Accessibility and safe movement in urban areas entail infrastructure that minimizes the risks for pedestrians and bikers with diverse levels of abilities. Recognizing and mapping unsafe areas can increase awareness among citizens and inform city projects to improve their infrastructure. This contribution presents an example in which the specific objective is to recognize the unprotected areas around the canals in the city of Amsterdam.
This is accomplished through running image processing algorithms on 11K waterside panoramas taken from the city of Amsterdam's open data portal. We created an annotated subset of 2K processed images for training and evaluation. This dataset debuts a novel pixel-level annotation style using multiple lines. To determine the best inference practice, we compared the IoU and robustness of several existing segmentation frameworks.
The best method achieves an IoU of 0.79. The outcome is superimposed on the map of Amsterdam, showing the geospatial distribution of the low, middle, and high fences around the canals.
In addition to this specific application, we discuss the broader use of the presented method for the problem of “transparent object detection” in an urban context.