| 摘要 |
A moving object detection method is provided which can accurately perform segmentation on an image including an object such as a person that moves changing shape. The method includes: accepting pictures included in the video (S101); calculating movement trajectories by detecting motions of an image between two temporally adjoining pictures in units of blocks constituting each of the pictures and each including one or more pixels, and concatenating detected motions for all the pictures (S102 and S103); calculating distances each indicating similarity between the movement trajectories, for the calculated movement trajectories (S104); and performing segmentation by performing geodetic distance transformation by combining distances smaller than a predetermined threshold from among the calculated distances, detecting a discontinuity point in a distribution of the calculated geodetic distances, and classifying, into one cluster, movement trajectories separate from each other at a geodetic distance smaller than a length indicating the detected discontinuity point (S105 and 106). |
