Abstract
Abstract. 3D LiDAR point cloud obtained from the laser scanner is too dense and contains millions of points with information. For such huge volume of data to be sorted, identified, validated and be used for prediction, data mining provides immense scope and has been used to achieve the same. Certain unique attributes were selected as an input for creating models through machine learning. Supervised models were thus built for prediction of classes through the available LiDAR data using random forest algorithm. The algorithm was chosen owing to its efficiency and accuracy over other data mining algorithms. The models created using random forest were then tested on an unclassified point cloud data of an urban area. The method shows promising results in terms of classification accuracy as overall accuracy of 91.71 % was achieved for pixel-based classification. The method also displays enhanced efficiency over common classification algorithms as the time taken to make predictions about the data is reduced considerably for a set of dense LiDAR data. This shows positive foresight of making use of data mining and machine learning to handle large volume of LiDAR data and can go a long way in augmenting efficient processing of LiDAR data.
Highlights
1.1 Classification of an urban sceneFor urban development planning, forecast and simulation and for automatic positioning of vehicle, it has been desirable to extract terrain and building information in such an urban area (Shan and Sampath, 2007)
Application of only Principal Component Analysis (PCA) showed that roads, parts of buildings as well as some parts of thick tree trunks are classified as planes
Using python script, running the program and classification took more than 12 hours and sometimes the well configured computer would hang owing to large amount of data
Summary
Forecast and simulation and for automatic positioning of vehicle, it has been desirable to extract terrain and building information in such an urban area (Shan and Sampath, 2007). An urban area consists of mixed features mainly like roads, trees, buildings, traffic, poles. The extraction of these features has been a difficult task due to the proximity of the various features that exist in an urban area. The extraction of urban information is a challenging task in remote sensing. This is because the per-pixel methods that are commonly used are likely to fail due to their inability to capture the increased natural inconsistencies in the reflectance, and due to the reality, that each class category may contain several spatially adjacent pixels The highly heterogeneous nature of urban surface materials creates problems at different spatial levels to classify urban areas and accurately
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
