Automatic stitching approach of aerial image sequence based on SIFT features;

Taking into account characteristic of the UAV aerial images,this paper present a wavelet-based multiresolution analysis hierarchical scheme for image matching.

The UAV aerial images have fine resolution.

Many experiments show that this method can recognize the runways of the airports exactly and quickly in the aerial images.

This paper realized a location system which locates moving-objects in aerial video.

Brings forward multiscale edge detecting method by using cubic B-Spline wavelet transform on aerial image.

In the field of military scouting, analysis is often carried by superposingaerial image on digital map; sometimes slant correction isrequiredto superpose correctly.

By correcting the rotating angle of the image based on the flight attitude of the UAV,the direction of the aerial image can be fixed to help the operator to observe and decide correctly.

Aimed at the real-time application, such as air vehicle visual navigation, a scheme for fast extracting and matching line segments on the aerial sequential images is proposed.

In condition that there is no proiri knowledge on the model and the scenes in the aerial sequential images change continuously, first the images are filtered because of a large amount of noise.