Pointing Gesture Based Point of Interest Identification in Vehicle Surroundings

This article presents a pointing gesture-based point of interest computation method via pointing rays’ intersections for situated awareness interactions in vehicles. The proposed approach is compared with two alternative methods: (a) a point of interest identification method based on the intersection of the pointing ray with the point cloud (PoC) resulting from the vehicle sensors, and (b) the traditional ray-casting approach, where the point of interest is computed based on the first intersection of the pointing rays with locations stored in a 2D annotated map. Simulation results show that the presented method outperforms by 36.25% the traditional ray casting one. However, as it was expected, the sensor-based computation method is more accurate. The validation of our approach was conducted by experiments performed in a test track facility. Although limited due to instrumentation challenges that will be described, the analysis of the results shows that a point of interest computation method based on pointing rays’ intersections performs 16.25% better than the traditional ray-casting one. This result is of particular interest in dense scenarios, where more than one point of interest intersects the pointing rays in a 2D map. Finally, this article shows how a POI disambiguation step can help to solve all the POI identification inaccuracies.

Language

  • English

Media Info

  • Media Type: Web
  • Features: Figures; Photos; References; Tables;
  • Serial:

Subject/Index Terms

Filing Info

  • Accession Number: 01727988
  • Record Type: Publication
  • Source Agency: SAE International
  • Report/Paper Numbers: 2018-01-1094
  • Files: TRIS, SAE
  • Created Date: Jan 27 2020 9:23AM