摘要 |
A reconnaissance process for taking successive images (7, 10) of an object using a camera by pairing optimally points (A, B) into a single movement (Deltam) compatible with the movement of the camera that has taken two images to calculate the position of the object. The points that can be paired belong to the object even if they have been obtained automatically, whereas the background of the image often has a lower number of points making it impossible to pair with the movement (Deltam).
|