《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (1): 278-284.DOI: 10.11772/j.issn.1001-9081.2023010009

• 多媒体计算与计算机仿真 • 上一篇    

人手抓取物体的三维数据集的建立及应用

刘健1,2, 尤晨晨1, 曹金明1, 曾琼1, 屠长河1()   

  1. 1.山东大学 计算机科学与技术学院,山东 青岛 266237
    2.清华大学 软件学院,北京 100084
  • 收稿日期:2023-01-06 修回日期:2023-03-18 接受日期:2023-03-20 发布日期:2023-06-06 出版日期:2024-01-10
  • 通讯作者: 屠长河
  • 作者简介:刘健(1987—),男,山东潍坊人,助理研究员,博士,CCF会员,主要研究方向:计算机图形学、机器人;
    尤晨晨(1994—),女,山东济南人,硕士,主要研究方向:计算机图形学;
    曹金明(1990—),女,山东临沂人,博士,CCF会员,主要研究方向:计算机视觉;
    曾琼(1987—),女,湖南新化人,副研究员,博士,CCF会员,主要研究方向:数据可视分析、计算机图形学;
    第一联系人:屠长河(1968—),男,山东济南人,教授,博士,CCF会员,主要研究方向:计算机图形学、机器人。
  • 基金资助:
    国家自然科学基金资助项目(62072284)

Construction and application of 3D dataset of human grasping objects

Jian LIU1,2, Chenchen YOU1, Jinming CAO1, Qiong ZENG1, Changhe TU1()   

  1. 1.College of Computer Science and Technology,Shandong University,Qingdao Shandong 266237,China
    2.School of Software,Tsinghua University,Beijing 100084,China
  • Received:2023-01-06 Revised:2023-03-18 Accepted:2023-03-20 Online:2023-06-06 Published:2024-01-10
  • Contact: Changhe TU
  • About author:LIU Jian, born in 1987, Ph. D., assistant research fellow. His research interests include computer graphics, robot.
    YOU Chenchen, born in 1994, M. S. Her research interests include computer graphics.
    CAO Jinming, born in 1990, Ph. D. Her research interests include computer vision.
    ZENG Qiong, born in 1987, Ph. D., associate research fellow. Her research interests include visual data analysis, computer graphics.
  • Supported by:
    National Natural Science Foundation of China(62072284)

摘要:

真实人手抓取数据在人类抓取行为分析和机器人类人抓取等研究中起到至关重要的作用。抓取数据集中应包含复杂形状的三维物体信息、抓取点的信息以及手的姿态和形状,然而目前普遍方法是采集视频图像并从中估计人的抓取行为,导致不能准确记录手部各个关节的自由度信息。利用虚拟现实技术建立虚拟环境,利用数据手套直接捕捉在虚拟环境中三维物体和手部姿态信息作为抓取数据。提出的数据集包含生活中常见的49类物体中的91个不同形状的物体(每个有108个姿态)以及共52 173人次的抓取记录,规模和丰富性都远远超过了已有的用于研究人类的抓取行为和研究以人为核心的抓取技术的数据集。此外,使用采集的数据集进行抓取显著性分析和类人抓取计算,实验结果验证了数据集的应用价值。

关键词: 人手抓取数据集, 虚拟现实, 关节自由度, 抓取显著性, 类人抓取

Abstract:

Realistic human grasping data is of vital importance in the research of human grasping behavior analysis and human-like robotic grasping. A grasping dataset should include object shape information, contact points, and hand shapes and poses. However, related works often capture images or videos to estimate the human grasping behavior, which leads to the inaccuracy of joint degrees of freedom. Virtual Reality (VR) technology was used to establish a virtual environment, and digital gloves were used to directly capture 3D objects and hand poses in the virtual environment as capturing data. The proposed dataset contains 91 objects with various shapes (each with 108 poses) from 49 object categories, and 52 173 3D hand grasps, which scale and richness are far more than existing dataset used to study human grasping behavior and human-centered grasp technology. In addition, the collected dataset was used for grasp saliency analysis and human-like grasping calculation, and the experimental results demonstrate the practical value of this dataset.

Key words: human grasping dataset, virtual reality, joint degree of freedom, grasp saliency, human-like grasping

中图分类号: