Abstract
To deal with the problem of urban ground object information extraction, the paper proposes an object-oriented classification method using aerial image and LiDAR data. Firstly, we select the optimal segmentation scales of different ground objects and synthesize them to get accurate object boundaries. Then, this paper uses ReliefF algorithm to select the optimal feature combination and eliminate the Hughes phenomenon. Eventually, the multiple classifier combination method is applied to get the outcome of the classification. In order to validate the feasible of this method, this paper selects two experimental regions in Stuttgart and Germany (Region A and B, covers 0.21 km<sup>2</sup> and 1.1 km<sup>2</sup> respectively). The aim of the first experiment on the Region A is to get the optimal segmentation scales and classification features. The overall accuracy of the classification reaches to 93.3 %. The purpose of the experiment on region B is to validate the application-ability of this method for a large area, which is turned out to be reaches 88.4 % overall accuracy. In the end of this paper, the conclusion shows that the proposed method can be performed accurately and efficiently in terms of urban ground information extraction and be of high application value.
Highlights
As the development of Remote sensing technology, the approach to extract information from high resolution images has become the key to monitor the development of urban area, including the changes of land usage
The single scale of segmentation result is liable to be over- or under-segmented, For a complex urban ground field, to get a high quality segmented result, it is essential to use multi-scale segmentation considering the scale characteristics of various objects For example, a multi-scale segmentation method based on QuickBird imagery and nDSM data was proposed by Chen etc (2009), in which different land cover classes were extracted using different segmentation parameters based on different images
In order to solve these problems that the urban ground object boundary is difficult to extract accurately and the classification method is hard to be reused for other application, this paper proposes an object-oriented method integrating high spatial resolution image and LiDAR data
Summary
As the development of Remote sensing technology, the approach to extract information from high resolution images has become the key to monitor the development of urban area, including the changes of land usage. Charaniya (2004) classified aerial LiDAR height data into roads, grass, buildings, and trees using a supervised parametric classification algorithm All these researches use the pixel-based classification methods, which will result in the serious Pepper-Salt effect. The single scale of segmentation result is liable to be over- or under-segmented, For a complex urban ground field, to get a high quality segmented result, it is essential to use multi-scale segmentation considering the scale characteristics of various objects For example, a multi-scale segmentation method based on QuickBird imagery and nDSM (normalized digital surface model) data was proposed by Chen etc (2009), in which different land cover classes were extracted using different segmentation parameters (such as scale, color and shape parameters) based on different images.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
