Ground control point center determination
Methods, systems and apparatus, including computer programs encoded on computer storage media for determining a center location of a ground control point used in aerial surveys. Machine learning models are used to identify in digital images pixel coordinates of the ground control point identified in the digital images. These image pixel coordinates are used in photogrammetric processing and software.
1. A computing apparatus comprising:
one or more computer-readable storage media; and
program instructions stored on the one or more computer-readable storage media that, when executed by one or more processors, direct an aerial vehicle to a least:
segment digital images obtained by the aerial vehicle into one or more groups corresponding to one or more ground control point depicted in the digital images;
identify a center location of a ground control point in a particular digital image of at least one of the one or more groups; and
determine a pixel coordinate of the center location of the ground control point.
2. The computing apparatus of claim 1 , wherein the program instructions, when executed by the one or more processors, are further configured to direct the aerial vehicle to:
generate a dataset including the pixel coordinate identifying the center location of the ground control point in the particular digital image.
3. The computing apparatus of claim 1 , wherein the program instructions, when executed by the one or more processors, are further configured to direct the aerial vehicle to:
associating the determined pixel coordinate with a geo-spatial location of the ground control point.
4. The computing apparatus of claim 1 , wherein at least one digital image of the digital images has an associated geo-spatial coordinate indicating a location of where the digital image was captured by the aerial vehicle.
5. The computing apparatus of claim 1 , wherein at least one digital image of the digital images has an associated yaw, pitch, and roll value of the aerial vehicle at the time when the aerial vehicle captured the digital image.
6. The computing apparatus of claim 1 , wherein the program instructions, when executed by the one or more processors, are further configured to direct the aerial vehicle to:
generate a geo-rectified 3D model, or composite image, based on the digital images using the pixel coordinate.
7. The computing apparatus of claim 1 , wherein the program instructions, when executed by the one or more processors, are further configured to direct the aerial vehicle to:
determine a quality score associated with the particular digital image; and
discard the particular digital image from determining a pixel coordinate if the quality score does not meet a threshold value.
8. A method comprising:
segmenting digital images obtained by an aerial vehicle into groups corresponding to one or more ground control points depicted in the digital images;
identifying a center location of a ground control point in a particular digital image of at least one of the groups; and
determining a pixel coordinate of the center location of the ground control point.
9. The method of claim 8 , further comprising:
generating a dataset including the pixel coordinate that identifies the center location of the ground control point in the particular digital image.
10. The method of claim 8 , further comprising:
associating the determined pixel coordinate with a geo-spatial location of the ground control point.
11. The method of claim 8 , wherein at least one digital image of the digital images has an associated geo-spatial coordinate indicating a location where the digital image was captured by the aerial vehicle.
12. The method of claim 8 , wherein at least one digital image of the digital images has an associated yaw, pitch, and roll value of the aerial vehicle at the time when the aerial vehicle captured the digital image.
13. The method of claim 8 , further comprising:
generating a geo-rectified 3D model, or composite image, based on the digital images using the pixel coordinate.
14. The method of claim 8 , further comprising:
determining a quality score associated with the particular digital image; and
discarding the particular digital image from determining a pixel coordinate if the quality score does not meet a threshold value.
15. An aerial vehicle comprising:
a processing system configured to:
segment digital images obtained by the aerial vehicle into groups, wherein a group includes digital images for a particular control point;
identify a center location of a ground control point in a particular digital image; and
determine a pixel coordinate of the center location of the ground control point.
16. The aerial vehicle of claim 15 , wherein the processing system is further configured to:
generate a dataset including the pixel coordinate identifying the center location of the ground control point in the particular digital image.
17. The aerial vehicle of claim 15 , wherein the processing system is further configured to:
associate the determined pixel coordinate with a geo-spatial location of the ground control point.
18. The aerial vehicle of claim 15 , wherein at least one digital image of the digital images has an associated geo-spatial coordinate indicating a location of where the digital image was captured by the aerial vehicle.
19. The aerial vehicle of claim 15 , wherein at least one digital image of the digital images has an associated yaw, pitch and roll value of the aerial vehicle at the time when the aerial vehicle captured the digital image.
20. The aerial vehicle of claim 15 , wherein the processing system is further configured to:
generating a 3D surface model, or a composite image, based on the digital images using the pixel coordinate.