Classification of Ultra-High Resolution Orthophotos Combined with DSM Using a Dual Morphological Top Hat Profile

Abstract

New aerial sensors and platforms (e.g., unmanned aerial vehicles (UAVs)) are capable of providing ultra-high resolution remote sensing data (less than a 30-cm ground sampling distance (GSD)). This type of data is an important source for interpreting sub-building level objects; however, it has not yet been explored. The large-scale differences of urban objects, the high spectral variability and the large perspective effect bring difficulties to the design of descriptive features. Therefore, features representing the spatial information of the objects are essential for dealing with the spectral ambiguity. In this paper, we proposed a dual morphology top-hat profile (DMTHP) using both morphology reconstruction and erosion with different granularities. Due to the high dimensional feature space, we have proposed an adaptive scale selection procedure to reduce the feature dimension according to the training samples. The DMTHP is extracted from both images and Digital Surface Models (DSM) to obtain complimentary information. The random forest classifier is used to classify the features hierarchically. Quantitative experimental results on aerial images with 9-cm and UAV images with 5-cm GSD are performed. Under our experiments, improvements of 10% and 2% in overall accuracy are obtained in comparison with the well-known differential morphological profile (DMP) feature, and superior performance is observed over other tested features. Large format data with 20,000 × 20,000 pixels are used to perform a qualitative experiment using the proposed method, which shows its promising potential. The experiments also demonstrate that the DSM information has greatly enhanced the classification accuracy. In the best case in our experiment, it gives rise to a classification accuracy from 63.93% (spectral information only) to 94.48% (the proposed method).

High-Resolution Remote Sensing Data Classification over Urban Areas Using Random Forest Ensemble and Fully Connected Conditional Random Field

“…This approximation is iteratively optimized through a series of message passing steps, each of which updates a single variable by aggregating information from all other variables; its efficiency for the FCCRF inference has been demonstrated by Krahenbuhl [57]. Like the model fusion stage in Section 2.2, the validation set is also used in this stage to learn the best values of the hyper parameters w (1) , w (2) , σ α , σ β and σ γ in Equation (12). As described in Chen [13], a two level coarse-to-fine grid search scheme is used to search for the best values.…”

“…To exploit the complementary characteristics of multisource data, data fusion based methods are also popular and have been proven to be more reliable than the single-source data methods used by many researchers [8]. For example, both images and 3D geometry data have been used in several previous studies [9][10][11][12].…”

Improving Tree Species Classification Using UAS Multispectral Images and Texture Measures

“…Their capability to generate ultra-high resolution imagery [7] at flexible temporal scales makes the UAS suitable to fill the gap between finer scale field samples and coarser scale aerial…”

Strategies for the Management of Built Heritage Linked to Maintenance and Monitoring. Case Study of the San Roque Neighborhood, Cuenca, Ecuador

“…The use of UAVs for the acquisition of high-quality images on rooftops requires the use of new techniques to process these data. Different studies (Hebel &Stilla, 2008), (Qin, Huang, Gruen, & Schmitt, 2015), (Zhang, Qin, Huang, & Liu, 2015) outline the use of geometric information segmentation, reconstruction and extraction techniques from multispectral or conventional images.…”