Evaluating and enhancing google tango localization in indoor environments using fiducial markers

Marques, Bernardo; Carvalho, Raphael Torres Santos; Dias, Paulo; Oliveira, Miguel; Ferreira, Carlos; Santos, Beatriz Sousa

doi:10.1109/icarsc.2018.8374174

Cited by 6 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To rectify these drifts, we integrate motion tracking and area learning features of the Tango technology. Specifically, area learning stores the key visual landmarks of a physical space in highly-compressed files, namely area description files (ADFs) for later identification of that space [20]. Such visual landmarks are exploited as reference frames to be matched with the frames collected while moving around the same space.…”

Section: Point Clouds Generationmentioning

confidence: 99%

MapSense

Abdelaal

Sekar

Dürr

et al. 2020

ACM Trans. Internet Things

View full text Add to dashboard Cite

Recently, indoor modeling has gained increased attention, thanks to the immense need for realizing efficient indoor location-based services. Indoor environments 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 this 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, which 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 that 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 crowd-sensing 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 while drastically reducing the energy overhead on the mobile devices.

show abstract

Section: Point Clouds Generationmentioning

confidence: 99%

MapSense

Abdelaal

Sekar

Dürr

et al. 2020

ACM Trans. Internet Things

View full text Add to dashboard Cite

show abstract

“…Regardless, there are several approaches that produce good quality models from RGB-D data, in particular those based on signed distance fields [29][30][31], or implicit surfaces [32,33]. In this work, we use 3D meshes directly generated by a Google Tango device (https://en.wikipedia.org/wiki/Tango_(platform), accessed on 15 March 2021) [34][35][36][37], which uses a surface reconstruction approach based on dynamic spatially-hashed truncated signed distance field for mapping the scene [17]. The input 3D meshes and RGB-D images are provided by Open Constructor (https://github.com/lvonasek/tango/wiki/Open-Constructor, accessed on 15 March 2021), a software that uses a google tango device to perform 3D reconstruction.…”

Section: Introductionmentioning

confidence: 99%

“…Note that, while there are several systems which use RGB-D cameras to perform surface reconstruction, and thus build a 3D mesh of the captured scene, our approach is not limited to these systems. Yet, using an RGB-D camera for texture mapping is a forthright choice when the same RGB-D camera was used for reconstructing the 3D model [ 34 , 35 , 36 , 37 ]. Still, we highlight that this approach may also be of use for texturing 3D meshes produced by other systems, such as 3D LIDARs.…”

Section: Introductionmentioning

confidence: 99%

Robust Texture Mapping Using RGB-D Cameras

Oliveira

Lim

Madeira

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

The creation of a textured 3D mesh from a set of RGD-D images often results in textured meshes that yield unappealing visual artifacts. The main cause is the misalignments between the RGB-D images due to inaccurate camera pose estimations. While there are many works that focus on improving those estimates, the fact is that this is a cumbersome problem, in particular due to the accumulation of pose estimation errors. In this work, we conjecture that camera poses estimation methodologies will always display non-neglectable errors. Hence, the need for more robust texture mapping methodologies, capable of producing quality textures even in considerable camera misalignments scenarios. To this end, we argue that use of the depth data from RGB-D images can be an invaluable help to confer such robustness to the texture mapping process. Results show that the complete texture mapping procedure proposed in this paper is able to significantly improve the quality of the produced textured 3D meshes.

show abstract