Image extraction device, image extraction method, and image extraction program

An image extraction device, comprising:

• at least one memory configured to store computer program code;
• at least one processor configured to access said computer program code and operate as instructed by said computer program code, said computer program code including:
• display object information acquisition code configured to cause at least one of the at least one processor to acquire position information indicating a position of a display object and display object information indicating a feature of an appearance of at least part of the display object;
• image acquisition code configured to cause at least one of the at least one processor to acquire a plurality of images photographed from a plurality of spots located within a predetermined distance of a position indicated by the acquired position information;
• detection code configured to cause at least one of the at least one processor to detect image feature information indicating a feature of an appearance of at least part of each of the acquired plurality of images;
• determination code configured to cause at least one of the at least one processor to determine a similarity degree between the acquired display object information and the detected image feature information on the each of the acquired plurality of images;
• identification code configured to cause at least one of the at least one processor to identify at least one image, among the acquired plurality of images, for which the determined similarity degree is higher than a predetermined value;
• and
• output code configured to cause at least one of the at least one processor to output at least one image including at least part, of the at least one identified image, from which the image feature information has been detected, wherein
• the image acquisition code is further configured to cause at least one of the at least one processor to acquire a plurality of low resolution images from an image storage that stores, as the plurality of images photographed from the plurality of spots, the plurality of low resolution images and a plurality of high resolution images corresponding to the plurality of respective low resolution images,
• each of the plurality of high resolution images has a resolution higher than a resolution of a corresponding low resolution image among the plurality of low resolution images,
• a scene in each of the plurality of high resolution images is the same as a scene in a corresponding low resolution image among the plurality of low resolution images,
• the detection code is further configured to cause at least one of the at least one processor to detect the image feature information indicating the feature of the appearance of at least part of each of the acquired plurality of low resolution images,
• the identification code is further configured to cause at least one of the at least one processor to identify at least one low resolution image, among the acquired plurality of low resolution images, for which the determined similarity degree is higher than the predetermined value, and acquire, from the image storage, at least one high resolution image, among the plurality of high resolution images, corresponding to the at least one identified low resolution image;
• and
• the output code is further configured to cause at least one of the at least one processor to output the at least one image including at least part, of the at least one acquired high resolution image, from which the image feature information has been detected.

An image extraction method performed by a computer, the method comprising:

• acquiring position information indicating a position of a display object and display object information indicating a feature of an appearance of at least part of the display object;
• acquiring a plurality of images photographed from a plurality of spots located within a predetermined distance of a position indicated by the acquired position information;
• detecting image feature information indicating a feature of an appearance of each of a plurality of parts of each of the acquired plurality of images;
• determining a similarity degree between the acquired display object information and the detected image feature information on the each of the acquired plurality of images;
• identifying at least one image, among the acquired plurality of images, for which the determined similarity degree is higher than a predetermined value;
• extracting a partial image from each of the at least one identified image based on position information indicating a position of a specific part among the plurality of parts of the at least one identified image, wherein the similarity degree between the acquired display object information and the image feature information detected from the specific part is higher than the predetermined value, and the partial image corresponds to the specific part;
• and
• outputting the extracted partial image.

A non-transitory computer readable medium storing thereon a computer program, the program causing a computer to:

• acquire position information indicating a position of a display object and display object information indicating a feature of an appearance of at least part of the display object;
• acquire a plurality of images photographed from a plurality of spots located within a predetermined distance of a position indicated by the acquired position information;
• detect image feature information indicating a feature of an appearance of each of a plurality of parts of each of the acquired plurality of images;
• determine a similarity degree between the acquired display object information and the detected image feature information on the each of the acquired plurality of images;
• identify at least one image, among the acquired plurality of images, for which the determined similarity degree is higher than a predetermined value;
• extract a partial image from each of the at least one identified image based on position information indicating a position of a specific part among the plurality of parts of the at least one identified image, wherein the similarity degree between the acquired display object information and the image feature information detected from the specific part is higher than the predetermined value, and the partial image corresponds to the specific part;
• and
• output the extracted partial image.