Method of learning a target object by detecting an edge from a digital model of the target object and setting sample points, and method of augmenting a virtual model on a real object implementing the target object using the learning method
A method of learning a target object by detecting an edge from a digital model of the target object and setting a sample point according to one embodiment of the present disclosure, which is performed by a computer-aided design program of an authoring computing device, includes: displaying a digital model of a target object that is a target of image recognition; detecting edges on the digital model of the target object; classifying the detected edges according to a plurality of characteristics; obtaining sample point information on the detected edges; and generating object recognition library data for recognizing a real object implementing the digital model of the target object based on the detected edges, characteristic information of the detected edges, and the sample point information.
1. A method of learning a target object by detecting an edge from a digital model of the target object and setting a sample point, which is performed by a computer-aided design program of an authoring computing device, the method comprising:
displaying the digital model of the target object that is a target of image recognition
detecting edges on the digital model of the target object;
classifying the detected edges according to a plurality of characteristics;
obtaining sample point information on the detected edges; and
generating object recognition library data for recognizing a real object implementing the digital model of the target object based on the detected edges, characteristic information of the detected edges, and the sample point information,
wherein the obtaining of the sample point information on the detected edges includes detecting a midpoint of each of the detected edges, and detecting sample points along the edges from the midpoints.
2. The method of claim 1 , wherein the classifying of the detected edges according to the plurality of characteristics includes:
classifying the detected edges into a sharp edge, a dull edge, and a flat edge based on information on angles formed by normal vectors of faces including components of the digital model of the target object.
3. The method of claim 2 , wherein an angle between the normal vectors of the faces forming the sharp edge has a first angle range,
an angle between the normal vectors of the faces forming the dull edge has a second angle range having a maximum angle smaller than a minimum angle within the first angular range,
an angle between the normal vectors of the faces forming the flat edge has a third angle range having a maximum angle smaller than a minimum angle within the second angle range.
4. The method of claim 1 , further comprising:
classifying and visualizing the detected edges according to characteristics by superimposing the detected edges on the digital model of the target object,
wherein the classifying and visualizing of the detected edges according to characteristics includes updating visualization of the detected edges on the digital model of the target object in response to a change of a position of the digital model of the target object.
5. The method of claim 4 , wherein the classifying and visualizing of the detected edges according to characteristics includes, in synchronization with a design change of a partial area of the digital model of the target object, modifying and displaying an edge on the design-changed area.
6. The method of claim 1 , further comprising:
generating augmented content, matching and storing the augmented content with the digital model of the target object.
7. A method of augmenting a virtual model to a real object implementing a target object learned by detecting edge characteristics and setting sample points, which is performed by an augmented reality program of a terminal including a camera, the method comprising:
displaying a digital model of the implemented target object that is a target of image recognition
detecting edges on the digital model of the target object;
classifying the detected edges according to a plurality of characteristics;
obtaining sample point information on the detected edges; and
generating object recognition library data for recognizing a real object implementing the digital model of the target object based on the detected edges, characteristic information of the detected edges, and the sample point information
receiving and storing the object recognition library data;
capturing an image by photographing surrounding environment;
detecting a real object that is matched with the stored object recognition library data in the captured image; and
matching and displaying augmented content to the detected real object,
wherein the obtaining of the sample point information on the detected edges includes detecting a midpoint of each of the detected edges, and detecting sample points along the edges from the midpoints.
8. The method of claim 7 , wherein the detecting of a real object matched with the stored object recognition library data in the captured image includes detecting a real object in the captured image based on characteristic information of edges detected on a digital model of the target object and a sample point of each edge.
9. The method of claim 7 , further comprising:
detecting and tracking a pose of the real object by detecting a dull edge of the real object in the captured image.