Abstract
Aerial topographic surveys using Light Detection and Ranging (LiDAR) technology collect dense and accurate information from the surface or terrain; it is becoming one of the important tools in the geosciences for studying objects and earth surface. Classification of Lidar data for extracting ground, vegetation, and buildings is a very important step needed in numerous applications such as 3D city modelling, extraction of different derived data for geographical information systems (GIS), mapping, navigation, etc... Regardless of what the scan data will be used for, an automatic process is greatly required to handle the large amount of data collected because the manual process is time consuming and very expensive. <br><br> This paper is presenting an approach for automatic classification of aerial Lidar data into five groups of items: buildings, trees, roads, linear object and soil using single return Lidar and processing the point cloud without generating DEM. Topological relationship and height variation analysis is adopted to segment, preliminary, the entire point cloud preliminarily into upper and lower contours, uniform and non-uniform surface, non-uniform surfaces, linear objects, and others. <br><br> This primary classification is used on the one hand to know the upper and lower part of each building in an urban scene, needed to model buildings façades; and on the other hand to extract point cloud of uniform surfaces which contain roofs, roads and ground used in the second phase of classification. A second algorithm is developed to segment the uniform surface into buildings roofs, roads and ground, the second phase of classification based on the topological relationship and height variation analysis, The proposed approach has been tested using two areas : the first is a housing complex and the second is a primary school. The proposed approach led to successful classification results of buildings, vegetation and road classes.
Highlights
LIDAR systems are active sensors that incorporate a mechanism for direct georeferencing witch allow the collection of a significant number of points in three dimensions in a very short time, which requires a careful and powerful treatment
Automatic extraction of 3D objects from 3D LIDAR data has a very important role in the scientific community given its importance for modeling an urban scene, as it can significantly reduce the resources required for data analysis and 3D modeling of cities
The segmentation can be conducted in three distinct approaches categorized on the basis of type of data used: The first is based on the point cloud; the second relates to derivative products and the third uses several complementary data sources, as nonlimiting examples, satellite images, aerial photos, cadastral data, digital terrain models ... these are multi-source approaches
Summary
LIDAR systems are active sensors that incorporate a mechanism for direct georeferencing witch allow the collection of a significant number of points in three dimensions in a very short time, which requires a careful and powerful treatment. Automatic extraction of 3D objects from 3D LIDAR data has a very important role in the scientific community given its importance for modeling an urban scene, as it can significantly reduce the resources required for data analysis and 3D modeling of cities. Processing LIDAR point cloud in an automatic way by special algorithms permits to generate plans in an instant way. Through this paper, a study of the state of the art of different segmentation and modeling methods proposed in the literature. The segmentation can be conducted in three distinct approaches categorized on the basis of type of data used: The first is based on the point cloud; the second relates to derivative products and the third uses several complementary data sources, as nonlimiting examples, satellite images, aerial photos, cadastral data, digital terrain models ... The segmentation can be conducted in three distinct approaches categorized on the basis of type of data used: The first is based on the point cloud; the second relates to derivative products and the third uses several complementary data sources, as nonlimiting examples, satellite images, aerial photos, cadastral data, digital terrain models ... these are multi-source approaches
Sign-in/Register to view highlights & summary 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 callMore From: ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
