Skip to main navigation Skip to main content
  • E-Submission

JKSPE : Journal of the Korean Society for Precision Engineering

OPEN ACCESS
ABOUT
BROWSE ARTICLES
EDITORIAL POLICIES
FOR CONTRIBUTORS
SPECIAL

산업용 검사장비 비전 센서 기술 동향

Vision Sensor Technology Trends for Industrial Inspection System

Journal of the Korean Society for Precision Engineering 2021;38(12):897-904.
Published online: December 1, 2021

1 한국광기술원 지능형광학모듈연구센터

1 Intelligent Optical Module Research Center, Korea Photonics Technology Institute

#E-mail: jpark@kopti.re.kr, TEL: +82-62-605-9257
• Received: August 30, 2021   • Revised: October 8, 2021   • Accepted: October 12, 2021

Copyright © The Korean Society for Precision Engineering

This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

  • 8 Views
  • 0 Download
  • 1 Crossref
  • 1 Scopus
prev next

Citations

Citations to this article as recorded by  Crossref logo
  • Image Data-based Product Classification and Defect Detection
    Hye-Jin Lee, Do-Gyeong Yuk, Jung Woo Sohn
    Transactions of the Korean Society for Noise and Vibration Engineering.2022; 32(6): 601.     CrossRef

Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:

Include:

Vision Sensor Technology Trends for Industrial Inspection System
J. Korean Soc. Precis. Eng.. 2021;38(12):897-904.   Published online December 1, 2021
Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:
Include:
Vision Sensor Technology Trends for Industrial Inspection System
J. Korean Soc. Precis. Eng.. 2021;38(12):897-904.   Published online December 1, 2021
Close

Figure

  • 0
  • 1
  • 2
  • 3
  • 4
  • 5
Vision Sensor Technology Trends for Industrial Inspection System
Image Image Image Image Image Image
Fig. 1 Schematic illustrations of vision sensor technology. (a) 1D, 2D and 3D scan vision sensors classified according to scanning methods, (b) A machine learning architecture to classify objects
Fig. 2 Schematic illustrations of (a) line scan vision senor, and (b) time-delayed integration line scan vision sensor. A reconstructed image is obtained by merging images acquired from staggered image sensors in the TDI vision sensor
Fig. 3 Schematic illustrations of (a) Prism line scan vision sensor composed of color image sensors (Blue, green, red), and (b) Beam splitter prism. The color line scan vison sensor without prism categorized with (c) trilinear line scan, and (d) bilinear line scan respect to the pixel size
Fig. 4 A schematic illustration of 2D scan vison sensor based on zoom optics. A resolution of 2D scan vison system depends on both field of view and size of pixel
Fig. 5 Schematic illustrations of 3D scan vision sensor. (a) 3D imaging through stereo vision. (b) Acquisition of 3D information by using pattern projection, (c) 3D TOF sensor for 3D depth estimation, and (d) 3D surface imaging based on alight field camera
Fig. 6 A schematic illustration of deep-learning based inspection system. After capturing images through vision sensor, feature points are extracted by image processing algorithms. The inspection system finally estimates the object through the classification of trained data
Vision Sensor Technology Trends for Industrial Inspection System

Comparison of specifications according to the imaging principles of vision sensor

Imaging principle Resolution/Working
distance
Speed Ref.
TDI line scan camera with
a bayer filter matrix
1,280 Pixels per
row/ -
Line rate
[kHz]: 100
47
Color multi-line scan
sensor
2,048 Pixels per
row/ -
Line rate
[kHz]: 200
22
Stereo vision with
MEMS scanner
- /65-120 mm Scanning speed
[Hz]: 136
48
Stereo vision with
micro-prism arrays
1,280 × 1,024
pixels/10-100 mm
- 49
Structured light imaging
with dammann-grating
64 × 64 Spot Array/
- 150 mm
Frame rate
[fps]: 5
50
Time-of-fight imaging
with MEMS scanner
256 × 64 pixels/
up to 20 m
Frame rate
[fps]: 10
51
Light field imaging for pin
& connector inspection
10 μm/170-350 mm Frame rate
[fps]: 30
45
Light field imaging for
pick & place robotics
160 μm/450-2,
100 mm
Frame rate
[fps]: 30
45
Table 1 Comparison of specifications according to the imaging principles of vision sensor