Constant density displays using diversity sampling

The Informedia Digital Video Library user interface summarizes query results with a collage of representative keyframes. We present a user study in which keyframe occlusion caused difficulties. To use the screen space most efficiently to display images, both occlusion and wasted whitespace should be minimized. Thus optimal choices will tend toward constant density displays. However, previous constant density algorithms are based on global density, which leads to occlusion and empty space if the density is not uniform. We introduce an algorithm that considers the layout of individual objects and avoids occlusion altogether. Efficiency concerns are important for dynamic summaries of the Informedia Digital Video Library, which has hundreds of thousands of shots. Posting multiple queries that take into account parameters of the visualization as well as the original query reduces the amount of work required. This greedy algorithm is then compared to an optimal one. The approach is also applicable to visualizations containing complex graphical objects other than images, such as text, icons, or trees.