Image recoginition device, image recognition method, and image recognition program
An image recognition device includes an image acquiring unit configured to acquire an image, and an object recognition unit configured to extract feature points from the image acquired by the image acquiring unit, to detect coordinates of the extracted feature points in a three-dimensional spatial coordinate system, and to determine a raster scan region which is used to recognize a target object based on the detection result.
1. An image recognition device comprising:
an image acquirer configured to acquire an image; and
an object recognizer configured to extract a plurality of feature points from the image acquired by the image acquirer, to detect coordinates of the plurality of extracted feature points in a three-dimensional spatial coordinate system, and to determine a raster scan region which is used to recognize a target object based on the coordinates of the extracted feature points; wherein
the object recognizer is further configured to create the raster scan region based on at least information on distances between the image acquirer and the plurality of extracted feature points using the coordinates thereof;
the object recognizer is configured to create the raster scan region based on information on positions of the plurality of extracted feature points other than the distances between the image acquirer and the plurality of extracted feature points, the information on positions of the plurality of extracted feature points being calculated using the coordinates;
the object recognizer is configured to refer to a difference between the information of positions of the two or more preliminary windows and a difference between sizes of the two or more preliminary windows, and to consolidate the two or more preliminary windows to generate the raster scan region using a predetermined conditional expression; and
the object recognizer is configured to set sizes of the preliminary windows based on the information on the distances, to set the positions of the preliminary windows based on the information on the positions other than the distances of the extracted feature points, and to consolidate the preliminary windows of which the sizes and the positions have been set using the predetermined conditional expression.