{
  "paper_id": "48de5bdfc311f968c6e3560e42474ed4",
  "paper_title": "Pedestrian Recognition Using High-definition LIDAR",
  "paper_authors": [
    "Kiyosumi Kidono",
    "Takeo Miyasaka",
    "Akihiro Watanabe",
    "Takashi Naito",
    "Jun Miura"
  ],
  "publication_date": "",
  "publication_venue": "2011 IEEE Intelligent Vehicles Symposium (IV)",
  "abstract": "Pedestrian detection is one of the key technologies for autonomous driving systems and driving assistance systems. To predict the possibility of a future collision, these systems have to accurately recognize pedestrians as far away as possible. Moreover, the function to detect not only people walking but also people who are standing near the road is also required. This paper proposes a method for recognizing pedestrians by using a high-definition LIDAR. Two novel features are introduced to improve the classification performance. One is the slice feature, which represents the profile of a human body by widths at the different height levels. The other is the distribution of the reflection intensities of points measured on the target. This feature can contribute to the pedestrian identification because each substance has its own unique reflection characteristics in the near-infrared region of the laser beam. Our approach applies a support vector machine (SVM) to train a classifier from these features. The classifier discriminates the clusters of the laser range data that are the pedestrian candidates, generated by pre-processing. A quantitative evaluation in a road environment confirms the effectiveness of the proposed method.",
  "keywords": [
    "pedestrian recognition",
    "LIDAR",
    "slice feature",
    "reflection intensity",
    "support vector machine",
    "autonomous driving"
  ],
  "paper_institutions": [],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:46:44.849660Z",
  "template_tag": "simple",
  "summary": "### 摘要\n本文针对自动驾驶与驾驶辅助系统中远距离行人识别的问题，提出了一种基于高分辨率激光雷达（LIDAR）的行人识别方法。相关研究背景包括基于图像的方法以及基于2D/3D激光数据的行人检测，但现有方法在远距离（超过30米）性能下降明显。所提出的方法引入两种新颖特征：切片特征（slice feature）和反射强度分布特征。切片特征通过沿人体主方向将点云划分为多个高度块，计算各块中点在正交平面上的宽度，从而粗略描述从头部到腿部的轮廓；反射强度分布利用近红外激光对不同材料的反射特性差异，统计候选簇内点的平均强度、标准差和归一化直方图。方法采用支持向量机（SVM）配合RBF核训练分类器，首先通过分割和聚类生成行人候选，再利用特征向量进行分类。实验在真实道路环境下采集数据，数据集I（11人步行，最高50米）和数据集II（75个动态道路场景）分别用于基础性能评估和道路环境评估。在总体样本评估中，所提方法在假阳性率0.01时真阳性率比Navarro-Serment方法高约0.1；在30-50米距离范围内性能提升明显。核心机制为通过切片特征和强度分布增强远距离低分辨率下的形状区分能力。未来工作包括融合图像传感器和针对遮挡目标的鲁棒特征开发。\n\n### 关键要点\n- 使用高分辨率LIDAR（Velodyne HDL-64ES2，64线，垂直分辨率0.4度）获取3D点云，用于行人识别。\n- 提出切片特征：将候选簇沿主成分方向分为10个均匀块，每块在正交平面投影后计算两个宽度，共20维特征。\n- 提出反射强度分布特征：利用近红外（905nm）激光对不同材料的反射差异，统计点云强度的均值、标准差及25-bin归一化直方图，共27维。\n- 分类器采用SVM（RBF核），特征向量总共包含9个特征（f1至f9），其中f8为切片特征，f9为强度分布。\n- 预处理流程包括：LIDAR数据采集、基于占用栅格的地面分割（阈值0.3m）、距离聚类（0.5m内合并）、基于尺寸的候选提取（高度0.8-2.0m，宽和长≤1.2m）。\n- 评估数据集I（11人，最高50米）和数据集II（75个场景，124人，动态道路环境）均手动标注正负样本。\n- 总体性能：在假阳性率1%时，所提方法真阳性率比Navarro-Serment方法高约0.1。\n- 不同距离评估显示，在30-50米范围内所提方法性能显著优于参考方法，而2D直方图特征对点数敏感，远距离效果不佳。\n- 道路环境评估中，在每帧0.1个假阳性条件下，真阳性率约85%，即使测试集中包含训练中未出现的穿裙子和打伞女性。\n- 切片特征维数低（20维）但判别能力强，强度分布特征可区分相似形状但材质不同的物体（如行人vs路灯杆）。\n- 反射强度与距离平方成反比，但传感器已输出距离归一化的8位强度值，可直接使用。"
}