REU Site: Research Experience for Undergraduates in Computer Vision

这个项目是计算机视觉本科生研究体验网站的延续，该网站在过去21年里一直在中佛罗里达大学成功运营。多年来，来自全国各地43所院校的约210名本科生参加了这一项目。研究的重点领域是计算机视觉。目前的提议是每年有10名参与者，为期三年。每年，学生将参加为期12周的全日制暑期课程。根据前几年的经验教训，拟议的模式包括由一个团队全天候指导，该团队包括一名教授和一名博士后研究员或研究生；一个精简的短期课程，让参与者更早开始他们的研究项目；每天与导师会面，计划全天的活动。参与者参加短期课程，将自己与他们最渴望的项目主题相匹配，并花费足够的时间进行重点研究。然后，他们可以选择在一年内与教授合作，就他们的项目撰写一份技术报告，为GRE做准备，并申请研究生项目。在过去的几年里，我们的REU参与者中有相当一部分人能够准备一篇提交给裁判会议的论文，该论文被接受，然后参加会议提交论文。该网站由国防部与NSF REU计划共同资助。智力优势：开发新的算法来解决学习场景模型、超分辨率增强、目标检测、跟踪、活动和事件识别方面的科学问题。理论和实践都涉及对困难视觉问题的数学建模和分析以及开发算法，同时构建在现实生活中演示这些解决方案的真实系统。更广泛的影响：该项目将有助于培养一支年轻科学家的工作队伍，以保持美国以前在科学和工程领域占据的战略指挥地位。学员将接受计算机视觉方面的培训，特别是学习图像科学和视觉的基础知识，这些知识在安全/监控、游戏、娱乐、医疗保健、国防和制造业中发挥着重要作用。通过这个项目，我们将能够为不同的本科生群体提供机会，其中许多人来自以本科为主的机构，与一个非常成功的研究小组度过一个夏天。REU的这一模式将在其他学校中传播。

This project is a continuation of a Research Experience for Undergraduates site in Computer Vision which has operated successfully at the University of Central Florida for the past twenty-one years. Approximately two hundred and ten undergraduate students from forty-three institutions all over the country have participated in this program over the years. The research focus area is Computer Vision. The current proposal is to have 10 participants per year, for three years. Each year, students will participate in a 12-week duration full-time Summer program. From lessons learned in prior years, the proposed model includes round-the-clock mentoring by a team that includes a professor, and a post-doctoral fellow or a graduate student; a streamlined short course that lets participants start their research projects sooner; and daily meetings with mentors to plan activities throughout the day. Participants take the short course, match themselves to a project topic that they most desire, and spend sufficient time in focused research. They then can opt for follow-through over the year by working with the professors to write a technical report on their project, to prepare for the GREs and to apply to graduate programs. In past years, a substantial fraction of our REU participants have been able to prepare a paper for submission to a refereed conference, have the paper accepted and then attend the conference to present the paper. The site is Co-funded by the Department of Defense in partnership with the NSF REU program. Intellectual Merit:Development of new algorithms for solving scientific problems in learning scene models, super-resolution enhancement, object detection, tracking, activity and event recognition. Both theory and practice is involved with an interest in mathematical modeling and analysis of difficult vision problems and developing algorithms, while at the same time building real systems for demonstrating those solutions in real life situations. Broader Impacts:The project will contribute to preparing a work force of young scientists in order to maintain America's previously-held strategic position of command in Science and Engineering. Participants will be trained in Computer Vision, in particular they will learn fundamentals of image science and vision, which plays an important role in security/surveillance, gaming, entertainment, healthcare, defense, and manufacturing. Through this project we will able to provide opportunities to a diverse group of undergraduates, many from predominantly undergraduate institutions, to spend a summer with a highly successful research group. This model for REU will be disseminated among other Schools.