(收录号：WOS:000452936000008)、、EI(收录号：20184706106724)、Scopus(收录号：2-s2.0-85056605138)、WOS

基金：This work was supported by National Natural Science Foundation of China (Grant No. 61662025, 61601200), and the Research Foundation of Philosophy and Social Science of Hunan Province, China (Grant No. 16YBX042), the Research Foundation of Education Bureau of Hunan Province, China (Grant No. 16C1311), and the Startup Project of Doctor Scientific Research of Shaoxing University, China (Grant No. 20185001, 20185003).

语种：英文

外文关键词：Robotic dance pose; Feature fusion; Machine learning; Automatic aesthetics estimation

外文摘要：Inspired by human dancers who make a comprehensive aesthetic judgement of their own dance poses by using both visual and non-visual information, this paper presents a novel feature fusion based approach to automatic aesthetics evaluation of robotic dance poses in order to improve the performance of robotic choreography creation. Four kinds of features are extracted, namely kinematic feature, region feature, contour feature, and spatial distribution feature of colour block. Based on different feature combinations, machine learning is deployed to train aesthetics models for the automatic judgement on robotic dance poses. The proposed approach has been implemented on a simulated robot environment, and experimental results are presented to verify its feasibility and good performance. (C) 2018 Elsevier B.V. All rights reserved.