Abstract

Abstract. Tree detection using aerial sensors in early decades was focused by many researchers in different fields including Remote Sensing and Photogrammetry. This paper is intended to detect trees in complex city areas using aerial imagery and laser scanning data. Our methodology is a hierarchal unsupervised method consists of some primitive operations. This method could be divided into three sections, in which, first section uses aerial imagery and both second and third sections use laser scanners data. In the first section a vegetation cover mask is created in both sunny and shadowed areas. In the second section Rate of Slope Change (RSC) is used to eliminate grasses. In the third section a Digital Terrain Model (DTM) is obtained from LiDAR data. By using DTM and Digital Surface Model (DSM) we would get to Normalized Digital Surface Model (nDSM). Then objects which are lower than a specific height are eliminated. Now there are three result layers from three sections. At the end multiplication operation is used to get final result layer. This layer will be smoothed by morphological operations. The result layer is sent to WG III/4 to evaluate. The evaluation result shows that our method has a good rank in comparing to other participants’ methods in ISPRS WG III/4, when assessed in terms of 5 indices including area base completeness, area base correctness, object base completeness, object base correctness and boundary RMS. With regarding of being unsupervised and automatic, this method is improvable and could be integrate with other methods to get best results.

Highlights

  • Detection and classification of objects on earth were and still are important fields for researchers in different majors including Remote Sensing and Photogrammetry (Rottensteiner et el., 2011)

  • As emerging new sensors like laser scanners, developing Photogrammetry field, and utilizing digital cameras, methods of detection and classification are got into new era

  • Normalized Difference Vegetation Index (NDVI) and Shadow Index (SI) are calculated and NDVI is divided on SI

Read more

Summary

Introduction

Detection and classification of objects on earth were and still are important fields for researchers in different majors including Remote Sensing and Photogrammetry (Rottensteiner et el., 2011). At high resolution aerial images boundary of objects like Buildings is clearly notable, but in LiDAR data there are some problems in detecting such boundaries. There are lots of methods and algorithms in detection and classification field but it is not possible to compare those together This is because of lack of bench mark data sets. In other hand most of algorithms and methods have tested in different data sets To overcome this problem and making it easier to compare methods together a working group established in ISPRS, named WG III/4. This WG grants a bench mark data set to participants and encourages them to test their methods on this data and send the results to WG for evaluation We separated WG III/4 participants’ related works from the others

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call