Entity visualization method
The invention relates to the field of information technologies and computer technology, and specifically to the processing and generation of image data, and to the processing of images for computer graphics. An entity visualization method consists in capturing a digital image, receiving units of additional information from an electronic memory which stores a plurality of units of additional information, and displaying at least one unit of the plurality of additional information units, superimposing same onto the digital image; the electronic memory also stores data related to representations of corresponding entities; in each captured image frame, at least one entity is detected and recognized using the entity representation data received from electronic memory; computing the coordinates of the detected entity on the captured image, and displaying at least one unit of additional information in direct proximity to the corresponding entity on the captured image, which is output to a display.
1. A method for visualizing of an object at a visualizer device, comprising a camera, an electronic memory and a screen, said method comprising:
capturing a digital image of the object by the camera, forming a captured digital image,
acquiring additional information elements from the electronic memory, said electronic memory adapted to stores image data of a plurality of predetermined objects and a plurality of additional information elements, wherein each said additional information element corresponds to one of said plurality of predetermined objects,
displaying on the screen at least one of the plurality of additional information elements while superimposing them on the digital image,
detecting at least one detected object in each selected frame of the captured digital image,
recognizing the detected object by identifying a corresponding predetermined object from the plurality of predetermined objects;
using image data of the corresponding predetermined object obtained from the electronic memory,
calculating coordinates of the detected object on the captured digital image,
retrieving from the electronic memory and displaying at least one additional information element of the corresponding predetermined object in an immediate vicinity of a recognized object on the displayed captured digital image,
if the object detected and recognized on previously selected frames is no longer being detected on subsequently selected frames for a predetermined time, concluding that there is no object on the captured digital image and stopping output of the at least one additional information element associated with the recognized object.
2. The method according to claim 1 , characterized in that the step of object recognizing is performed on basis of its shape and/or its color and/or its texture.
3. The method according to claim 1 , characterized in that the selected frame of the captured digital image on which the object is detected and recognized comprising each n-th frame of a video image, wherein n is a natural number of 1, 2, 3, 4 . . ., or each frame formed by the time the computing means are ready to detect and recognize an object on it.
4. The method according to claim 1 , characterized in that image data of the object includes at least common features and special features, while the detection and recognition of objects performed in the following sequence: detecting the object on the selected frame using the common features, calculating the coordinates of the detected object on the selected frame using the special features, performing recognition of the object in the selected frame of the captured digital image.
5. The method according to claim 1 , characterized in that expected coordinates of the object in a next frame are calculated based on the object's coordinates in a previous frames, and limiting an area of recognition of the object on the next frame by a set of expected object coordinates, wherein if recognition time in] the subsequently selected frames will exceed a pre-set threshold value, then further detection is performed on an entire selected frame.
6. The method according to claim 1 , characterized in that an area of the detected and recognized object is marked on the screen when the captured digital image is displayed.
7. The method according to claim 1 , characterized in that the recognized object is marked by highlighting a portion of the captured digital image containing the object.
8. The method according to claim 1 , characterized in that the captured digital image forming and storing in the electronic memory is performed in advance.