为了较好地实现变电站电气设备红外图像的分割，采用了一种自适应的变电站电气设备红外图像分割方法。通过采用基于形态学的权重自适应算法对变电站电气设备红外图像进行增强处理，然后采用基于加权切比雪夫距离的 K-means算法对变电站电气设备红外图像进行分割，最后对分割得到的二值图像采用形态学方法进行处理。通过实验验证了该方法的有效性和适应性，方便了后续的特征提取和识别。

In order to achieve the segmentation of substation electrical equipment infrared image better, an adaptive substation electrical equipment infrared image enhancement and segmentation algorithm was adopted in the paper. An adaptive weight algorithm based on morphological was used to enhance the infrared image of substation electrical equipment, then the K-means algorithm based on weighted Chebyshev distance was used for segmentation of substation electrical equipment infrared image, lastly the morphological method was used to deal with the segmented binary image. The arithmetic was validated by experiment later, and this method is convenient for follow-up feature extraction and recognition.