Urban road underground disease recognition method based on constrained robust principal component analysis

Abstract

The invention discloses an urban road underground disease recognition method based on constrained robust principal component analysis, which comprises the steps of obtaining original training sample data of underground diseases through ground penetrating radar, decomposing each piece of the original training sample data into a low-rank matrix representing the background clutter and a sparse matrixrepresenting a foreground object by using a constrained robust principal component analysis method, obtaining an over-complete dictionary of the original training sample data and a test sample complete feature vector, and recognizing the test sample complete feature vector by adopting a kernel function based sparse representation classification method. The urban road underground disease recognition method has the characteristics of high robustness, high operation speed, short data analysis time and the like, and can realize automatic recognition for the underground hidden disease quickly andaccurately.

Description

technical field [0001] The invention relates to the field of automatic target identification, in particular to a method for identifying underground diseases of urban roads based on constrained robust principal component analysis. Background technique [0002] The development of urbanization in China is the general trend. By 2050, the proportion of urban residents will reach 70%. The smooth flow of urban roads is an important basis for the survival and development of cities. In recent years, urban road surface collapse accidents have occurred frequently, especially in large cities. According to the "National Land Subsidence Prevention and Control Plan (2011-2020)" issued by the Ministry of Land and Resources and the Ministry of Water Resources, there are currently more than 50 cities in the country suffering from land subsidence disasters. It can be expected that land subsidence will become a long-term problem along with urban development. Therefore, it has become an import...

AI Technical Summary

Problems solved by technology

However, the existing methods have the following problems in the application of urban road disease identification: the robustness of the algorithm to noise / clutter needs to be strengthened

Compared with highways, urban roads have diverse functions, complex composition, and many pipelines and other structures under the road. The radar echo signal is affected by many interference sources above and below the ground, and the signal-to-noise ratio is low, which makes data interpretation very difficult. Therefore, A very robust recognition method is required; classification recognition speed needs to be improved

Classifiers based on artificial neural networks and support vector machines require a large amount of test data and multiple training times, and it takes a lot of time to adjust parameters to obtain better test accuracy.

Images