Abstract
Abstract. A reliable and accurate facade database would be a major asset in applications such as localization of autonomous vehicles, registration and fine building modeling. Mobile mapping devices now provide the data required to create such a database, but efficient methods should be designed in order to tackle the enormous amount of data collected by such means (a million point per second for hours of acquisition). Another important limitation is the presence of numerous objects in urban scenes of many different types. This paper proposes a method that overcomes these two issues: – The facade detection algorithm is streamed: the data is processed in the order it was acquired. More precisely, the input data is split into overlapping blocks which are analysed in turn to extract facade parts. Close overlapping parts are then merged in order to recover the full facade rectangle. – The geometry of the neighborhood of each point is analysed to define a probability that the point belongs to a vertical planar patch. This probability is then injected in a RANdom SAmple Consensus (RANSAC) algorithm both in the sampling step and in the hypothesis validation, in order to favour the most reliable candidates. This ensures much more robustness against outliers during the facade detection. This way, the main vertical rectangles are detected without any prior knowledge about the data. The only assumptions are that the facades are roughly planar and vertical. The method has been successfully tested on a large dataset in Paris. The facades are detected despite the presence of trees occluding large areas of some facades. The robustness and accuracy of the detected facade rectangles makes them useful for localization applications and for registration of other scans of the same city or of entire city models.
Highlights
The high level of detail of data collected by mobile lidar mapping systems allows for fine geometrical modeling of urban environment
Efficient methods are needed to detect the main scanned structures in order to split the modelization of a whole city into smaller parts Whereas numerous works focus on the fine reconstruction of certain types of urban objects the detection of such objects in large amounts of data remains quite unexplored, making these methods hardly scalable
Concerning under-segmentation, it is natural in the case of urban scenes as adjacent facades often share the same plane, so they cannot be distinguished based on our method
Summary
The high level of detail of data collected by mobile lidar mapping systems allows for fine geometrical modeling of urban environment. We aim to automate a necessary step in fine facade modeling over large areas: detect the main facade rectangles present in the scene This seemingly simple task faces the scaling problem and other difficulties that often leads to perform it in a semi-automatic way, by pre-selecting manually areas containing each facade or resorting to a cadastral database (Hammoudi et al, 2009), a 3D model (Benitez et al, 2010) or aerial lidar data (Poullis and You, 2009). Automation of this treatment is necessary to enable the modeling of large-scale urban scenes
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
