Identifying an object in an image using color profiles
View Patent ↗A representation of an object in an image of a live event is obtained by determining a color profile of the object. The color profile may be determined from the image in real time and compared to stored color profiles to determine a best match. For example, the color profile of the representation of the object can be obtained by classifying color data of the representation of the object into different bins of a color space, in a histogram of color data. The stored color profiles may be indexed to object identifiers, object viewpoints, or object orientations. Color data which is common to different objects or to a background color may be excluded. Further, a template can be used as an additional aid in identifying the representation of the object. The template can include, e.g., a model of the object or pixel data of the object from a prior image.
1. A computer-implemented method for processing image data, comprising the computer-implemented steps of:
obtaining at least one image of a vehicle in a live event as the vehicle traverses a track, the at least one image is captured by at least one camera;
determining an orientation of the vehicle based on a location of the vehicle along the track and a model of the track, the orientation comprises at least one of: (i) a heading of the vehicle, the heading is a direction of the track at the location (ii) a roll angle of the vehicle, the roll angle is a bank angle of the track at the location or (iii) a pitch angle of the vehicle, the pitch angle is a pitch of the track at the location;
determining a color profile of a representation of the vehicle in the at least one image;
retrieving color profiles which are mapped to the orientation, from among color profiles which are stored indexed to different vehicle orientations;
performing a matching process to determine a best match to the color profile of the representation of the vehicle in the at least one image, among the color profiles which are mapped to the orientation; and
identifying the representation of the vehicle in the at least one image based, at least in part, on the best match.
2. The computer-implemented method of claim 1 , wherein:
the color profiles are stored indexed to different vehicle identifiers.
3. The computer-implemented method of claim 1 , wherein:
the color profile of the representation of the vehicle is obtained by classifying color data of the representation of the vehicle into different bins for different color components of a multi-component color space, and by classifying the different bins for the different color components into different bins for the multi-component color space.
4. The computer-implemented method of claim 1 , wherein:
the best match is determined from among color profiles which exclude at least some color data which is common to different vehicles.
5. The computer-implemented method of claim 1 , further comprising:
updating at least one of registration data or sensor data of the at least one camera based on a position of the representation of the vehicle in the at least one image.
6. The computer-implemented method of claim 1 , wherein:
the color profiles mapped to the orientation comprise a 3d model of a shape of the vehicle.
7. The computer-implemented method of claim 1 , wherein:
the color profiles mapped to the orientation comprise pixel data of the vehicle from at least one prior image.
8. A system for processing image data, comprising:
at least one camera for capturing at least one an image of a live event, the live event including a vehicle traversing a track; and
at least one processing facility which receives the at least one image, the at least one processing facility: determines an orientation of the vehicle based on a location of the vehicle along the track and a model of the track, the orientation comprises at least one of: (i) a heading of the vehicle, the heading is a direction of the track at the location, (ii) a roll angle of the vehicle, the roll angle is a bank angle of the track at the location or (iii) a pitch angle of the vehicle, the pitch angle is a pitch of the track at the location, determines a color profile of a representation of the vehicle in the at least one image, retrieves color profiles which are mapped to the orientation, from among color profiles which are stored indexed to different vehicle orientations, performs a matching process to determine a best match to the color profile of the representation of the vehicle in the at least one image among the color profiles which are mapped to the orientation, and identifies the representation of the vehicle in the at least one image based, at least in part, on the best match.
9. At least one non-transitory processor readable storage device having processor readable code embodied thereon for programming at least one processor to perform a method, the method comprising:
obtaining at least one image of a vehicle in a live event as the vehicle traverses a track, the at least one image is captured by at least one camera;
determining an orientation of the vehicle based on a location of the vehicle along the track and a model of the track, the orientation comprises at least one of: (i) a heading of the vehicle, the heading is a direction of the track at the location, (ii) a roll angle of the vehicle, the roll angle is a bank angle of the track at the location or (iii) a pitch angle of the vehicle, the pitch angle is a pitch of the track at the location;
determining a color profile of a representation of the vehicle in the at least one image;
retrieving color profiles which are mapped to the orientation, from among color profiles which are stored indexed to different vehicle orientations;
performing a matching process to determine a best match to the color profile of the representation of the vehicle in the at least one image, among the color profiles which are mapped to the orientation; and
identifying the representation of the vehicle in the at least one image based, at least in part, on the best match.
10. The at least one non-transitory processor readable storage device of claim 9 , wherein the method performed further comprises:
updating at least one of sensor data or registration data of the at least one camera based on at least one a position of the representation of the first vehicle in the at least one image.
11. The at least one non-transitory processor readable storage device of claim 9 , wherein:
the color profile of the representation of the vehicle is obtained by classifying color data of the representation of the vehicle into different bins for different color components of a multi-component color space, and by classifying the different bins for the different color components into different bins for the multi-component color space.
12. The computer-implemented method of claim 1 , wherein:
the color profiles which are mapped to the orientation are obtained from prior images of the vehicle, the prior images of the vehicle comprise pixels in rectangles, the rectangles bound the vehicle, and a known background color in the rectangles is removed before creating the color profiles.
13. The computer-implemented method of claim 12 , wherein:
the prior images are of the vehicle on the track; and
the known background color comprises a color of the track.
14. The computer-implemented method of claim 1 , wherein:
the color profiles which are mapped to the orientation are obtained from prior images of the vehicle in an earlier traversal of the track.
15. The computer-implemented method of claim 1 , wherein:
the color profiles which are mapped to the orientation are obtained from information regarding a paint scheme of the vehicle.
16. The computer-implemented method of claim 1 , wherein:
the orientation is determined based on sensor data of the at least one camera.
17. The computer-implemented method of claim 1 , wherein:
the orientation is determined based on inertial measurement unit IMU data from an IMU carried on board the vehicle, the IMU data comprises at least one of roll, pitch or heading.
18. The computer-implemented method of claim 1 , wherein:
the color profiles account for camera settings of the at least one camera.
19. The computer-implemented method of claim 1 , wherein:
the orientation is an orientation relative to the at least one camera.
20. The system of claim 8 , wherein:
the color profiles are stored indexed to different vehicle identifiers.
21. The system of claim 8 , wherein:
the at least one processing facility, to obtain the color profile of the representation of the vehicle, classifies color data of the representation of the vehicle into different bins for different color components of a multi-component color space, and classifies the different bins for the different color components into different bins for the multi-component color space.
22. The system of claim 8 , wherein:
the color profiles mapped to the orientation comprise a 3d model of a shape of the vehicle.
23. The system of claim 8 , wherein:
the at least one processing facility, to determine the color profile of the representation of the vehicle in the at least one image, provides a mask based on a 3d model of a shape of the vehicle and based on a position of the vehicle in the live event, and uses the mask to avoid background colors in the at least one image.
24. The at least one non-transitory processor readable storage device of claim 9 , wherein:
the color profiles mapped to the orientation comprise a 3d model of a shape of the vehicle.