GraMap: QoS-Aware Indoor Mapping Through Crowd-Sensing Point Clouds with Grammar Support

Abstract

Recently, several approaches have been proposed to automatically model indoor environments. Most of such efforts principally rely on the crowd to sense data such as motion traces, images, and WiFi footprints. However, large datasets are usually required to derive precise indoor models which can negatively affect the energy efficiency of the mobile devices participating in the crowd-sensing system. Furthermore, the aforementioned data types are hardly suitable for deriving 3D indoor models. To overcome these challenges, we propose GraMap, a QoS-aware automatic indoor modeling approach through crowd-sensing 3D point clouds. GraMap exploits a recently-developed sensors fusion mechanism, namely Tango technology, to cooperatively collect point clouds from the crowd. Afterward, a set of backend servers extracts the required geometrical information to derive indoor models.For the sake of improving the energy efficiency of the mobile devices, GraMap performs data quality assurance along with 3D data compression. Specifically, we propose a probabilistic quality model-implemented on the mobile devices-to ensure high-quality of the captured point clouds. In this manner, we conserve energy via sidestepping the repetition of sensing queries due to uploading low-quality point clouds. Nevertheless, the resultant indoor models may still suffer from incompleteness and inaccuracies. Therefore, GraMap leverages formal grammars which encode design-time knowledge, i.e. structural information about the building, to enhance the quality of the derived models. To demonstrate the effectiveness of GraMap, we implemented a crowd-sensing Android App to collect point clouds from volunteers. We show that GraMap derives highly-accurate models while reducing the energy costs of pre-processing and reporting the point clouds. CCS CONCEPTS• Human-centered computing → Ubiquitous and mobile devices;

GreenMap: Approximated Filtering Towards Energy-Aware Crowdsensing for Indoor Mapping

“…This fact occurs since some walls which separate neighboring rooms are often scanned twice from both sides. Accordingly, we refine these disjointed lines to eventually obtain an initial indoor model [5].…”

“…The room size-extracted from the initial model-is then utilized to adjust the emission probabilities of the different states. More details about the grammar-enhanced modeling component can be found in our previous paper [5].…”

“…In this realm, we introduced an automatic modeling approach for 2D floor plans that relies on Markov chains to integrate a set of crowdsensed motion traces and a formal indoor grammar [2]. Afterwards, we proposed the crowdsensing of 3D point clouds for 3D indoor modeling applications [5]. Literally, point clouds are 3D data structures representing points in space where the points usually represent the X, Y, and Z geometric coordinates of a sampled surface.…”

“…Aside from being well-suited for indoor modeling, point clouds are naturally bulky data to be processed and uploaded by mobile devices to a crowdsensing server. In [5], the participating mobile devices have to sample and report several point clouds whose size rang from five MBytes to 50 MBytes. Despite adopting Octree compression [7], the energy costs of performing compression and reporting the results are relatively high (cf.…”

“…In detail, the paper makes the following contributions: (1) We define an architectural framework-built upon a previous work by our group [5]-for modeling indoor environments using crowdsensed 3D point clouds. Our framework first generates an initial model through processing the collected point clouds.…”