Object-Based Classification of Urban Distinct Sub-Elements Using High Spatial Resolution Orthoimages and DSM Layers

Abstract

This paper aims to assess the ways in which multi-resolution object-based classification methods can be used to group urban environments made up of a mixture of buildings, sub-elements such as car parks, roads, shades and pavements and foliage such as grass and trees. This involves using both unmanned aerial vehicles (UAVs) which provide high-resolution mosaic Orthoimages and generate a Digital Surface Model (DSM). For the study area chosen for this paper, 400 Orthoimages with a spatial resolution of 7 cm each were used to build the Orthoimages and DSM, which were georeferenced using well distributed network of ground control points (GCPs) of 12 reference points (RMSE = 8 cm). As these were combined with onboard RTK-GNSS-enabled 2-frequency receivers, they were able to provide absolute block orientation which had a similar accuracy range if the data had been collected by traditional indirect sensor orientation. Traditional indirect sensor orientation involves the GNSS receiver in the UAV receiving a differential signal from the base station through a communication link. This allows for the precise position of the UAV to be established, as the RTK uses correction, allowing position, velocity, altitude and heading to tracked, as well as the measurement of raw sensor data. By assessing the results of the confusion matrices, it can be seen that the overall accuracy of the object-oriented classification was 84.37%. This has an overall Kappa of 0.74 and the data that had poor classification accuracy included shade, parking lots and concrete pavements. These had a producer accuracy (precision) of 81%, 74% and 74% respectively, while lakes and solar panels each scored 100% in comparison, meaning that they had good classification accuracy.