Road Accident Black Spot Localisation using Morphological Image Processing Methods on Heatmap
Sándor Szénási, Imre Felde, Gábor Kertész, László Nádai · 2018
Heatmaps are widely used by road safety engineers to visualise accident data (where heat refers to the concentration of accidents). In the subfield of road accident black spot localisation, the high number of similar black spot candidate locations makes this method unreliable and difficult to use. An additional process to convert the clusters of the heatmap into a list of black spot candidates results in an objective, comparable outcome. As we will show, the commonly used thresholding method (considering pixels above a given limit as parts of black spots) has several limitations. This paper presents a novel image processing approach to quantify the raw data of the heatmap. It is possible to give a more accurate splitting between black spot and safe areas, using the morphological function named erosion.