The invention discloses a star
orbit mask calculation method for space target observation
image processing. The method belongs to the technical field of space target observation
image processing. The problems that in the existing space target detection field, a
frame difference method or a
mask method needs to depend on the level of an image
recognition algorithm, so that the
processing efficiency is low, and the
false alarm rate and the missed recognition rate are insufficient are solved. The method comprises the following steps: firstly, giving a fixed star
orbit width under a specific length and magnitude through a morphological method, secondly, giving a star
orbit length, a
distortion width and a star orbit slope of an image needing to be processed through a sample statistics method, and then carrying out star
map matching and high-magnitude fixed star coordinate inversion. Finally, star orbit expansion and rotation transformation are conducted on the inverted star point information to form a star orbit
mask.The method can be used for successfully conducting mask
processing on fixed star orbits in the specified star magnitude range in the image, the detection efficiency and the recognition rate of the space target can be greatly improved, the
false alarm rate of the space target is reduced, and the method has a wide application scene.