—We present a new method for the robust detection and matching of multiple planes in pairs of images. Such planes can serve as stable landmarks for vision-based urban navigation....
While video-based activity analysis and recognition has received much attention, existing body of work mostly deals with single object/person case. Coordinated multi-object activi...
Current visualization tools lack the ability to perform fullrange spatial and temporal analysis on terascale scientific datasets. Two key reasons exist for this shortcoming: I/O ...
Wesley Kendall, Markus Glatter, Jian Huang, Tom Pe...
Volunteered geographic information such as that available in blogs, wikis, social networking sites, and community contributed photo collections is enabling new applications. This ...
We recently proposed a new and efficient next-bestview algorithm for 3D reconstruction of indoor scenes using active range sensing. We overcome the computation difficulty of evalu...