摘要
为了弥补主观性评价方法的不足,以获得用户对于汽车造型设计的客观性评价,提出了一种基于眼动跟踪特征的汽车造型评价方法。以眼动热点图为基础构建车型评价指标体系,包括对热点图进行背景剥离,通过"色度-饱和度-亮度(HSV)"模型提取其颜色特征,并计算其灰度直方图的各项统计值;进一步将汽车造型的评价定义为二分类问题,运用Fisher判别建立函数模型。通过实例验证了该方法的可靠性与实用性。结果表明:该方法总体上具有较高准确度,为实现汽车造型评价提供了一种可行的技术途径。
Traditional subjective evaluation methods have limited success for automotive designs.An automobile style evaluation method based on eye tracking is developed to more accurately recognize the users'objective assessment of the automotive form design.An index system is structured based on a heat map including striping the background,extracting the color characteristics using a hue-saturationvalue(HSV)model and calculating the statistics of the grey level histogram.The automobile form evaluation is defined as a binary classification model with the function model built from a Fisher discriminate.The reliability and practicality of this method are validated using a test case.The results show that this method is accurate and a feasible technical approach for rapid evaluation of automotive styling.
出处
《清华大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
2015年第7期775-781,共7页
Journal of Tsinghua University(Science and Technology)
基金
国家自然科学基金项目(51205228,51505251)
中国博士后科学基金项目(2014M560955)
安徽省自然科学基金项目(1508085QG144)
安徽高校省级优秀青年人才基金重点项目(2013SQRL078ZD)
合肥学院人才基金项目(2014rc16)
关键词
汽车造型
评价方法
眼动跟踪技术
特征提取
判别函数
auto form
evaluation method
eye tracking
feature extraction
discriminate function