Research on vision detection technology based on photometric calibration

By using an automatic piston ring separator based on advanced computer vision detection technology, the end gaps of piston rings can be automatically measured with high efficiency and accuracy. To get a complete and accurate image of the end gap as well as measurement reliability, the positioning of the end gap of a piston ring must be accurate every time it is photographed. During the loading process, a mechanical structure and pneumatic actuators are used to provide the correct initial position and guide the motion. The actuators also control the deflection of the piston ring and get the top surface levels of the piston rings evened up at the detection position to ensure the correct detection position and imaging object plane. This guarantees the quality of the images of the end gaps. Data compensation is carried out to decrease the system errors arising from manufacturing errors in ring gauges and increasemeasurement accuracy. Experimental results show that the measurement accuracy meets the demands well, and measurement reliability is good.

Download Full-text

B-Spline Wavelets Vision Detection Technology Based on Adaptive Filter

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.198-199.284 ◽

2012 ◽

Vol 198-199 ◽

pp. 284-287

Author(s):

Ya Lin Ye ◽

Ning Shan ◽

Qian Zhang ◽

Ke Li Yang

Keyword(s):

Computer Vision ◽

Edge Detection ◽

Adaptive Filter ◽

B Spline ◽

Spline Wavelets ◽

Detection Technology ◽

Vision Detection

Edge is the most important information for computer vision. Wavelets edge detection can reduce noise disturbing, and also loses weak edging. This paper presents a new algorithm for edge detection. Based on sharping imaging edging by adaptive filter algorithm, the algorithm can detect edge by B-spline wavelets. This new algorithm has more higher precision than those normal algorithms.

Download Full-text

Research on Real-time Vision Detection Technology for Motion Feature of High-speed Mechanical System

Journal of Mechanical Engineering ◽

10.3901/jme.2016.02.082 ◽

2016 ◽

Vol 52 (2) ◽

pp. 82 ◽

Cited By ~ 2

Author(s):

Yaodong WANG

Keyword(s):

Mechanical System ◽

Real Time ◽

High Speed ◽

Motion Feature ◽

Detection Technology ◽

Vision Detection

Download Full-text

Research on Visual Detection Algorithm of 500kV High Voltage Live Operating Robot

Journal of Physics Conference Series ◽

10.1088/1742-6596/2087/1/012093 ◽

2021 ◽

Vol 2087 (1) ◽

pp. 012093

Author(s):

Suping Guo ◽

Jun Deng ◽

Yahui Fan ◽

Sijing Dai

Keyword(s):

Transmission Line ◽

High Voltage ◽

Visual Detection ◽

Detection Algorithm ◽

Operating Efficiency ◽

Detection Technology ◽

Power Operation ◽

Low Efficiency ◽

Working Device ◽

Vision Detection

Abstract The 500kV transmission line is exposed to the outdoor for a long time. It is affected by complex climate charge change and other factors which leads to line connection parts bolt loosening, wire breaking and fixture damage and other line failures. In order to ensure the stable transmission of electric energy, power operators need to wear shielding suits and work in the high-risk and high-voltage environment. Use of electric power operation robot instead of manual operation is an effective way to liberate maintenance staff labor. But robots still have some problems such as low degree of automation and low efficiency of power operation. Machine vision detection technology in recent years has been widely used in major areas including deep learning as emerging visual detection technology shows excellent performance. In this paper, the vision detection algorithm is studied respectively for the bolt fastening end working device and wire repairing end working device of the live transmission line robot to improve the operating efficiency of the robot.

Download Full-text

On-line image readout in CTEM

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100169730 ◽

1994 ◽

Vol 52 ◽

pp. 400-401

Author(s):

K.-H. Herrmann ◽

W. D. Rau ◽

R. Sikeler

Keyword(s):

Primary Electron ◽

Digital Information ◽

Electron Hole ◽

Detection Technology ◽

Long Time ◽

On Line ◽

Electron Image ◽

Optical Transfer ◽

Detection Quantum Efficiency ◽

Technical Solutions

Quantitative recording of electron patterns and their rapid conversion into digital information is an outstanding goal which the photoplate fails to solve satisfactorily. For a long time, LLL-TV cameras have been used for EM adjustment but due to their inferior pixel number they were never a real alternative to the photoplate. This situation has changed with the availability of scientific grade slow-scan charged coupled devices (CCD) with pixel numbers exceeding 106, photometric accuracy and, by Peltier cooling, both excellent storage and noise figures previously inaccessible in image detection technology. Again the electron image is converted into a photon image fed to the CCD by some light optical transfer link. Subsequently, some technical solutions are discussed using the detection quantum efficiency (DQE), resolution, pixel number and exposure range as figures of merit.A key quantity is the number of electron-hole pairs released in the CCD sensor by a single primary electron (PE) which can be estimated from the energy deposit ΔE in the scintillator,

Download Full-text