Font Size: a A A

Road Construction Supervision System Design And Implementation Based On High Resolution Remote Sensing Images

Posted on:2021-01-14Degree:MasterType:Thesis
Country:ChinaCandidate:Q SuFull Text:PDF
GTID:2392330605461054Subject:Computer technology
Abstract/Summary:PDF Full Text Request
As an important part of transportation system,highway transportation plays an increasingly important role in the development of national economy.In the 21 st century,China has accelerated the speed of highway construction,but the supervision of highway construction is still dominated by manual supervision,which requires a lot of human and material resources.With the rapid development of remote sensing technology,it has been successfully applied in agriculture,geology,meteorology,military and environmental protection,and is developing to other fields.Using remote sensing image to identify and monitor the construction road can not only reduce the investment in construction supervision,but also increase the timeliness and safety of supervision,which has important practical value and practical significance.This dissertation takes the remote sensing image of the construction site of G55 Changde section of expressway as the experimental data,and uses the remote sensing image classification and change detection technology to extract the road supervision information.The main research work of this dissertation is as follows:(1)Fuzzy c-means clustering(FCM)algorithm is sensitive to noise in the process of classification,which affects the accuracy of experiments.Moreover,as an important basis of regulatory information,the road and surrounding features will lose the feature information when FCM is used for classification.In view of the above problems,this dissertation first uses KPCA to reduce the dimension of the data,then uses KFCM to calculate the membership degree of the reduced dimension data,finally uses neighborhood information to distinguish the fuzzy boundary pixels,and obtains the experimental results.The experimental results show that this classification method can not only retain the feature information of the edge region,but also solve the problem that some objects in the same spectrum are difficult to distinguish.(2)If there is salt and pepper noise in remote sensing image,it will affect the accuracy of change detection,and the unsupervised change detection method is more sensitive to noise,which is easy to generate a large number of false alarms.These problems cause great interference to the extraction of road and surrounding features.In this dissertation,we use the improved intuitionistic fuzzy c-means clustering algorithm to detect the changes.Firstly,we use the difference method,ratio method and image regression method to construct three spectral change difference images,and use PCA to extract the features of the difference images.Finally,we use intuitionistic fuzzy c-means clustering method to detect the changes.Experimental results show that this method can effectively reduce the impact of salt and pepper noise,and improve the accuracy of change detection.(3)The road construction supervision information is divided into three points: first,the evaluation of the road construction progress,using the road vector data and related basic knowledge,according to the classification information and change detection information for analysis,to get the road construction progress and approximate speed.The second is the evaluation of the temporary land occupation around the road under construction.Using the remote sensing image classification method and the remote sensing image change detection method,the use and change of the temporary land occupation around the road in different periods are extracted.The third is the evaluation of the ecological restoration around the road after the completion of the construction.By using the remote sensing image classification method and the remote sensing image change detection method,and combining the normalized vegetation index and the vegetation index difference,the corresponding ecological restoration around the road in the two groups of remote sensing images is obtained.(4)The road construction supervision system in this dissertation is designed and implemented based on development kit of MapWindowGIS.The system implements the information extraction of road construction supervision,and has a certain value in practical engineering application.
Keywords/Search Tags:Remote Sensing Image Classification, Fuzzy Kernel C-means Clustering, Remote Sensing Image Change Detection, Intuitionistic Fuzzy C-means Clustering, Road Construction Supervision System
PDF Full Text Request
Related items