Contour Primitive of Interest Extraction Network Based on One-Shot Learning for Object-Agnostic Vision Measurement

被引:5
|
作者
Qin, Fangbo [1 ]
Qin, Jie [1 ]
Huang, Siyu [2 ]
Xu, De [1 ]
机构
[1] Chinese Acad Sci, Res Ctr Precis Sensing & Control, Inst Automat, Beijing 100190, Peoples R China
[2] Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China
基金
中国国家自然科学基金;
关键词
SEGMENTATION;
D O I
10.1109/ICRA48506.2021.9561168
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Image contour based vision measurement is widely applied in robot manipulation and industrial automation. It is appealing to realize object-agnostic vision system, which can be conveniently reused for various types of objects. We propose the contour primitive of interest extraction network (CPieNet) based on the one-shot learning framework. First, CPieNet is featured by that its contour primitive of interest (CPI) output, a designated regular contour part lying on a specified object, provides the essential geometric information for vision measurement. Second, CPieNet has the one-shot learning ability, utilizing a support sample to assist the perception of the novel object. To realize lower-cost training, we generate support-query sample pairs from unpaired online public images, which cover a wide range of object categories. To obtain single-pixel wide contour for precise measurement, the Gabor-filters based non-maximum suppression is designed to thin the raw contour. For the novel CPI extraction task, we built the Object Contour Primitives dataset using online public images, and the Robotic Object Contour Measurement dataset using a camera mounted on a robot. The effectiveness of the proposed methods is validated by a series of experiments.
引用
收藏
页码:4311 / 4317
页数:7
相关论文
共 20 条
  • [1] Object-Agnostic Vision Measurement Framework Based on One-Shot Learning and Behavior Tree
    Qin, Fangbo
    Xu, De
    Hannaford, Blake
    Hao, Tiantian
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2023, 53 (08) : 5202 - 5215
  • [2] Contour Primitive of Interest Extraction Network Based on Dual-Metric One-Shot Learning for Vision Measurement
    Qin, Fangbo
    Lin, Shan
    Xu, De
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2023, 19 (04) : 5839 - 5848
  • [3] Quadruplet Network With One-Shot Learning for Fast Visual Object Tracking
    Dong, Xingping
    Shen, Jianbing
    Wu, Dongming
    Guo, Kan
    Jin, Xiaogang
    Porikli, Fatih
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (07) : 3516 - 3527
  • [4] One-shot learning based on improved matching network
    Jiang, Liubing
    Zhou, Xiaolong
    Jiang, Fengwei
    Che, Li
    [J]. Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics, 2019, 41 (06): : 1210 - 1217
  • [5] One-Shot Object Detection Based on Cross-Domain Learning
    Feng Jiawei
    Chu Jinghui
    Lu Wei
    [J]. LASER & OPTOELECTRONICS PROGRESS, 2023, 60 (04)
  • [6] Recursive Spoken Instruction-Based One-Shot Object and Action Learning
    Scheutz, Matthias
    Krause, Evan
    Oosterveld, Bradley
    Frasca, Tyler
    Platt, Robert
    [J]. PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2018, : 5354 - 5358
  • [7] Deep Learning-Based Action Classification Using One-Shot Object Detection
    Yoo, Hyun
    Lee, Seo-El
    Chung, Kyungyong
    [J]. CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 76 (02): : 1343 - 1359
  • [8] Vision-Based One-Shot Imitation Learning Supplemented with Target Recognition via Meta Learning
    Yang, Xuyun
    Peng, Yueyan
    Li, Wei
    Wen, James Zhiqing
    Zhou, Decheng
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION (IEEE ICMA 2021), 2021, : 1008 - 1013
  • [9] Object Detection-Based One-Shot Imitation Learning with an RGB-D Camera
    Shao, Quanquan
    Qi, Jin
    Ma, Jin
    Fang, Yi
    Wang, Weiming
    Hu, Jie
    [J]. APPLIED SCIENCES-BASEL, 2020, 10 (03):
  • [10] Spoken Instruction-Based One-Shot Object and Action Learning in a Cognitive Robotic Architecture
    Scheutz, Matthias
    Krause, Evan
    Oosterveld, Brad
    Frasca, Tyler
    Platt, Robert
    [J]. AAMAS'17: PROCEEDINGS OF THE 16TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2017, : 1378 - 1386