Locating and augmenting object features in images
A computer-implemented method and system are described for augmenting image data of an object in an image, the method comprising receiving captured image data from a camera, storing a plurality of augmentation image data defining a respective plurality of augmentation values to be applied to the captured image data, storing a plurality of augmentation representations, each representation identifying a respective portion of augmentation image data, selecting one of said augmentation image data and one of said augmentation representations based on at least one colorization parameter, determining a portion of the augmentation image data to be applied based on the selected augmentation representation, augmenting the captured image data by applying said determined portion of the augmentation image data to the corresponding portion of the captured image data, and outputting the augmented captured image data.
1. A computer-implemented method of generating at least one augmentation representation based on respective predefined mask data identifying coordinates of a plurality of masked pixels, the method comprising the computer-implemented steps of:
receiving data of an image captured by a camera;
receiving data identifying coordinates of a plurality of labelled feature points defining a detected object in the captured image;
generating at least one augmentation representation based on respective predefined mask data identifying coordinates of a plurality of masked pixels, by:
retrieving data defining a plurality of polygonal regions of augmentation image data determined for the detected object, wherein the augmentation image data defines a plurality of augmentation values to be applied to the captured image data, and wherein each polygonal region is defined by three or more vertices, each vertex of the three or more vertices being associated with a corresponding labelled feature point;
placing the retrieved plurality of polygonal regions over the respective mask data;
identifying polygonal regions that include at least one masked pixel; and
storing data representing the identified subset of polygonal regions.
2. The method of claim 1 , further comprising:
determining a transformation of the at least one polygonal region of the representation based on the received coordinates of the corresponding feature points;
applying the determined transformation to corresponding regions of the augmentation image data defined by the at least one polygonal regions of the augmentation representation; and
augmenting the captured image data by applying the transformed at least one portion of the augmentation image data to the corresponding portion of the captured image data.
3. The method of claim 2 , wherein the augmentation image data comprises one or more of texture image data, data identifying one or more material properties, and a mathematical model to generate an array of augmentation values.
4. The method of claim 2 , wherein the augmentation image data and the captured image data have the same dimensions.
5. The method of claim 2 , wherein the augmentation image data and the captured image data have different dimensions.
6. The method of claim 2 , wherein coordinates of the vertices of the augmentation representation are defined relative to pixel locations of the augmentation image data.
7. The method of claim 2 , wherein augmenting the captured image data further comprises applying at least one image data adjustment to the transformed at least one portion of the augmentation image data.
8. The method of claim 7 , wherein the at least one image data adjustment comprises one or more of a highlight adjustment, a colour adjustment, a glitter adjustment, a lighting model adjustment, a blend colour adjustment, and an alpha blend adjustment.
9. The method of claim 7 , wherein the at least one image data adjustment comprises alpha blending said transformed masked data regions.
10. The method of claim 2 , further comprising selecting a stored augmentation image data and a stored augmentation representation based on at least one colourisation parameter.
11. The method of claim 10 , wherein a plurality of stored augmentation image data and stored augmentation representations are selected based on respective at least one colourisation parameters.
12. The method of claim 11 , wherein augmenting the captured image data comprises alpha blending the results of applying, for each selected augmentation representation in sequence, transformed at least one portions of each selected augmentation image data to the corresponding portion of the captured image data, and applying the alpha blended output to the captured image data.
13. The method of claim 1 , wherein each masked pixel comprises a value representing a blend parameter.
14. The method of claim 1 , further comprising locating the detected object in the captured image by:
storing a representation of the object, the representation including data defining a first object model and a corresponding function that approximates variations to the first object model, and data defining at least one second object model comprising a subset of the data defining the first object model, and at least one corresponding function that approximates variations to the respective second object model;
determining an approximate location of the object in the captured image, based on the first object model and its corresponding function; and
refining the location of the object in the captured image by determining a location of a portion of the object, based on the at least one second object model and its corresponding function.
15. The method of claim 14 , wherein the first object model comprises data representing locations of a plurality of feature points and the second object model comprises a subset of the feature points of the first object model.
16. The method of claim 14 , wherein the first object model defines a shape of the whole object and the at least one second object model defines a shape of a portion of the object.
17. The method of claim 14 , wherein determining the approximate location of the object in the image comprises generating a candidate object shape based on the first object model and applying the corresponding function to determine an approximate location of the candidate object shape.
18. The method of claim 17 , further comprising splitting the candidate object into one or more candidate object sub-shapes based on the at least one second object models.
19. The method of claim 18 , further comprising refining the location of the one or more candidate object sub-shapes based on the respective second object model and its corresponding function.
20. The method of claim 14 , wherein the corresponding functions comprise regression coefficient matrices.
21. The method of claim 20 , wherein the corresponding function that approximates variations to the second object model comprises a plurality of cascading regression coefficient matrices.
22. The method of claim 21 , further comprising iteratively refining the location of the one or more candidate object sub-shapes based on the respective second object model and its corresponding plurality of cascading regression coefficient matrices.
23. A system comprising one or more processors configured to perform the method of:
receiving data of an image captured by a camera;
receiving data identifying coordinates of a plurality of labelled feature points defining a detected object in the captured image; and
generating at least one augmentation representation based on respective predefined mask data identifying coordinates of a plurality of masked pixels, by:
retrieving data defining a plurality of polygonal regions of augmentation image data determined for the detected object, wherein the augmentation image data defines a plurality of augmentation values to be applied to the captured image data, and wherein each polygonal region is defined by three or more of vertices, each vertex associated with a corresponding labelled feature point;
placing the retrieved plurality of polygonal regions over the respective mask data;
identifying polygonal regions that include at least one masked pixel; and
storing data representing the identified subset of polygonal regions.
24. A non-transitory computer-readable medium comprising computer-executable instructions, that when executed perform the method of:
receiving data of an image captured by a camera;
receiving data identifying coordinates of a plurality of labelled feature points defining a detected object in the captured image; and
generating at least one augmentation representation based on respective predefined mask data identifying coordinates of a plurality of masked pixels, by:
retrieving data defining a plurality of polygonal regions of augmentation image data determined for the detected object, wherein the augmentation image data defines a plurality of augmentation values to be applied to the captured image data, and wherein each polygonal region is defined by three or more of vertices, each vertex associated with a corresponding labelled feature point;
placing the retrieved plurality of polygonal regions over the respective mask data;
identifying polygonal regions that include at least one masked pixel; and
storing data representing the identified subset of polygonal regions.