Automatic Classification of Aerial Imagery for Urban Hydrological Applications

Abstract

ABSTRACT:In this paper we investigate the potential of automatic supervised classification for urban hydrological applications. In particular, we contribute to runoff simulations using hydrodynamic urban drainage models. In order to assess whether the capacity of the sewers is sufficient to avoid surcharge within certain return periods, precipitation is transformed into runoff. The transformation of precipitation into runoff requires knowledge about the proportion of drainage-effective areas and their spatial distribution in the catchment area. Common simulation methods use the coefficient of imperviousness as an important parameter to estimate the overland flow, which subsequently contributes to the pipe flow. The coefficient of imperviousness is the percentage of area covered by impervious surfaces such as roofs or road surfaces. It is still common practice to assign the coefficient of imperviousness for each particular land parcel manually by visual interpretation of aerial images. Based on classification results of these imagery we contribute to an objective automatic determination of the coefficient of imperviousness. In this context we compare two classification techniques: Random Forests (RF) and Conditional Random Fields (CRF). Experimental results performed on an urban test area show good results and confirm that the automated derivation of the coefficient of imperviousness, apart from being more objective and, thus, reproducible, delivers more accurate results than the interactive estimation. We achieve an overall accuracy of about 85% for both classifiers. The root mean square error of the differences of the coefficient of imperviousness compared to the reference is 4.4% for the CRF-based classification, and 3.8% for the RF-based classification.

Smart management of combined sewer overflows: From an ancient technology to artificial intelligence

“…Finally, it was agreed that the greater resolution image and mapping approach improved land cover discrimination and resulted in more accurate C estimation (Thanapura et al, 2007). Aerial images and height data have been used to determine the coefficient of imperviousness (Paul et al, 2018). In this work, random forest (RF) and conditional random fields supervised classification techniques were compared.…”