| 摘要 |
<p>Methods and systems for luggage visualization perform virtual unpacking by visually moving an object image away from its original pose. A scanned 3D volume is segmented guided by a confidence measure to create a label volume whose voxels specify the detected object IDs. The luggage dataset and the label volume are visualized by volume rendering. Using an automatic coloring algorithm, any pair of objects whose projections are adjacent in an image are assigned distinct hues. A layered framework efficiently renders a scene mixed with packed luggage, animated unpacking objects, and already unpacked objects put aside for further inspection. A GPU is used to automatically select objects that are not blocked by others and can be unpacked.</p> |
