Scene identification method based on deconvolution deep network learning with weight

Abstract

The invention relates to a scene identification method based on deconvolution deep network learning with a weight. The method comprises: (1), a weight-included deconvolution deep network model is constructed and learning is carried out on original input images by using the weight-included deconvolution deep network model, thereby obtaining feature graphs of the images on different scales; (2), feature sampling is carried out on the feature graphs obtained by learning at the step (1) by using a spatial pyramid model, thereby forming a feature vector expression of each image; and (3), the original input images are divided into a training set and a testing set and the feature vector expressions of the images are inputted into a classifier of a support vector machine respectively to complete classification training and testing, so that identification results of different scenes are obtained. According to the method provided by the invention, scene expressions with different scenes are established and thus the scene expressions become accurate and adequate, so that the scene classification precision is improved.

Description

technical field [0001] The invention belongs to the technical field of information processing, and relates to a scene recognition and understanding method of a remote sensing image, in particular to a scene recognition method based on weighted deconvolution deep network learning. Background technique [0002] With the development of my country's aerospace technology, more and more high-scoring satellites are launched into space to obtain data on the earth's surface for purposes such as disaster monitoring, agricultural production estimation, and military investigation. Usually, the data transmitted from the satellite to the ground has a large frame size. In order to make full use of these large amounts of large-scale and high-resolution remote sensing data, scene classification is a very important preprocessing method. important help. [0003] At present, the methods for scene classification of remote sensing images are mainly divided into four categories: [0004] One is ...

AI Technical Summary

Problems solved by technology

[0008] Although the above four methods have achieved good results, they all ignore the characteristics of remote sensing images with complex ground objects and great similarities between different scene categories, resulting in low classification accuracy.

For example, there are not only airplanes in the airport scene, but also runways and terminal buildings. The runway and road scenes are difficult to distinguish, and the terminal building is easy to be confused with residential areas. Another example is the city and the dense activity room, which belong to different scenes. But even from the perspective of human vision, they have great similarities, thus hindering the further improvement of classification accuracy; in addition, most of these existing methods use artificially designed features, such as: scale-invariant feature rotation Descriptors, color histograms, etc., are less universal than features learned from the data itself

Images