US-Korea Cooperative Research on Model-Based Analysis of Moving Objects for Video Tracking

美韩合作研究基于模型的视频跟踪运动物体分析

• 批准号: 0318427
• 负责人: Mongi Abidi
• 金额: --
• 依托单位: University of Tennessee Knoxville
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2003
• 资助国家: 美国
• 起止时间: 2003-08-15 至 2007-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0318427&HistoricalAwards=false
• 关键词: US; Korea; Cooperative; Research; Model

0318427AbidiThis award supports Mongi Abidi and Andreas Koschan of the University of Tennessee, together with a postdoctoral fellow and a graduate student, to establish a research collaboration in image processing with Professor Joonki Paik and his research group at the Graduate School of Advanced Imaging Science of Chung-Ang University in Seoul, Korea. Together they will build a theoretical framework for tracking one or more moving objects in two dimensions (Korean group) and in three dimensions (US group.) Their research will use multiple active video sensors and they will explore image-processing techniques to enhance input images gathered by a self-controlled specialized camera. Stabilizing input images from moving video sensors is a challenging task because of the irregular movements of the camera as well as its self-controlled mechanisms for focusing, adjusting shutter speed and iris, and gain control. Computational efficiency is the primary issue for achieving real-time video tracking on various computing platforms. The anticipated results of this work are improvements in both software and hardware used for video tracking. Important societal benefits of this research are improved video-based surveillance for security of large areas and enhanced control of robots used in hazardous situations. Broader impacts of this research include the educational value to the participating student and postdoc who will have access to complementary state-of-the-art equipment in the U.S. and Korea, while benefiting from the experience of research collaboration and establishing professional contacts in another country.

0318427 Abidi该奖项支持田纳西大学的Mongi Abidi和Andreas Koschan以及一名博士后和一名研究生与韩国首尔中央大学高级成像科学研究生院的Joonki Paik教授及其研究小组建立图像处理方面的研究合作。他们将共同建立一个理论框架，用于在二维（韩国组）和三维（美国组）中跟踪一个或多个移动物体。他们的研究将使用多个有源视频传感器，他们将探索图像处理技术，以增强由自控专用相机收集的输入图像。 稳定来自移动视频传感器的输入图像是一项具有挑战性的任务，因为相机的不规则移动以及其用于聚焦、调节快门速度和光圈以及增益控制的自控机制。 计算效率是在各种计算平台上实现实时视频跟踪的主要问题。 这项工作的预期成果是改进用于视频跟踪的软件和硬件。这项研究的重要社会效益是改进了基于视频的监控，以确保大面积的安全，并加强了对危险情况下使用的机器人的控制。 这项研究的更广泛的影响包括参与学生和博士后的教育价值，他们将获得美国和韩国最先进的设备，同时受益于研究合作的经验，并在另一个国家建立专业联系。