Doorgaan naar hoofdnavigatie Doorgaan naar zoeken Ga verder naar hoofdinhoud

Real-Time 2D LiDAR Object Detection Using Three-Frame RGB Scan Encoding

  • Departamento de Engenharia Elétrica

Onderzoeksoutput: Contribution to conference proceeding › Academic › peer review

Samenvatting

Indoor service robots need perception that is robust, more privacy-friendly than RGB video, and feasible on embedded hardware. We present a camera-free 2D LiDAR object detection pipeline that encodes short-term temporal context by stacking three consecutive scans as RGB channels, yielding a compact YOLOv8n input without occupancy-grid construction while preserving angular structure and motion cues. Evaluated in Webots across 160 randomized indoor scenarios with strict scenario-level holdout, the method achieves 98.4% [email protected] (0.778 [email protected]:0.95) with 94.9% precision and 94.7% recall on four object classes. On a Raspberry Pi 5, it runs in real time with a mean post-warm-up end-to-end latency of 47.8 ms per frame, including scan encoding and postprocessing. Although the evaluation is simulation-based, the results indicate that lightweight temporal encoding can support accurate and realtime LiDAR-only detection for embedded indoor robotics without relying on RGB appearance.
Originele taal-2English
Titel2026 IEEE Sensors Applications Symposium (SAS)
UitgeverijInstitute of Electrical and Electronics Engineers
Pagina's1-6
Aantal pagina's6
ISBN van geprinte versie979-8-3315-8264-7
DOI's
StatusPublished - 17 jul. 2026
Evenement2026 IEEE Sensors Applications Symposium (SAS) - Vitoria, Brazil
Duur: 15 jul. 2026 → 17 jul. 2026

Conference

Conference2026 IEEE Sensors Applications Symposium (SAS)
Periode15/07/26 → 17/07/26

Duurzame ontwikkelingsdoelstellingen van de VN

Deze output draagt bij aan de volgende duurzame ontwikkelingsdoelstelling(en)

  1. SDG 03 – Goede gezondheid en welzijn
    SDG 03 – Goede gezondheid en welzijn
  2. SDG 09 – Industrie, innovatie en infrastructuur
    SDG 09 – Industrie, innovatie en infrastructuur

Keywords

  • robotica
  • objectdetectie
  • LiDAR
  • YOLOv8
  • ingebedde systemen
  • tijdscodering
  • privacyvriendelijke detectie

Research Focus Areas Hanze University of Applied Sciences

  • No Hanze research focus area applicable
  • Healthy Ageing

Research Focus Areas Research Centre or Centre of Expertise

  • Artificial Intelligence
  • Cyberfysical systems

Publinova thema's

  • ICT & Media
  • Techniek
  • Gezondheid

Vingerafdruk

Duik in de onderzoeksthema's van 'Real-Time 2D LiDAR Object Detection Using Three-Frame RGB Scan Encoding'. Samen vormen ze een unieke vingerafdruk.
  • Best Poster Award - IEEE SAS 2026

    Martins, F. (Recipient), Roudsari, S. B. (Recipient) & Santos Brandão, A. (Recipient), 17 jul. 2026

    Prijs: Prize (including medals and awards)

Citeer dit