Image Processing of Vacuum Arc Based on Two-dimensional Segmentation Algorithm

摘要

The processing technology of the arc image is an effective and direct way to study the arc variation. The accuracy of the subsequent arc feature extraction is related to the segmentation of arc image. A two-dimensional algorithm is applied to the image processing of vacuum arc in this paper. The intermediate-frequency vacuum arc has been captured by the high speed camera. The arc images are processed by the dual-threshold adaptive segmentation algorithm. The genetic algorithm is applied to obtain the optimal solution and the parameters of the two-dimensional space. Compared with the traditional subjective threshold, the threshold of this two-dimensional algorithm is self-adaptive. The arc image can be divided into the high energy plasma zone, the contour area and the background area. The results showed that the two-dimensional algorithm proposed in this paper can be used to segment the arc image at the whole combustion stage.