一种改进的瓷套式电缆终端红外图像边缘提取算法  

An Improved Algorithm Based on Infrared Image Edge Extraction of Cable Terminal

作　　者：徐涛[1] 吴倩 牛海清[1] 郭然[1] 余佳[1] 郑文坚[1] 

机构地区：[1]华南理工大学电力学院,广州510641 [2]广州供电局有限公司,广州510310

出　　处：《电瓷避雷器》2016年第6期26-31,共6页Insulators and Surge Arresters

摘　　要：红外热像仪测温是电气设备状态检测的重要手段。在实际应用中,存在红外图像边缘粗糙模糊、噪声干扰严重等缺点,这给红外图像处理带来了极大的不便,为此提出一种基于改进Sobel算子和自适应最佳阈值的边缘提取算法。该算法利用八方向模板的Sobel算子对含有噪声的红外图像进行高温目标区域的边缘提取;通过广义高斯分布(GGD)描述图像的小波子带系数,并基于其间系数的局部领域信息进行方差估计,由此得到自适应最佳去噪阈值;结合改进Sobel算子和最佳阈值,最终得到所需边缘提取图像。MATLAB仿真结果表明:该算法在有效检测红外图像边缘信息的同时,极大提高了图像的抗噪能力。The infrared thermal imaging technology is an important means of condition monitoring for electrical equipment. The infrared image edge has defects of coarse, fuzzy, serious noise and so on in the practical applications, which brings great inconvenience to the infrared image processing. Therefore, an adaptive optimal threshold edge extraction algorithm based on improved Sobel operator is proposed. The edge extraction is made in the high temperature area of infrared image contained noise by using eight direction Sobel operators in the algorithm; At the same time, the wavelet coefficients in sub- band are described by general Gaussian distribution and the variance is estimated from the local neighborhood information of sub-band wavelet coefficients so that the adaptive optimal denoising threshold can be obtained; Finally, the needed edge extraction infrared image is got by combining with improved Sobel operator and the optimal threshold. Matlab simulation results show that the algorithm can effectively detect the edge information of infrared image and greatly improve the ability to resist noise of the image.

关 键 词：红外图像 改进Sobel算子 最佳阈值 边缘提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]