Abstract: Systems and methods for object detection generate a feature pyramid corresponding to image data, and rescaling the feature pyramid to a scale corresponding to a median level of the feature pyramid, wherein the rescaled feature pyramid is a four-dimensional (4D) tensor. The 4D tensor is reshaped into a three-dimensional (3D) tensor having individual perspectives including scale features, spatial features, and task features corresponding to different dimensions of the 3D tensor. The 3D tensor is used with a plurality of attention layers to update a plurality of feature maps associated with the image data. Object detection is performed on the image data using the updated plurality of feature maps.

Abstract: A road recognition method and system based on a seed point includes: obtaining a remote sensing image; obtaining a grayscale image; inserting a seed point in the grayscale image; searching for four initial road boundary points using the seed point as a reference point; obtaining a smallest bounding rectangle search box formed by the four initial road boundary points; obtaining a plurality of candidate search boxes based on the obtained search boxes; determining whether a sum of squares of grayscale differences between the plurality of candidate search boxes and the obtained search box is greater than a preset threshold; and if yes, stopping searching and completing road recognition; or if not, selecting a new search box from the plurality of candidate search boxes, and retrieving a plurality of candidate search boxes based on the new search box.

Abstract: The method includes a step of acquisition of an image of the leading aircraft, a step of extraction of the outline, an adjustment step including implementing an outline registration algorithm, to determine an optimized profile from a comparison of the outline of the leading aircraft with a profile of the leading aircraft determined from a three-dimensional model of the leading aircraft and from an initial position of the following aircraft with respect to the leading aircraft, and a step of determination of the positioning according to six degrees of freedom of the following aircraft with respect to the leading aircraft, from the optimized profile and from the three-dimensional model of the leading aircraft. The method thus makes it possible to rapidly and accurately determine the positioning of the following aircraft with respect to the leading aircraft, this positioning being used to implement a formation flight.