DSSD-based automatic illegal building detection method and system

Abstract

The invention relates to the field of illegal building image recognition, and particularly to a DSSD-based automatic illegal building detection method and a system. The system comprises an image workstation, a detection system and a system terminal, the image workstation is responsible for illegal building images, the detection system comprises training set and test set preprocessing, labeling andneural network discrimination, and the training set and test set preprocessing comprises multi-scale image denoising and enhancement. The method comprises the steps that the image workstation obtainsand collects a violation building map, then the DSSD neural network is used for judgment, and finally a result obtained through processing of the detection system is sent to the system terminal. Theautomatic illegal building detection system is completed on the basis of the intelligent image processing technology and the neural network, the workload of manual recognition can be reduced to a certain extent, and the intelligent illegal building detection system has important significance in urban dynamic monitoring, illegal building recognition, geographic information updating and the like.

Description

technical field [0001] The invention relates to the technical field of image recognition of illegal buildings, in particular to a method and system for automatically detecting illegal buildings based on DSSD. Background technique [0002] Building change detection, as one of the important contents of geographic national conditions monitoring, is of great significance to the identification of illegal buildings, urban dynamic monitoring and geographic information update. Taking the detection of illegal buildings in cities as an example, with the continuous development of my country's economy and society, the urbanization process continues to accelerate, urban buildings continue to grow, and the number and scale of illegal buildings are also increasing. Landscape, which also affects the image of the city and the lives of residents, is not only a hot issue of concern to the common people, but also a difficult issue of urban management, and it is also one of the negative factors a...

AI Technical Summary

Problems solved by technology

At present, "the cost of illegality is low, and the cost of law enforcement is high" is one of the main reasons why illegal buildings are repeatedly prohibited. In addition to the lack of relevant legal links, the detection of illegal buildings is also relatively weak. Due to the lack of automated monitoring methods for illegal buildings , the use of manual inspection has many disadvantages, one is that the discovery process cycle is longer, and the other is that the cost of large-scale monitoring is high

In recent years, Beijing and other cities have tried to use satellite image data to detect illegal buildings, but the automatic analysis technology of image information is still not mature enough, and the proportion of manual identification and verification in the process is large

Images