A Learning-Based Method for Airport Remote Sensing Image Detection

Abstract

The invention provides an airport remote sensing image detection method based on learning, which firstly performs Canny edge detection on the remote sensing image, removes noise interference in the remote sensing image, and obtains specific edge information of the remote sensing image; The starting coordinate value of the longest straight line segment, and the length of the longest straight line is calculated; finally, the support vector machine is used for learning classification prediction, and the coordinate value of the starting point of the longest straight line segment and the longest length value are cascaded to obtain An enhanced feature quantity is input into the support vector machine for sufficient learning; it can be seen that the present invention simplifies the complex remote sensing image classification problem, eliminates a large amount of interference information in the airport remote sensing image detection, and utilizes the powerful support vector machine. The two-classification ability does not need to modify the parameters too much. Under the same conditions, the method of the present invention is simple and has a detection accuracy rate of 96.5%.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a learning-based airport remote sensing image detection method. Background technique [0002] Airport detection plays a key role in airport navigation and military target strike. At the same time, the rapid development of remote sensing technology has made it a reality to obtain high-quality remote sensing images. The difference between remote sensing images of airports and non-airport remote sensing images will inevitably lead to differences in image feature quantities. Because airport runways usually appear as strips with straight edges and relatively uniform edges, the length and width have a certain range, and the edge lines are generally parallel; the gray level of airport runways in remote sensing images is obvious, and it is also different from the surrounding environment. . These characteristics of airport remote sensing images are possible for airport detecti...

AI Technical Summary

Problems solved by technology

Because the result of edge detection greatly affects the extraction effect of the straight line, it is easy to be confused with other irrelevant targets, resulting in the failure of detection, so the stability of this method is poor.

Images