Classification system for remote sensing image scene

Abstract

The invention discloses a classification system for a remote sensing image scene. The classification system comprises a collection module, a gray level processor, a fitting module, an edge detection module, a remote sensing image pixel classification module and a neural network trainer, wherein the collection module is used for collecting an original remote sensing image as a sample and transmitting the original remote sensing image to the gray level processor; the gray level processor is used for carrying out gray level processing on the original remote sensing image transmitted by the collection module through a component method; the fitting module is used for adopting a low-order spline function to carry out fitting on a gray level histogram; the edge detection module is used for adopting a method based on zero crossing to find the zero crossing point of a second derivative obtained by the image to position an edge; the remote sensing image pixel classification module adopts pixel-based classification to judge and classify ground feature category attributes expressed by the pixels to obtain a classification thematic map; and the neural network trainer is used for inputting a convolutional neural network model for training so as to obtain a classification result of remote sensing image scenes which require accuracy. the system is high in classification accuracy.

Description

technical field [0001] The invention relates to the field of classification of remote sensing images, in particular to a classification system of remote sensing image scenes. Background technique [0002] At present, many famous scholars at home and abroad are devoted to the research of image classification algorithm. Image classification is an image processing method that distinguishes different types of objects according to the different characteristics reflected in the image information. [0003] However, the shortcomings of the existing scene image classification and extraction in the prior art mainly lie in (1) in the traditional classification method, the manual extraction of features is quite time-consuming and labor-intensive, and requires high accuracy, and generally the accuracy is not as good as that of neural network classification. method. (2) When using neural networks and related models to implicitly extract features using general methods, the requirements fo...

AI Technical Summary

Problems solved by technology

In general, the number of commonly used data sets or self-made data sets is not enough to allow the neural network to fully learn and avoid over-fitting, resulting in an accuracy that cannot meet expectations.

Images