Object Detection Algorithm of Remote Sensing Image Based on Projective Zeroing Recurrent Neural Network

Abstract

The invention discloses a remote sensing image target detection algorithm based on projection zeroing recursive neural network. Firstly, for the input original remote sensing image, a linear constraint optimization mathematical model of its filtering output is established, and then converted into a The unconstrained optimization mathematical model is converted into a linear equation mathematical model, and the projection zeroing recursive neural network algorithm is used to solve it. Finally, the output filter coefficient vector is passed through the change domain to obtain the filtered output remote sensing image, and the remote sensing image target is realized. detection. Compared with the traditional target detection algorithm, the algorithm of the present invention converts a constrained quadratic optimization problem into the solution of the linear equation equation mathematical model, which greatly improves the simplicity of calculation; it has faster convergence speed, shorter calculation time, It has the advantages of high detection accuracy and strong classification ability; it has a certain inhibitory effect on the noise signal of remote sensing image target detection.

Description

technical field [0001] The invention belongs to the technical field of remote sensing technology and image processing, and in particular relates to a remote sensing image target detection algorithm based on projection zeroing recursive neural network. Background technique [0002] After decades of development of remote sensing technology, the way people acquire remote sensing images has changed a lot. The resolution of remote sensing images is higher, which not only promotes the application of remote sensing images in many aspects, but also lays a good foundation for remote sensing image target detection. The basics. Remote sensing images contain a wealth of ground object information, through the processing and analysis of these information can help people solve many problems. Remote sensing image target detection is one of the important application directions. Many military and civilian applications involve target detection or tracking. The research on rapid identification...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a remote sensing image target detection algorithm based on projection zeroing recursive neural network, which solves the problems of high complexity, slow convergence speed and low precision caused by traditional remote sensing image target detection algorithms

Images