{
  "paper_id": "f9a6e07d373b90af337bd8976121c70f",
  "paper_title": "Head-to-shoulder signature for person recognition",
  "paper_authors": [
    "Nathan Kirchner",
    "Alen Alempijevic",
    "Alexander Virgona"
  ],
  "publication_date": "",
  "publication_venue": "2012 IEEE International Conference on Robotics and Automation",
  "abstract": "Ensuring that an interaction is initiated with a particular and unsuspecting member of a group is a complex task. As a first step the robot must effectively, expediently and reliably recognise the humans as they carry on with their typical behaviours (in situ). A method for constructing a scale and viewing angle robust feature vector (from analysing a 3D pointcloud) designed to encapsulate the inter-person variations in the size and shape of the people's head to shoulder region (Head-to-shoulder signature - HSS) is presented. Furthermore, a method for utilising said feature vector as the basis of person recognition via a Support-Vector Machine is detailed. An empirical study was performed in which person recognition was attempted on in situ data collected from 25 participants over 5 days in an office environment. The results report a mean accuracy over the 5 days of 78.15% and a peak accuracy 100% for 9 participants. Further, the results show a considerably better-than-random (1/23 = 4.5%) result for when the participants were: in motion and unaware they were being scanned (52.11%), in motion and face directly away from the sensor (36.04%), and post variations in their general appearance. Finally, the results show the HSS has considerable ability to accommodate for a person's head, shoulder and body rotation relative to the sensor - even in cases where the person is faced directly away from the robot.",
  "keywords": [
    "person recognition",
    "head-to-shoulder signature",
    "3D pointcloud",
    "support vector machine",
    "in situ",
    "scale invariant",
    "view angle robust"
  ],
  "paper_institutions": [
    "Centre for Autonomous Systems, University of Technology Sydney"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:46:46.547258Z",
  "template_tag": "simple",
  "summary": "### 摘要\n本文针对机器人在群体中准确识别特定目标人物这一复杂任务，提出了一种基于3D点云构建尺度与视角鲁棒的头部-肩部签名（HSS）特征向量的方法，并利用支持向量机（SVM）实现人物识别。该方法在办公室环境中对25名参与者（其中23名有效）进行了为期5天的现场实验评估。实验结果表明，在参与者静止站立时，平均识别准确率为78.15%，峰值准确率达100%（9名参与者）；当参与者行走且未意识到被扫描时，准确率为52.11%；当参与者背对传感器行走时，准确率为36.04%，均显著高于随机猜测概率（4.5%）。此外，HSS对头部、肩部和身体的旋转具有较好的鲁棒性，即使参与者完全背对机器人也能保持一定识别能力。核心机制是通过水平切片计算旋转不变的跨度向量，隐式编码垂直特征，从而避免对物理特征进行显式标记。实验数据包括自然发生的姿势和着装变化，验证了该方法在实际场景中的可用性。未来工作将进一步探索外观变化、姿势变化及移动参与者的影响，并考虑与人类识别能力的比较。\n\n### 关键要点\n- 问题背景：机器人需要在多人交互中识别特定目标，而目标人物可能未意识到扫描且处于自然行为状态。\n- 方法核心：构造头部-肩部签名（HSS）特征向量，基于3D点云的水平切片跨度，具有尺度和视角鲁棒性。\n- 特征构建：将点云上半部分（0.4米高度）分为等厚水平切片，每个切片计算最大点间距离作为跨度，有序向量即HSS。\n- 分类模型：使用径向基核函数（RBF）的多类支持向量机（SVM），参数通过交叉验证优化，训练数据来自Day 0的站立数据。\n- 实验设计：25名参与者（24男1女，年龄22-45岁），在办公室环境持续5天，机器人固定，参与者按指令行走并停留。\n- 数据收集：训练数据为Day 0站立时的数据，测试数据为随后4天收集，参与者未被限制着装，自然出现外观变化。\n- 主要结果：站立静止时平均准确率78.15%，峰值100%（9人），最低0%（1人）；行走朝向传感器52.11%，行走离开36.04%。\n- 外观变化鲁棒性：准确率在几天间有波动，但始终显著高于随机，表明HSS对常规外观变化（如衣物）有较好适应性。\n- 姿态变化测试：对单个参与者的头部和肩部角度进行测试，发现肩部角度在-60°至+60°（面向传感器）及-140°至+160°（背对传感器）时识别成功。\n- 局限与未来：存在参与者姿势异常（如侧身、举臂）导致识别失败的情况，未来将改进并考虑多帧概率融合。"
}