Simplifying Urban Data Fusion with BigSUR

Our ability to understand data has always lagged behind our ability to collect it. This is particularly true in urban environments, where mass data capture is particularly valuable, but the objects captured are more varied, dense, and complex. Captured data has several problems; it is unstructured (we do not know which objects are encoded by the data), contains noise (the scanning process is often inaccurate) and omissions (it is often impossible to scan all of a building). To understand the structure and content of the environment, we must process the unstructured data to a structured form.

BigSURi is an urban reconstruction algorithm which fuses GIS (Geographic Information System / mapping) data, photogrammetric meshes, and street level photography, to create clean representative, semantically labelled, geometry. However, we have identified three problems with the system i) the street level photography is often difficult to acquire; ii) novel façade styles often frustrate the detection of windows and doors; iii) the computational requirements of the system are large, processing a large city block can take up to 15 hours.

Here we describe the process of simplifying and validating the BigSUR semantic reconstruction system. In particular, the requirement for street level images is removed, and a greedy post-process profile assignment is introduced to accelerate the system. We accomplish this by modifying the binary integer programming (BIP) optimization, and re-evaluating the effects of various parameters.

The new variant of the system is evaluated over a variety of urban areas. We objectively measure mean squared error (MSE) terms over the unstructured geometry, showing that BigSUR is able to accurately recover omissions and discard inaccuracies in the input data. Further, we evaluate the ability of the system to label the walls and roofs of input meshes, concluding that our new BigSUR variant achieves highly accurate semantic labelling with shorter computational time and less input data.