High Precision Automatic Alignment and its Computer Vision Technology

1989 ◽  
Vol 1 (3) ◽  
pp. 220-226
Author(s):  
Tohru Tanigawa ◽  
◽  
Toshitsugu Sawai ◽  
Tadashi Nakao

Recently, industrial robotics and computer vision technology has become very important in flexible manufacturing systems and automated factories. Especially high precision automatic alignment technology beyond human ability is essential to some manufactures, and its application fields are extending rapidly. This paper describes the high precision automatic alignment system of large-sized LCD panels. The features of the system are (1) high precision and high speed detection of position using the special alignment mark, (2) high contrast image obtained by the use of ultraviolet rays, (3) new image-processing algorithms for improvement of system reliability.

2014 ◽  
Vol 644-650 ◽  
pp. 207-210
Author(s):  
Shuang Liu ◽  
Xiang Jie Kong ◽  
Ming Cai Shan

Binocular parallax vision system is a kind of computer vision technology. Two cameras on different locations can get two different pictures of same object. The space position of the object can be calculated by the parallax information of two different pictures. The binocular parallax vision technology includes cameras calibration, image processing, and stereo matching analysis. The paper will introduce the inside and outside parameters calibration methods, and combing the traffic applications, designed the calibrating scheme. The parameters that obtained according to the scheme can meet the demands of measuring the vehicle distance. The high precision can meet the needs of intelligent transportation vehicles in a security vehicles spacing survey, which is an effective way for measuring the front car distance.


Author(s):  
X. W. Ye ◽  
T. Jin ◽  
P. Y. Chen

The computer vision technology has gained great advances and applied in a variety of industry fields. It has some unique advantages over the traditional technologies such as high speed, high accuracy, low noise, anti-electromagnetic interference, etc. In the last decade, the technology of computer vision has been widely employed in the field of structure health monitoring (SHM). Many specific hardware and algorithms have been developed to meet different kinds of monitoring demands. This chapter presents three application scenarios of computer vision technology for health monitoring of engineering structures, including bridge inspection and evaluation with unmanned aerial vehicle (UAV), recognition and surveillance of foreign object intrusion for railway system, and identification and tracking of concrete cracking. The principles and procedures of three application scenarios are addressed following with the experimental study, and the possibilities and ideas for the application of computer vision technology to other monitoring items are also discussed.


Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1349
Author(s):  
Zhiyuan Sun ◽  
Linlin Huang ◽  
Ruiqing Jia

In coal production, the raw coal contains a large amount of gangue, which affects the quality of coal and pollutes the environment. Separating coal and gangue can improve coal quality, save energy, and reduce consumption and make rational use of resources. The separated gangue can also be reused. Robots with computer vision technology have become current research hotspots due to simple equipment, are efficient, and create no pollution to the environment. However, the difficulty in identifying coal and gangue is that the difference between coal and gangue is small, and the background and prospects are similar. In addition, due to the irregular shape of gangue, real-time grasping requirements make robot control difficult. This paper presents a coal and gangue separating robot system based on computer vision, proposes a convolutional neural network to extract the classification and location information, and designs a robot multi-objective motion planning algorithm. Through simulation and experimental verification, the accuracy of coal gangue identification reaches 98% under the condition of ensuring real-time performance. The average separating rate reaches 75% on low-, medium-, and high-speed moving conveyor belts, which meets the needs of actual projects. This method has important guiding significance in detection and separation of objects in complex scenes.


Sign in / Sign up

Export Citation Format

Share Document