MapSense

Mohamed Abdelaal, Suriya Sekar, Frank Dürr, Kurt Rothermel, Susanne Becker, Dieter Fritsch
2020 ACM Transactions on Internet of Things  
Recently, indoor modeling has gained increased attention thanks to the immense need for realizing efficient indoor location-based services. Indoor environments de facto differ from outdoor spaces in two aspects: spaces are smaller and there are many structural objects such as walls, doors, and furniture. To model the indoor environments in a proper manner, novel data acquisition concepts and data modeling algorithms have been devised to meet the requirements of indoor spatial applications. In
more » ... is realm, several research efforts have been exerted. Nevertheless, these efforts mostly suffer either from adopting impractical data acquisition methods or from being limited to 2D modeling. To overcome these limitations, we introduce the MapSense approach that automatically derives indoor models from 3D point clouds collected by individuals using mobile devices, such as Google Tango, Apple ARKit, and Microsoft HoloLens. To this end, MapSense leverages several computer vision and machine learning algorithms for precisely inferring the structural objects. In MapSense, we mainly focus on improving the modeling accuracy through adopting formal grammars which encode design-time knowledge, i.e. structural information about the building. In addition to modeling accuracy, MapSense considers the energy overhead on the mobile devices via developing a probabilistic quality model through which the mobile devices solely upload high-quality point clouds to the crowd-sensing servers. To demonstrate the performance of MapSense, we implemented a crowdsensing Android App to collect 3D point clouds from two different buildings by six volunteers. The results showed that MapSense can accurately infer the various structural objects together with drastically reducing the energy overhead on the mobile devices. executive's office and both rooms have specific dimensions. Through exploiting this knowledge, we can simply correct and complete a floor plan derived from inaccurate or incomplete data. In this article, we encode such structural information using a grammar that includes, for instance, the dimensions of rooms, the number of rooms, the relative room ordering, geometric constraints, etc. MapSense also considers the energy efficiency of the participating mobile devices. In this realm, MapSense makes use of several energy-awareness techniques, including Octree compression, voxel grid downsampling, and probabilistic quality model. The first two techniques tackle the communication energy overhead through reducing the number of points to be reported to a crowdsensing server. Whereas, the probabilistic quality model is mainly used to prevent reporting low-quality point clouds, thus reducing the energy overhead of repeating the sensing queries. To the best of our knowledge, MapSense is the first QoS-aware mapping method which employs formal indoor grammars in combination with a probabilistic quality model to derive highly-accurate indoor models from a small set of crowd-sensed point clouds in an energy-efficient manner.
doi:10.1145/3379342 dblp:journals/tiot/AbdelaalSDRBF20 fatcat:yovxy2thebd3ncmsg5n4xpsyee