IEEE Transactions on Pattern Analysis and Machine Intelligence
A Fast Line Finder for Vision-Guided Robot Navigation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Extraction of Straight Lines in Aerial Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Finding Line Segments by Stick Growing
IEEE Transactions on Pattern Analysis and Machine Intelligence
Line detection in images through regularized hough transform
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
Laser welding requires quite high trajectory accuracy of articulated welding robot. To increase this dynamic trajectory accuracy, a novel 3D seam tracking method is proposed based on stereo visual feedback control, in which a key task is to detect the seam from the vision image. To improve the precision and efficiency of the GPI seam-detecting method, this paper proposed a new method, the multi-step gray projecting integral (MSGPI) method with a circular sub-window. This method applies a circular division in image as the sub-window for detection and the means of GPI values, based on while surpassing the Standard GPI method. It adopts a link table to store edge points gained by Sobel filtering previously to reduce the amount of computation. A threshold method is employed to effectively eliminate noises caused by scratching and rust. The searching range of the line's angle in GPI process is divided into coarse searching and fine searching, which not only ensures detection accuracy but also greatly reduces the amount of computation. The experimental results show that the MSGPI method can achieve rapid and accurate detection for weld seam even if the seam is quite narrow, and can thus greatly improve the trajectory accuracy of industrial robot for laser welding, and the system using this method could meet the demand of high accuracy trajectory tracking.