Using of machines learning in extraction of urban roads from DEM of LIDAR data: Case study at Baghdad expressways, Iraq

Oday Zakariya Jasim

doi:10.21533/pen.v7i4.914

Abstract

Road extraction from remotely perceived information may be a difficult issue and has been approached in many various ways in which by photogrammetrists and digital image processors. This study was given extraction of roads from DEM of LiDAR with IKONOS image using machines learning (ML). Two set of data were used in this study. IKONOS Image and Digital Elevation Model (DEM) data were combined to produce thematic mapping. The spatial resolution of data is 1 m and was acquired on 2010. The result f thematic map based on theses images and the methods was used three models of machines learning. The problem of this study, when was used the LIDAR data to extract the road is very difficult because the LiDAR data is too noisy and employed it also so hard. Moreover, this article will describe an effective and compare between several machines learning algorithms (RF, BYO and MLP) for detection the roads from LIDAR data. The statistical indictors such as an overall accuracy (OA), kappa analysis statistic (K), (MAE) which is Mean Absolute Error and finally the (RMSE) which is Root Mean Squared Error. All these will be use to get the accuracy of classification assessment and the best model to produce the thematic map.

Highlights

Light Detection and Ranging (LIDAR) Remote sensing is the technique of obtain remotely the electromagnetic radiation emitted or reflected by a surface without direct contact with it [1]
We found the Multi layer Perceptron (MLP) is the best model for testing the other models through achieved the highest Acc with K and lest MAE and RMSE which are 96.24, 0.93, 0.06 and 0.16 receptively
This study suggests that the MLP model with simple sensitivity analysis can significantly outperform the random frost model (RF), OBY and maximum Likelihood models

Summary

Introduction

Light Detection and Ranging (LIDAR) Remote sensing is the technique of obtain remotely the electromagnetic radiation emitted or reflected by a surface without direct contact with it [1]. With the Geographic Information System, extraction and classification roads can be made to the land or in any area [2]. The new Machine learning is a technique that utilized to detect, recognize and extract data or land uses from the images [5]. It was noted that different classification outcomes are achieved from the use of different classifiers. In machine learning, at least three major factors that influence accuracy of classification should be considered. The three aforementioned factors have been investigated in the past, only few investigations in relation to settings of tuning parameters have been witnessed. The first step and the most important among the factors use in machine learning is the setting tuning parameters.

Methods

Results

Discussion

Conclusion