专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08184913B2 Clustering videos by location 有权
标题翻译：按位置分组视频
公开(公告)号：US08184913B2
公开(公告)日：2012-05-22
申请号：US12416152
申请日：2009-04-01
申请人： Simon J. Baker , Charles Lawrence Zitnick, III , Gerhard Florian Schroff
发明人： Simon J. Baker , Charles Lawrence Zitnick, III , Gerhard Florian Schroff
IPC分类号： G06K9/68
CPC分类号： G06K9/00718 , G06F17/30781 , G06F17/3082 , G06K9/6219 , Y02D10/45
摘要： Described is a technology in which video shots are clustered based upon the location at which the shots were captured. A global energy function is optimized, including a first term that computes clusters so as to be reasonably dense and well connected, to match the possible shots that are captured at a location, e.g., based on similarity scores between pairs of shots. A second term is a temporal prior that encourages subsequent shots to be placed in the same cluster. The shots may be represented as nodes of a minimum spanning tree having edges with weights that are based on the similarity score between the shots represented by their respective nodes. Agglomerative clustering is performed by selecting pairs of available clusters, merging the pairs and keeping the pair with the lowest cost. Clusters are iteratively merged until a stopping criterion or criteria is met (e.g., only a single cluster remains).
摘要翻译：描述了一种基于拍摄拍摄位置来进行视频拍摄的技术。优化了全局能量函数，包括计算集群以便相当密集和良好连接的第一项，以匹配在某个位置捕获的可能的拍摄，例如，基于拍摄对之间的相似性得分。第二个术语是时间先前，鼓励后续的镜头被放置在同一个集群中。拍摄可以被表示为具有基于由它们各自的节点表示的拍摄之间的相似性得分的权重的边缘的最小生成树的节点。通过选择成对的可用集群，合并对并保持成本最低的组合来执行集群聚类。集群被迭代合并，直到满足停止标准或条件（例如，仅剩下一个集群）。

2. 发明申请

US20100254614A1 CLUSTERING VIDEOS BY LOCATION 有权
标题翻译：按地点分组视频
公开(公告)号：US20100254614A1
公开(公告)日：2010-10-07
申请号：US12416152
申请日：2009-04-01
申请人： Simon J. Baker , Charles Lawrence Zitnick, III , Gerhard Florian Schroff
发明人： Simon J. Baker , Charles Lawrence Zitnick, III , Gerhard Florian Schroff
IPC分类号： G06K9/68
CPC分类号： G06K9/00718 , G06F17/30781 , G06F17/3082 , G06K9/6219 , Y02D10/45
摘要： Described is a technology in which video shots are clustered based upon the location at which the shots were captured. A global energy function is optimized, including a first term that computes clusters so as to be reasonably dense and well connected, to match the possible shots that are captured at a location, e.g., based on similarity scores between pairs of shots. A second term is a temporal prior that encourages subsequent shots to be placed in the same cluster. The shots may be represented as nodes of a minimum spanning tree having edges with weights that are based on the similarity score between the shots represented by their respective nodes. Agglomerative clustering is performed by selecting pairs of available clusters, merging the pairs and keeping the pair with the lowest cost. Clusters are iteratively merged until a stopping criterion or criteria is met (e.g., only a single cluster remains).
摘要翻译：描述了一种基于拍摄拍摄位置来进行视频拍摄的技术。优化了全局能量函数，包括计算集群以便相当密集和良好连接的第一项，以匹配在某个位置捕获的可能的拍摄，例如，基于拍摄对之间的相似性得分。第二个术语是时间先前，鼓励后续的镜头被放置在同一个集群中。拍摄可以被表示为具有基于由它们各自的节点表示的拍摄之间的相似性得分的权重的边缘的最小生成树的节点。通过选择成对的可用集群，合并对并保持成本最低的组合来执行集群聚类。集群被迭代合并，直到满足停止标准或条件（例如，仅剩下一个集群）。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式