Granted Patent B2

US 12,651,350 · App. 18/189,486 · Granted Jun 9, 2026

Inventors: Niko Nevatie (Helsinki, FI); Erkki Parkkulainen (Helsinki, FI)

Assignee: TGI SPORT VIRTUAL TECHNOLOGIES LIMITED

G06T7/194G06T2207/20021G06T2207/20081G06T2207/20084

Abstract

Claims (38)

1 . A computer-implemented training method for training a segmentation model to segment an image, the method comprising receiving a plurality of training data sets, the training data sets each comprising:

image data representing an image comprising a foreground and a background, the image data being captured by at least one visible electromagnetic radiation imaging device; and

sample image data comprising one or more sample image occurring in the background of the image, wherein one or more advertising boards is present in the background of the image represented by the image data, the sample image data comprising a library of images displayed on the one or more advertising boards, the library of images being updated dynamically by identifying and extracting an image displayed on the advertising board;

wherein the method comprises:

processing each training data set using the segmentation model, the processing of each training data set comprising:

supplying the sample image data to the segmentation model;

segmenting the image data to generate a candidate segmentation in dependence on the sample image data;

determining an error of the candidate segmentation; and

updating the segmentation model in dependence on the determined error.

2 . A computer-implemented training method as claimed in claim 1 , wherein the sample image data comprises a plurality of sample images, one or more of the sample images appearing in the background of the image.

3 . A computer-implemented training method as claimed in claim 1 , comprising supplying background composition data defining a composition of at least a portion of the background of the image represented by the image data.

4 . A computer-implemented training method as claimed in claim 3 , wherein the segmentation of the image by the segmentation model is performed in dependence on the background composition data.

5 . A computer-implemented training method as claimed in claim 1 , wherein the image comprises at least one background area occurring in the background of the image, the segmentation model being configured to process the image data to segment the image to determine the at least one background area.

6 . A computer-implemented training method as claimed in claim 1 , wherein the image comprises at least one mixed area occurring in the foreground and the background of the first image, the segmentation model being configured to process the image data to segment the first image to determine the at least one mixed area.

7 . A non-transitory computer-readable medium having a set of instructions stored therein which, when executed, cause a processor to perform the method claimed in claim 1 .

8 . An image segmentation system for segmenting an image, the image segmentation system comprising one or more processors; wherein the one or more processors is configured to implement a segmentation model trained according to the method claimed in claim 1 .

9 . A system for training a segmentation model to segment an image, the system comprising at least one processor and at least one memory device, the at least one processor comprising at least one input configured to receive a plurality of training data sets, the training data sets each comprising:

image data representing an image comprising a foreground and a background, the image data being captured by at least one visible electromagnetic radiation imaging device; and

sample image data comprising one or more sample image occurring in the background of the image, wherein one or more advertising boards is present in the background of the image represented by the image data, the sample image data comprising a library of images displayed on the one or more advertising boards, the library of images being updated dynamically by identifying and extracting an image displayed on the advertising board;

wherein, in respect of each of the plurality of first training data sets, the at least one processor is configured to:

process each training data set using the segmentation model, the processing of each training data set comprising:

supplying the sample image data to the segmentation model;

segmenting the image data to generate a candidate segmentation in dependence on the sample image data;

determining an error of the candidate segmentation; and

updating the segmentation model in dependence on the determined error.

10 . A system as claimed in claim 9 , wherein the sample image data comprises a plurality of sample images, one or more of the sample images appearing in the background of the image.

11 . A system as claimed in claim 9 , wherein the at least one processor is configured to receive background composition data defining a composition of at least a portion of the background of the image represented by the image data.

12 . A system as claimed in claim 11 , wherein the segmentation of the image by the segmentation model is performed in dependence on the background composition data.

13 . A system as claimed in claim 9 , wherein the image comprises at least one background area occurring in the background of the image, the segmentation model being configured to process the image data to segment the image to determine the at least one background area.

14 . A system as claimed in claim 9 , wherein the image comprises at least one mixed area occurring in the foreground and the background of the first image, the segmentation model being configured to process the image data to segment the first image to determine the at least one mixed area.

15 . An image processing system for processing an image, the image processing system comprising one or more processors having at least one electrical input for receiving:

first image data captured by at least one visible electromagnetic radiation imaging device and representing a first image comprising a foreground and a background; and

receiving sample image data comprising one or more sample image occurring in the background of the image, wherein one or more advertising boards is present in the background of the image represented by the image data, the sample image data comprising a library of images displayed on the one or more advertising boards, the library of images being updated dynamically by identifying and extracting an image displayed on the advertising board;

wherein the one or more processors is configured to implement a segmentation model; the segmentation model being configured to segment the first image to determine the foreground and the background of the first image, the segmentation model accessing the sample image data to determine the one or more sample image occurring in the background of the image.

16 . An image processing system for processing an image, the image processing system comprising one or more processors having an electrical input for receiving image data captured by at least one visible electromagnetic radiation imaging device and representing a image comprising a foreground and a background;

wherein the one or more processors is configured to implement a segmentation model trained using the computer-implemented training method claimed in claim 1 ; the segmentation model being configured to segment the image to differentiate between the foreground and the background of the image.

17 . A computer-implemented method of processing a first image, the method comprising receiving image data captured by at least one visible electromagnetic radiation imaging device and representing an image comprising a foreground and a background;

wherein the method comprises implementing a segmentation model to segment the image to differentiate between the foreground and the background of the first image, the segmentation model being trained using the computer-implemented training method claimed in claim 1 .

Assignments (2)

Priority Claims (1)

Continuity (1)

References Cited (85)