Finding and Tracking People from the Bottom Up

自下而上查找和跟踪人员

• 批准号: 0098682
• 负责人: David Forsyth
• 金额: $ 25万
• 依托单位: University of California-Berkeley
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2001
• 资助国家: 美国
• 起止时间: 2001-09-01 至 2005-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0098682&HistoricalAwards=false
• 关键词: Finding; Tracking; People; Bottom; Up

The project addresses the issues of vision tracking, in particular the consecutive use of hypotheses generated by tracking methods to yield better results in tracking. The proposed approach is likely to be expendable to various tasks, such as finding clothed people in images. Overall the approach promises a powerful technique for building an accurate self-initializing tracker.

该项目解决了视觉跟踪问题，特别是连续使用跟踪方法产生的假设，以产生更好的跟踪结果。所提出的方法很可能是可消耗的各种任务，如寻找穿着的人的图像。总的来说，该方法有望为构建一个准确的自初始化跟踪器提供一个强大的技术。