PREDICTING ACCURACY OF OBJECT RECOGNITION IN A STITCHED IMAGE

摘要

A device may receive a set of images for an object recognition operation to identify one or more objects in the set of images after the set of images are combined into a stitched image. The device may combine the set of images into the stitched image. The device may determine reliability scores for the set of images. The reliability scores may be determined based on a difference in images of the set of images, and the reliability scores may predict a quality of the stitched image that includes an image, of the set of images, to which the reliability scores correspond. The device may determine whether a result of the object recognition operation is likely to satisfy a threshold based on the reliability scores. The device may selectively perform the object recognition operation based on whether the result of the object recognition operation is likely to satisfy the threshold.

主权项

1. A device, comprising:
one or more processors to:
receive a plurality of images for an object recognition operation,
the object recognition operation identifying one or more objects in the plurality of images after the plurality of images are combined into a stitched image;combine the plurality of images into the stitched image;determine one or more reliability scores for the plurality of images,
the one or more reliability scores being determined based on a difference in a color parameter of two or more images of the plurality of images, andthe one or more reliability scores predicting a quality of the stitched image that includes an image, of the plurality of images, to which the one or more reliability scores correspond;determine whether a result of the object recognition operation is likely to satisfy a threshold based on the one or more reliability scores; andselectively perform the object recognition operation based on whether the result of the object recognition operation is likely to satisfy the threshold.