The Research Of Image Detection System Of Fiber Tape Laying Based On Computer Vision

Automated tape laying is a mature process and is widely being used in the composite material molding technology. It is very important to control precision and detect the defect in the process of laying the fiber. It is essential to detect the spacing between the fibers under the same angle of the fiber laid. Experiments prove that the spacing between the fibers could affect the mechanical property of the composite material. To meet the specified design goals and to improve product quality, the adjacent bands on the lay-up surface must be closed together and there must be no gaps or overlaps between the bands.The design is based on the precision control of composite material in the fiber laying, if it can control the precision automation, we will be able to improve production efficiency and product quality, reduce production costs and save money. With the computer vision and digital image technology development, fiber laying accuracy of automatic detection which based on image processing and computer platforms is made possible. The detection system based on computer vision always has many advantages such as high speediness, high precision, contactless measure, etc. In some cases, it can replace the inspection of the people. The detection system obtains the image information with a camera and a visual controller, image pre-processing by the visual processor. PC achieves the accuracy of detection and identification in the fiber laying.The system used the DirectShow technology to capture the video sequence of the laying through the camera controlled by the visual controller. The image process is the emphasis of the detection system. To enhance the quality of the image, the system eliminate the noise, suppress useless information and highlight the edge features through the effective image preprocessing, including histogram equalization to image enhancement, median filtering to filter noise, Canny edge detection to image processing. The different threshold values for Canny edge detection in the Hough line detection is to be able to extract the real edge line. The gap detection algorithm is proposed using the least squares linear fitting, but replaced by the projection center way in order to shorten the real time. The effect and detection accuracy of these algorithms above-mentioned are tested by experiments respectively. To get the relation between the pixel distance in image and actual range, the program of camera is calibrated by selecting a distorted non-linear camera calibration model, the calibration experiment is implemented on the basis of OpenCV and Matlab, Camera calibration sets up the relationship between the pixel distance in image and actual range, and the error caused by camera's distortion is estimated.Finally, the software for the tape laying detection is realized on the basis of MFC and OpenCV. The study of the technique which is used to construct the image detection system of tape laying is of much practical value.