基于改进PSO-Otsu的电气设备红外图像分割算法

Infrared Image Segmentation Algorithm for Electrical Equipment Based on Improved PSO-Otsu

红外图像分割对于电气设备的热故障检测至关重要。鉴于红外图像存在图像模糊、分辨率不高等缺点,为了增强红外图像的清晰度,改进红外图像分割效果,文章提出一种基于改进PSO优化的Otsu电气设备红外图像分割方法。该方法首先使用Sobel算子锐化图像;其次通过PSO-Otsu算法对电气设备红外图像进行分割;最后依据红外图像的特征优化PSO-Otsu算法中的参数,提高算法运行效率。实验结果表明,所提算法分割后的图像轮廓清晰,可识别性高,在图像分割效果和分割速度上都优于对比算法,能够满足对电气设备红外图像实时处理的需求。

Infrared image segmentation is crucial for thermal fault detection of electrical equipment.In view of the infrared images have the disadvantages of blurring and low resolution,in order to enhance the clarity of infrared images and improve the effect of infrared image segmentation,the paper proposes an Otsu electrical equipment infrared image segmentation method based on the improved PSO optimization.Firstly,the image is sharpened by Sobel operator.Secondly,the infrared image of electrical equipment is segmented by PSO-Otsu algorithm.Finally,the parameters in PSO-Otsu algorithm are optimized according to the characteristics of infrared image to improve the operation efficiency of the algorithm.The experimental results show that the images segmented by the algorithm proposed in this paper have clear contours and high recognizability.And it is better than the comparison algorithm in terms of image segmentation effect and segmentation speed,and can meet the demand for real-time processing of infrared images for electrical equipment.