US12687376 - Method, computer program, and device for identifying hit location of dart pin
The patent describes a computer program that identifies the hit location of a dart pin by processing images captured by multiple cameras positioned around a dartboard. It involves merging these images to create a single input for a location identification model, which then determines the precise location of the dart pin on the target.
Claim 1
1 . A computer program stored in a computer-readable storage medium, the computer program providing a dart pin hit location identification method when being executed by one or more control units of a dart game device including at least two cameras, each positioned in a predetermined direction, the method comprising: obtaining at least two dart target photographing images in response to a dart pin throw, wherein the dart target photographing image includes an image of a dart target and at least one dart pin hitting the dart target, and the at least two dart target photographing images are generated by at least two cameras, each positioned in the predetermined direction; and generating, by a dart pin location identification network model, hit location information of the at least one dart pin based on the at least two dart target photographing images, wherein the generating of the hit location information of the dart pin based on the at least two dart target photographing images includes: generating input data that is a single image by performing a merging operation on the at least two dart target photographing images, wherein the merging operation comprises (i) obtaining a bounding box image for each of the at least two dart target photographing images, and (ii) merging the bounding box images to create the single image; and generating the hit location information of the at least one dart pin by processing the input data by the dart pin location identification network model. obtaining at least two dart target photographing images in response to a dart pin throw, wherein the dart target photographing image includes an image of a dart target and at least one dart pin hitting the dart target, and the at least two dart target photographing images are generated by at least two cameras, each positioned in the predetermined direction; and generating, by a dart pin location identification network model, hit location information of the at least one dart pin based on the at least two dart target photographing images, wherein the generating of the hit location information of the dart pin based on the at least two dart target photographing images includes: generating input data that is a single image by performing a merging operation on the at least two dart target photographing images, wherein the merging operation comprises (i) obtaining a bounding box image for each of the at least two dart target photographing images, and (ii) merging the bounding box images to create the single image; and generating the hit location information of the at least one dart pin by processing the input data by the dart pin location identification network model.
Google Patents
https://patents.google.com/patent/US12687376
USPTO PDF
https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/12687376