It is easy to retrieve the small size parts from small videos. It is also easy to retrieve the middle size part from large videos. However, we have difficulties to retrieve the small size parts from large videos. We have large needs for estimating plays in sport videos. Plays in sports are described as the motions of players. This paper proposes the play retrieving method based on both motion compensation vectors and normal color frames in MPEG sports videos. This work uses the 1-dimensional degenerated descriptions of each motion image between two adjacent frames. Connecting the 1-dimensional degenerated descriptions on time direction, we have the space-time map. This spacetime map describes a sequence of frames as a 2-dimensional image. Using this space-time map on motion compensation vector frames and normal color frames, this work shows the method to create a new better template from a single template for retrieving a small number of plays in a huge number of frames. In an experiment, the resulting F-measure marks 0.955.
This paper proposes a method to estimate the directions of vertical surfaces in outdoor environments based on the
changes of the incident angle of the sunlight in a series of observation images caught with a fixed camera. This method
uses an interaction between a time when an incidence angle of the sunlight for every direction of a vertical surface is at
the minimum and a time when a brightness of every pixel in the series of observation image is at the maximum. This
method is not robust about the weather changes. This paper introduces the method integrating multi-day estimations.
With this multi-day integration, the proposed direction estimation method is robust about the weather changes. And then,
this paper shows experiments on real out-door images.