3D mapping from partial observations: An application to utility mapping

Abstract

Precise mapping of buried utilities is critical to managing massive urban underground infrastructure and preventing utility incidents. Most current research only focuses on generating such maps based on complete information of underground utilities. However, in real-world practice, it is rare that a full picture of buried utilities can be obtained for such mapping. Therefore, this paper explores the problem of generating maps from partial observations of a scene where the actual world is not fully observed. In particular, we focus on the problem of generating 2D/3D maps of buried utilities using a probabilistic based approach. This has the advantage that the method is generic and can be applied to various sources of utility detections, e.g. manhole observations, sensors, and existing records. In this paper, we illustrate our novel methods based on detections from manhole observations and sensor measurements.This paper makes the following new contributions. It is the first time that partial observations have been used to generate utility maps using optimization based approaches. It is the first time that such a large variety of utilities' properties have been considered, such as location, directions, type and size. Another novel contribution is that different kinds of connections are included to reflect the complex layout and structure of buried utilities. Finally, for the first time to the best of our knowledge, we have integrated utility detection, probability calculation, model formulation and map generation into a single framework.The proposed framework represents all detections using a common language of probability distributions and then formulates the mapping problem as an Integer Linear Programming (ILP) problem and the final map is generated based on the solution with the highest probability sum. The effectiveness of this system is evaluated on synthetic and real data using appropriate evaluation metrics.

Review of Artificial Intelligence Applications for Virtual Sensing of Underground Utilities

“…It is important to note from Table 1 that some assets belong to more than one utility class. While there exist physical methods to reduce uncertainties, such as investigating the type of utility by opening manholes, as carried out in Dou et al [4] and Chen and Cohn [36], or accessing other visual information, such as identification icons or inscriptions, automated routing algorithms could help understand and cope with these uncertainties. This can be carried out, for example, through fuzzy logic [37].…”

“…Segment connections are completed using a Bayesian approach, and finally, the underground utility map is prepared for visualization. Dou et al [4] generated utility maps from the combination of information collected from manhole investigations and GPR data. The manhole investigation allows the utility to be characterized by their directional angle, depth, and material type.…”

“…Evidence-based mapping also includes the use of any available information, such as asplanned and as-built maps. Nevertheless, while it is known that as-planned maps are often highly inaccurate, as-built maps may also be unreliable [4]. In particular, a recent survey reported that more than half of the utilities struck were missing from the available utility maps [5].…”

Probabilistic Method to Fuse Artificial Intelligence-Generated Underground Utility Mapping

“…Li et al [16] combined a global positioning system-aided GPR survey with preexisting knowledge of utility depth from excavation efforts to understand the limitations of GPR equipment through a comparison of sensor outputs with ground truth data, thus enabling the creation of an uncertainty-aware 3D model. Other works [5,17,18] fused utility data sources using similar probabilistic approaches similar to the aforementioned studies [8,14,15].…”

“…Underground utility investigations are typically initiated using as-built or as-planned records and then utility locating services, such as those from Subsurface Utility Engineering (SUE) providers [ 4 ]. As-built or as-planned records are not always readily available and may be inaccurate [ 5 ]. The popular One-Call system acts as a clearinghouse to notify utility companies of imminent construction activity and puts them on notice to indicate where their facilities are located with ground paint and flagging.…”