Nonseparable Multiclass Learning for Object Tracking

用于对象跟踪的不可分离多类学习

• 批准号: 0354881
• 负责人: Xiaotong Shen
• 金额: --
• 依托单位: University of Minnesota-Twin Cities
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2003
• 资助国家: 美国
• 起止时间: 2003-10-01 至 2007-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0354881&HistoricalAwards=false
• 关键词: Nonseparable; Multiclass; Learning; Object; Tracking

Robotics and Computer Vision ProgramABSTRACTProposal #: 0328802Title: Nonseparable Multiclass Learning for Object TrackingPI: Shen, XiaotongOhio State Univ Res FdnObject tracking is an important technology of image and video processing for many applications, including vision-guided automation, automatic target identification, object-based video compression, and face recognition. A fundamental tool that underlies the technology of object tracking is machine classification. Recent developments of binary psi-learning allow us to further achieve higher generalization accuracy for nonseparable and multiclass cases. This proposal presents an interdisciplinary research plan to address the problem of multiple object-tracking via this new learning tool. The project will investigate how the accuracy of psi-learning can be maximized by studying its generalization ability as well as methods for assessment. Specific desired outcomes of the project are (a) creation of a stable foundation for psi-learning and further development of learning theory, optimization theory, and algorithms, and (b) specific development of mechanisms for object tracking and extraction in multimedia compression.The proposed project is expected to have broad impacts to education, research, economy, and society at large. In particular, the technology developed in this project is widely applicable to scientific and engineering frontiers, including face-recognition, target identification, and cancer genomics classification. Plans for technology transfer are proposed to benefit the economy. The proposed educational program will train students in an interdisciplinary area of statistics and electrical engineering. Success of this project will bring tremendous benefits to fundamental scientific research, high-performance computing, and information technology, and have significant broad impacts to society at large.

机器人学和计算机视觉项目摘要提案编号：0328802标题：用于对象跟踪的不可分离多类学习PI：Shen，Xiaotong俄亥俄州立大学研究Fdn对象跟踪是许多应用的图像和视频处理的重要技术，包括视觉引导自动化、自动目标识别、基于对象的视频压缩和人脸识别。 对象跟踪技术的一个基本工具是机器分类。二元 psi 学习的最新发展使我们能够进一步实现不可分离和多类情况的更高泛化精度。该提案提出了一项跨学科研究计划，旨在通过这种新的学习工具解决多个对象跟踪问题。 该项目将研究如何通过研究 psi-learning 的泛化能力和评估方法来最大限度地提高 psi-learning 的准确性。 该项目的具体预期成果是（a）为 psi 学习奠定稳定的基础，并进一步发展学习理论、优化理论和算法，以及（b）多媒体压缩中对象跟踪和提取机制的具体开发。该项目预计将对教育、研究、经济和整个社会产生广泛影响。特别是，该项目开发的技术广泛适用于科学和工程前沿，包括人脸识别、目标识别和癌症基因组学分类。提出技术转让计划以造福经济。 拟议的教育计划将对统计和电气工程跨学科领域的学生进行培训。该项目的成功将为基础科学研究、高性能计算和信息技术带来巨大效益，对社会产生重大广泛影响。