Automatic topology mapping processing method and system based on omnidirectional image information

1. An automatic topology mapping processing method comprising:

acquiring, by an automatic topology mapping processing system, a plurality of images, wherein at least two of the plurality of images include a common area in which a common space is captured;

extracting, by the automatic topology mapping processing system, features of the images from each of the images through a feature extractor using a neural network; and

determining, by the automatic topology mapping processing system, mapping images of the images based on the features extracted from each of the images;

wherein the determining, by the automatic topology mapping processing system, mapping images of the images based on the features extracted from each of the images comprises:

constructing a database (DB) containing vectors representing the features extracted from each of the images;

performing a vector search using a vector set that includes at least some of first vectors corresponding to first features extracted from a predetermined first image among the images from the constructed DB, wherein only the features corresponding to a predefined area in the image are input into the vector search to identify a positional relation of the plurality of images, and acquiring a closest vector set to the vector set; and

determining a second image corresponding to the closest vector set as a mapping image of the first image.

2. The method according to claim 1 , further comprising mapping the first image and the second image determined as a mapping image of the first image.

3. The method according to claim 2 , wherein the mapping the first image and the second image determined as a mapping image of the first image comprises: determining first feature-corresponding positions on the first image corresponding to the first features extracted from the first image, respectively, and second feature-corresponding positions on the second image corresponding to second features extracted from the second image, respectively; and

determining a relative positional relation between the first image and the second image based on the determined first feature-corresponding positions and the second feature-corresponding positions.

4. The method according to claim 1 , wherein the neural network is a network trained to output a transformation relation so that points corresponding to each other extracted from an overlapping common area of divided images divided from a predetermined image to have an overlapping area optimally match.

5. The method according to claim 1 , wherein the images are 360-degree images photographed at different positions in an indoor space.

6. A non-transitory computer readable medium having stored thereon software instructions that, when executed by a processor, cause the processor to generate control signals to perform the method according to claim 1 .

7. An automatic topology mapping processing system comprising:

a processor; and

a memory for storing a program implemented by the processor,

wherein:

the program acquires a plurality of images; and

at least two of the plurality of images include a common area in which a common space is captured, extracts features of the images from each of the images through a feature extractor using a neural network, and determines mapping images of the images based on the features extracted from each of the images,

wherein the program constructs a database (DB) containing vectors corresponding to the features extracted from each of the images, performs a vector search using a vector set that includes at least some of first vectors corresponding to first features extracted from a predetermined first image among the images from the constructed DB, wherein only the features corresponding to a predefined area in the image are input into the vector search to identify a positional relation of the plurality of images, and acquiring a closest vector set closest to the vector set; and

determines a second image corresponding to the closest vector set as a mapping image of the first image.

8. The system according to claim 7 , wherein the program constructs the database (DB) containing vectors corresponding to the features extracted from each of the images, performs the vector search using a vector set that is at least some of first vectors corresponding to first features extracted from the predetermined first image among the images from the constructed DB, and determines the second image extracted based on a result of the vector search as a mapping image of the first image.

9. The system according to claim 8 , wherein the program determines first feature-corresponding positions on the first image corresponding to the first features extracted from the first image, respectively, and second feature-corresponding positions on the second image corresponding to second features extracted from the second image, respectively, and determines a relative positional relation between the first image and the second image based on the determined first feature-corresponding positions and the second feature-corresponding positions.