Video processing system, video processing method, video processing device for mobile terminal or server and control method and control program thereof

摘要

The present invention is to notify a recognition result with respect to a recognition object in a video in real time while maintaining recognition accuracy. A recognition object and m-number of first local characteristic quantities which are respectively 1-dimensional to i-dimensional characteristic vectors are stored in association with each other, and n-number of second local characteristic quantities which are respectively 1-dimensional to j-dimensional characteristic vectors are generated for n-number of local areas respectively including n-number of characteristic points from an image in a video. In addition, a smaller dimension is selected from the dimension i and the dimension j, a recognition that the recognition object exists in an image in the video is made when it is determined that a prescribed proportion or more of the m-number of first local characteristic quantities which are characteristic vectors up to the selected number of dimensions correspond to the n-number of second local characteristic quantities which are characteristic vectors up to the selected number of dimensions, and information representing the recognition object is displayed in superposition on an image in which the recognition object exists in the video.

主权项

1. A video processing device, comprising:
a first local characteristic quantity storing unit that stores a recognition object and m-number of first local characteristic quantities which are respectively 1-dimensional to i-dimensional characteristic vectors and which are generated for each of m-number of local areas including each of m-number of characteristic points in an image of the recognition object, with the recognition object and m-number of first local characteristic quantities being associated with each other; a second local characteristic quantity generating unit that extracts n-number of characteristic points from an image in a video and that generates n-number of second local characteristic quantities which are respectively 1-dimensional to j-dimensional characteristic vectors for n-number of local areas including each of the n-number of characteristic points; a recognizing unit that selects a smaller number of dimensions among the number of dimensions i of the characteristic vectors of the first local characteristic quantities and the number of dimensions j of the characteristic vectors of the second local characteristic quantities, and recognizes that the recognition object exists in the image in the video when determining that a prescribed proportion or more of the m-number of first local characteristic quantities which are characteristic vectors up to the selected number of dimensions correspond to the n-number of second local characteristic quantities which are characteristic vectors up to the selected number of dimensions, and a displaying unit that displays information representing the recognition object recognized by the recognizing unit in an image in which the recognition object exists in the video.