文章基本信息

标题：Autonomous Viewpoint Selection of Robot Based on Aesthetic Evaluation of a Scene
本地全文：下载
作者：Kai Lan ; Kosuke Sekiyama
期刊名称：Journal of Artificial Intelligence and Soft Computing Research
电子版ISSN：2083-2567
出版年度：2016
卷号：6
期号：4
页码：255-265
DOI：10.1515/jaiscr-2016-0019
出版社：Walter de Gruyter GmbH
摘要：In this paper, we propose an optimal viewpoint selection system for monitoring robots to search for the optimal viewpoint of a scene with the highest aesthetic property. Using the information of the targets, we propose a novel method for predicting human aesthetic sense for a scene. We construct evaluation functions based on certain known composition rules using three factors, namely, target size, visual balance, and composition fitting value. Then a score, which is a reflection of human evaluation, will be obtained using these functions. The optimal viewpoint will be selected from a number of candidates around the target group, by evaluating the aesthetic properties of scenes for each candidate viewpoint. Finally, once the optimal viewpoint is confirmed, path planning and path following controls are implemented for the robots during the moving process.
关键词：optimal viewpoint selection system ; aesthetic evaluation ; viewpoint searching