Methods and systems for multiplayer tagging using artificial intelligence

1. A method for image clustering, comprising:

receiving a plurality of images from a video of a game;

determining a first feature vector of a first player from the plurality of images by inputting the plurality of images to an artificial intelligence (AI)-based process;

determining a location information associated with the first player using a pose-estimation technique;

dividing the plurality of images into a first subset of images and a second subset of images based on the first feature vector;

receiving a first identifier tagging the first player in a first image of the first subset; and

identifying a second player in a second image in the second subset by propagating the first identifier of the first subset, based on a distance measure associated with the first feature vector from the AI-based process, wherein the AI-based process is based on the location information.

2. The method of claim 1 , wherein the determination of the first feature vector further comprises:

performing pose estimation on the plurality of images in order to determine one or more colors associated with pixels of the first player in the plurality of images.

3. The method of claim 1 , wherein the AI-based process comprises a person re-identification technique.

4. The method of claim 1 , wherein the AI-based process is selected from the group consisting of a deep neural network, a Siamese/triplet-loss neural network, and a direct low-level image feature extraction technique.

5. The method of claim 1 , wherein the location information is further determined using at least one of an image-segmentation technique and an object-detection technique.

6. The method of claim 1 , wherein the first identifier tagging the first player in the first image is determined based on a clustering process, the clustering process including at least one of a k-means, an affinity propagation, and a density-based spatial clustering of applications with noise (DBSCAN).

7. The method of claim 1 , wherein the propagating the first identifier of the first subset comprises propagating the first identifier of the first subset using a clustering process.

8. The method of claim 1 , wherein the dividing the plurality of images into the first subset of images and the second subset of images further comprises:

determining the first subset of images based on a second feature vector determined from a second plurality of images selected from the first plurality of images.

9. A non-transitory computer-readable medium storing computer-executable instructions which, when executed by a processor, cause the processor to perform operations for image clustering, comprising computer-executable instructions to:

receive a plurality of images from a video of a game;

determine a first feature vector of a first player from the plurality of images by inputting the plurality of images to an artificial intelligence (AI)-based process;

determine a location information associated with the first player using a pose-estimation technique;

divide the plurality of images into a first subset of images and a second subset of images based on the first feature vector;

receive a first identifier tagging the first player in a first image of the first subset; and

identify a second player in a second image in the second subset by propagating the first identifier of the first subset, based on a distance measure associated with the first feature vector from the AI-based process, wherein the AI-based process is based on the location information.

10. The non-transitory computer-readable medium of claim 9 , wherein the computer-executable instructions to determine the first feature vector further comprise computer-executable instructions to:

perform pose estimation on the plurality of images in order to determine one or more colors associated with pixels of the first player in the plurality of images.

11. The non-transitory computer-readable medium of claim 9 , wherein the AI-based process comprises a person re-identification technique.

12. The non-transitory computer-readable medium of claim 9 , wherein the AI-based process is selected from the group consisting of a deep neural network, a Siamese/triplet-loss neural network, and a direct low-level image feature extraction technique.

13. The non-transitory computer-readable medium of claim 9 , wherein the location information is further determined using at least one of an image-segmentation technique and an object-detection technique.

14. The non-transitory computer-readable medium of claim 9 , wherein the computer-executable instructions to receive the first identifier tagging the first player in the first image is determined based on a clustering process, the clustering process including at least one of a k-means, an affinity propagation, or a density-based spatial clustering of applications with noise (DBSCAN).

15. The non-transitory computer-readable medium of claim 9 , wherein the propagating the first identifier of the first subset comprises propagating the first identifier of the first subset using a clustering process.

16. The non-transitory computer-readable medium of claim 9 , wherein the computer-executable instructions to divide the plurality of images into the first subset of images and the second subset of images further comprises computer-executable instructions to:

determine the first subset of images based on a second feature vector determined from a second plurality of images selected from the first plurality of images.

17. A device for image clustering, comprising:

at least one memory device that stores computer-executable instructions; and

at least one processor configured to access the at least one memory device, wherein the at least one processor is configured to execute the computer-executable instructions to:

receive a plurality of images from a video of a game;

determine a first feature vector of a first player from the plurality of images by inputting the plurality of images to an artificial intelligence (AI)-based process;

determine a location information associated with the first player using a pose-estimation technique;

divide the plurality of images into a first subset of images and a second subset of images based on the first feature vector;

receive a first identifier tagging the first player in a first image of the first subset; and

identify a second player in a second image in the second subset by propagating the first identifier of the first subset, based on a distance measure associated with the first feature vector from the AI-based process, wherein the AI-based process is based on the location information.

18. The device of claim 17 , wherein the computer-executable instructions to determine the first feature vector further comprise computer-executable instructions to:

perform pose estimation on the plurality of images in order to determine one or more colors associated with pixels of the first player in the plurality of images.

19. The device of claim 17 , wherein the AI-based process comprises a person re-identification technique.

20. The device of claim 17 , wherein the AI-based process is selected from the group consisting of a deep neural network, a Siamese/triplet-loss neural network, and a direct low-level image feature extraction technique.