arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.02167eess.SPcs.CVcs.LGcs.RO
收藏

基于三帧RGB扫描编码的实时2D激光雷达目标检测

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

Smart Systems Group, Institute of Engineering Hanze University of Applied Sciences, Groningen, The Netherlands

Soheil Behnam Roudsari, Alexandre S. Brandão, Felipe N. Martins

AI总结:

本研究提出一种基于三帧RGB扫描编码的实时2D激光雷达目标检测方法,实现高效且隐私友好的嵌入式室内机器人感知。

摘要:

室内服务机器人需要鲁棒、比RGB视频更隐私友好且能在嵌入式硬件上实现的感知能力。我们提出了一种无需摄像头的2D激光雷达目标检测流水线,通过将三个连续扫描堆叠为RGB通道来编码短期时间上下文,从而获得一个紧凑的YOLOv8n输入,无需构建占用网格,同时保留角度结构和运动线索。在Webots上评估了160个随机化的室内场景,严格场景级留出测试下,该方法在四个目标类别上实现了98.4%的mAP@0.5(0.778 mAP@0.5:0.95)的精度,94.9%的召回率。在Raspberry Pi 5上,其以每帧47.8ms的平均端到端延迟实现实时运行,包括扫描编码和后处理。与在同一平台上报告的密切相关占用网格激光雷达-YOLO流水线相比,所提出的表示方法与显著较低的端到端延迟相关。尽管结果是基于模拟的,但它们表明,轻量级的时间编码可以实现嵌入式室内机器人中无需捕捉RGB外观的准确且实时的激光雷达-only检测。

英文摘要:

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% mAP@0.5 (0.778 mAP@0.5:0.95) 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 47.8ms per frame, including scan encoding and postprocessing. Relative to a closely related occupancy-grid LiDAR-YOLO pipeline reported on the same platform, the proposed representation is associated with substantially lower reported end-to-end latency. Although results are simulation-based, they suggest that lightweight temporal encoding can enable accurate and real-time LiDAR-only detection for embedded indoor robotics without capturing RGB appearance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑