Multi-time-phase remote sensing image building changing detection method based on image block

Abstract

The invention discloses a multi-time-phase remote sensing image building changing detection method based on an image block. The multi-time-phase remote sensing image building changing detection methodbased on the image block firstly inputs building detection rough results of different time phases, equally divides a length and a width of each detection result into N parts, obtaining a ratio of pixel quantities of a building in a same area of two time phases at any random time interval, divides a building change in this area into three changing modes which include 'dramatic increase', ' substantial unchanged' and 'dramatic decrease', marks the changing mode of each area on an image of a later time phase and outputs a detection result. Furthermore, the multi-time-phase remote sensing image building changing detection method based on the image block can perform quantitative analysis on the area change on the basis of ratios of building areas of the two time phases at the random time interval. The multi-time-phase remote sensing image building changing detection method based on image block can comprehensive consider information according to a context, overcomes noise in a high resolution image, effectively realizes fast automatic changing detection of the building, fully mines the changing mode of the building and reaches ideal accuracy when the building detection result is an average.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a method for detecting building changes in remote sensing images, in particular to a method for detecting building changes in multi-temporal remote sensing images based on image blocks. Background technique [0002] Remote sensing is one of the important means of earth observation. With the launch of high-resolution remote sensing satellites such as IKONOS, Quick Bird, WorldView, GeoEye, and Gaofen-2, the spatial resolution and temporal resolution of remote sensing images have been significantly improved. The data sources of high-resolution remote sensing images are getting wider and wider, and the updates are getting faster and faster. Applications such as disaster monitoring, urban expansion, urban planning, and land management based on remote sensing technology are of great significance to the country and society. In these applications, an important link is to obtain ...

AI Technical Summary

Problems solved by technology

Remote sensing images acquired at different times are affected by conditions such as space, spectrum, and time, as well as radiation, atmospheric conditions, etc., which brings difficulties to high-precision change detection

In addition, high-resolution remote sensing images generally only have four bands of near-infrared, red, green, and blue, and the spatial information is much richer than that of medium and low-resolution images. The internal differences of the same kind of ground objects increase, and the differences between different ground objects are not significant.

As a result, traditional spectral information-based detection methods applied to high-resolution images will cause a large number of false alarms and missed alarms

[0007] (2) At present, most high-precision change detection algorithms are still far away from practical applications

[0008] At present, geographic information product production units such as surveying and mapping bureaus and geographic information centers often use manual sketching to realize the classification of ground objects and then perform change detection to generate thematic maps. Although the accuracy is high, it is time-consuming, labor-intensive, and inefficient; To achieve high-precision target recognition and change detection results, it often requires manual collection of a large number of training samples, and it takes a long time to train the model. At the same time, different models have different generalization capabilities, and it is difficult to find a model that is suitable for various detections at the same time. High-precision detection model for regions

Therefore, although these methods can achieve higher accuracy under certain conditions, they are still far away from the actual automation application.

[0009] (3) In the face of massive data, there is a lack of simple, fast and effective change detection methods

Faced with massive remote sensing data of TB level every day, some of the methods described in (2) are more complex and time-consuming, while traditional change detection methods are mostly based on spectral information, which is not suitable for high-score data

Therefore, it remains a great challenge to use change detection algorithms that are fast, simple, efficient, and suitable for high-performance environments

[0011] (4) The research on change detection at the local urban scale and below is of great significance, but there is currently a lack of systematic and effective theoretical methods

[0013] (5) Many algorithms for change detection currently have limited analysis and mining of changes and their essence

Most of the existing methods are to detect changes, and the analysis of changes, especially the quantitative analysis, is still weak

On the other hand, the change analysis of long-term remote sensing images often needs to study the change pattern of an object. Most of the current research first detects the targets of each time phase or classifies the ground objects, and then manually compares and analyzes them. The degree of intelligence is relatively low. Low, and easily mixed with subjective factors

In summary, there is a great demand for algorithms that can analyze and mine changes and their essence

Images