移除地面点可提升点云压缩率，不影响目标检测性能
Can We Remove the Ground? Obstacle-aware Point Cloud Compression for Remote Object Detection
- 基于柱状结构设计轻量级地面点过滤算法，不依赖复杂模型
- 在KITTI和Waymo数据集上移除20-30%点云，检测性能不变
- 算法高效并行，实测帧率提升至86 FPS，适合实时传输场景
高效的点云压缩对增强现实、协同感知等流媒体应用至关重要。传统方法对每帧所有点进行编码。本文针对接收端感知任务，提出疑问：能否在传输中移除地面点而不影响检测性能？研究发现当前主流3D目标检测模型对地面点有强依赖，尤其在物体下方及周围区域。为此，我们提出轻量级障碍物感知的柱状地面移除（PGR）算法。PGR过滤掉对目标识别无上下文意义的地面点，显著提升压缩比，且不影响接收端感知性能。该算法无需使用重型目标检测或语义分割模型，具备轻量、高度并行、高效等优势。在KITTI与Waymo Open Dataset上的评估表明，使用PGR移除20-30%点云后，SOTA检测模型性能保持不变，同时实现86 FPS的处理速度。
原文摘要 · Abstract (English)
Efficient point cloud (PC) compression is crucial for streaming applications, such as augmented reality and cooperative perception. Classic PC compression techniques encode all the points in a frame. Tailoring compression towards perception tasks at the receiver side, we ask the question, "Can we remove the ground points during transmission without sacrificing the detection performance?" Our study reveals a strong dependency on the ground from state-of-the-art (SOTA) 3D object detection models, especially on those points below and around the object. In this work, we propose a lightweight obstacle-aware Pillar-based Ground Removal (PGR) algorithm. PGR filters out ground points that do not provide context to object recognition, significantly improving compression ratio without sacrificing the receiver side perception performance. Not using heavy object detection or semantic segmentation models, PGR is light-weight, highly parallelizable, and effective. Our evaluations on KITTI and Waymo Open Dataset show that SOTA detection models work equally well with PGR removing 20-30% of the points, with a speeding of 86 FPS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。