针对高压巡检车视觉获取路径信息的问题.由于噪声掩盖了电线在图像中的成像特征,给获取路径信息带来了很大的困难且影响了循迹的精度,所以提出了一种基于灰度距离加权的自适应中值滤波方法来滤除图像噪声.该方法经预先滤波后,再通过噪声检测确定噪声点及其个数,自适应的调整稀疏分布模板,最后根据模板内灰度距离而赋予各像素点不同的权重值而滤除噪声.实验结果表明,该算法所加权重值简单易实现,在很好的滤除噪声且较好的保护图像细节,还能较好的滤除图像随机噪声,使得其可很好的应用于路径图像的噪声滤除.%In the process of repairing and maintaining high voltage transmission lines, the visual distance measuring system is used to obtain the distance information between people and high-voltage wires because of accidental electric shock caused by the workers crossing the safe distance. As the noise mask the image characteristics of the wire, it is very difficult to obtain the distance information and affects the accuracy of distance measuring, therefore, the weighting median filtering method of based on gray-scale distance is proposed to filter out image noise in this paper. In the algorithm, first by the pre-filter, and then, noise detection is utilized to determine the number of noise points. Base on the number of noise points to adaptively adjust sparse distribution templates. Finally, according to the gray-scale distance within the template to give each pixel a different weight value, and remove noise. The experiment shows that the weighted weight of the algorithm is simple and easy to achieve, and it can protect the detail of image well while removing the noise, and filter out random noise. So that it can be applied to actual image noise filtering based on visual distance measuring in power scene.
展开▼
