一种基于多因子贝叶斯决策的泛在地图图像视觉平衡度计算框架  

A Calculation Framework of Visual Balance Index of Ubiquitous Map Images Based on Multi-factor Bayesian Decision Making

作　　者：徐晔秋 杨剑 贾奋励[1] 杨磊 郭丽萍 王维明 XU Yeqiu;YANG Jian;JIA Fenli*;YANG Lei;GUO Liping;WANG Weiming(School of Geospatial Information,Information Engineering University,Zhengzhou 450052,China;PLA Unit 61363,Xi'an 710054,China;PLA Unit 61175,Nanjing 210049,China;PLA Unit 61243,Urumqi 830000,China)

机构地区：[1]信息工程大学地理空间信息学院,郑州450052 [2]61363部队,西安710054 [3]61175部队,南京210049 [4]61243部队,乌鲁木齐830000

出　　处：《地球信息科学学报》2024年第1期184-196,共13页Journal of Geo-information Science

基　　金：国家自然科学基金项目(42130112、41671407、41901335);国家重点研发计划项目(2017YFB0503500)。

摘　　要：视觉平衡是影响地图信息传输效果的重要因素之一。由于泛在制图的非专业性,泛在地图图像的视觉平衡效果往往取决于制图者自身美学素养的高低,不具有可控性。因此,迫切需要发展泛在地图图像的视觉平衡度计算方法。现有的地图视觉平衡度计算方法存在因子不全、判别结果主观依赖性强等问题。针对这些问题,本文提出了一种结合地图图像计算特征与专家评价知识的泛在地图图像视觉平衡度计算框架。通过丰富地图视觉密度影响因子,并引入概率模型学习专家对泛在地图图像的评价知识,实现对泛在地图图像视觉平衡度复杂分布的有效判别。本文以专家问卷的方式搜集了30名地图制图专家对1730幅泛在地图图像的视觉平衡评价数据,构建了一个泛在地图图像视觉平衡度评价数据集。将计算得到的地图视觉平衡指标作为贝叶斯决策器的地图特征属性输入,将地图视觉平衡的专家评价数据作为贝叶斯决策器的分类结果,利用最小错误率贝叶斯决策方法对泛在地图图像的视觉平衡度进行判别,有效解决了人为主观判别地图视觉平衡度存在的不确定性问题。经实验验证,该框架在本文构建的泛在地图图像视觉平衡度评价数据集上能取得82.85%的评价准确率。Visual balance is one of the important factors that affect the effect of map information transmission.Due to the non-specialty of ubiquitous mapping,the visual balance of ubiquitous map images often depends on the cartographer's understanding of aesthetic quality,which can be unreliable.Therefore,it is necessary to develop a calculation method of visual balance index of ubiquitous map images.The existing methods for such purpose often fail to provide accurate and robust results due to use of incomplete factors and subjective parameter selection.To overcome such shortcomings,this paper proposes a framework to calculate the visual balance of ubiquitous map images by combining the computational features of map images and expert evaluation knowledge.It could effectively discriminate the complex distribution of visual balance index of ubiquitous map images by enriching the influence factors of visual density of the map and introducing the probabilistic model that learn expert evaluation knowledge for ubiquitous map images.To verify the proposed framework,we develop a visual balance benchmark dataset of ubiquitous map images by employing the evaluation data of 1730 ubiquitous map images from 30 cartographers by questionnaires investigation.The calculated map visual balance indexes are used as the map feature input of the Bayesian classification of visual balance,and the map evaluations are used as the classification results for model evaluation.And the rule of minimum error rate is used to optimize the performance of the classifier.Extensive experiments show that this calculation framework can achieve an accuracy of 82.85%in the evaluation dataset of visual balance index of ubiquitous map images constructed in our paper.

关 键 词：视觉平衡 泛在地图图像 地图设计 知识获取 图面配置 多因子分析 贝叶斯决策 问卷调查 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]