POWRE: Integration of Human Perception into a Robust On-Line Vision System Designed to Assess Surface Appearance

这项研究的目标是开发一种低成本、健壮、自动化的在线监控系统，该系统部分地根据感知的表面外观来控制涂装过程。该计划将侧重于以下目标：确定将人的感知整合到视觉系统中的有效方法；使用反射模型作为合理基础的硬件和软件设计；研究最佳图像属性和处理技术，以利用该视觉系统和感知的表面外观之间的联系；以及在视觉系统软件中开发专家系统的原型，以便于基于捕获的图像数据对表面质量进行评估。该项目采用了四管齐下的方法，包括小规模实验、模拟、原型测试和现场测试，与现有方法并行。这项工作将扩大小规模的设置，并使用模拟来开发一种方法，用于捕获图像并获得和分析系统软件和生产线操作员都容易解释的派生属性。该研究将为更稳健的方法提供方向，以表征、监测和控制表面质量。该项目的教育计划包括针对不同人群的协作、实践研究经验和指导，以及增强首席研究员建立和维持具有竞争力的研究项目的能力，以吸引准备充分的、多样化的学生群体。

The goal of this research is to develop a low-cost, robust, automated on-line monitoring system, which controls the painting process based, in part, upon perceived surface appearance. This program will focus on the following objectives: determination of an efficient way to integrate human perception into a vision system hardware and software design which uses reflectance models as a rational basis; an investigation of the best image attributes and processing techniques to exploit the link between this vision system and perceived surface appearance; and prototype development of an expert system within the vision system software which facilitates as assessment of surface quality based on captured image data. The project utilizes a four-prong approach, which includes small-scale experiments, simulation, prototype testing and on-site testing in parallel with existing methods. This effort will expand the small-scale setup and use simulation to develop a methodology for capturing images and obtaining and analyzing derived attributes which are readily interpreted by both system software and line operators.This research should provide direction to a more robust method to characterize, monitor and control surface quality. The educational plan for the program includes collaborative, hands-on research experiences and mentoring for a diverse population, and enhancement of the principal investigator's ability to build and maintain a competitive research program, which attracts a well-prepared, diverse group of students.