Interest point detection and scale selection in space-time.pdf

Interest point detection and scale selection in space-time.pdf

  1. 1、本文档共16页,可阅读全部内容。
  2. 2、有哪些信誉好的足球投注网站(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
  3. 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载
  4. 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
Interest point detection and scale selection in space-time

Interest point detection and scale selection in space-time Ivan Laptev and Tony Lindeberg Computational Vision and Active Perception Laboratory (CVAP) Dept. of Numerical Analysis and Computing Science KTH, S-100 44 Stockholm, Sweden Abstract. Several types of interest point detectors have been proposed for spatial images. This paper investigates how this notion can be gener- alised to the detection of interesting events in space-time data. Moreover, we develop a mechanism for spatio-temporal scale selection and detect events at scales corresponding to their extent in both space and time. To detect spatio-temporal events, we build on the idea of the Harris and Fo?rstner interest point operators and detect regions in space-time where the image structures have significant local variations in both space and time. In this way, events that correspond to curved space-time struc- tures are emphasised, while structures with locally constant motion are disregarded. To construct this operator, we start from a multi-scale windowed sec- ond moment matrix in space-time, and combine the determinant and the trace in a similar way as for the spatial Harris operator. All space- time maxima of this operator are then adapted to characteristic scales by maximising a scale-normalised space-time Laplacian operator over both spatial scales and temporal scales. The motivation for performing tem- poral scale selection as a complement to previous approaches of spatial scale selection is to be able to robustly capture spatio-temporal events of different temporal extent. It is shown that the resulting approach is truly scale invariant with respect to both spatial scales and temporal scales. The proposed concept is tested on synthetic and real image sequences. It is shown that the operator responds to distinct and stable points in space-time that often correspond to interesting events. The potential applications of the method are discussed. 1 Introduction Analysing and interpreting video is a g

文档评论(0)

l215322 + 关注
实名认证
内容提供者

该用户很懒,什么也没介绍

1亿VIP精品文档

相关文档