煤矿视频监控图像的改进非局部均值滤波算法

Improved non-local means filtering algorithm for video monitoring image of coal mine

针对井下光线较差、粉尘大而导致视频监控图像清晰度不佳的问题,提出了一种改进非局部均值滤波算法。首先采用Log边缘检测算子对图像进行边缘提取,获得边缘和非边缘图像;然后分别从相似图像块获取方法以及权重值计算方法2个方面对非局部均值滤波算法进行改进,用于去除非边缘图像中的噪声点;最后将边缘图像与滤波后的非边缘图像进行融合。分别采用该算法与中值滤波算法、均值滤波算法、非局部均值滤波算法对现场采集的图像进行测试,结果表明该算法的图像处理效果明显优于其他算法。

For unclear underground video monitoring image caused by poor light and a lot of dust, an improved non-local means filtering algorithm was proposed. Firstly, video monitoring images are processed by Log edge extraction operator, so as to extract edge information of the images, and edge images and non- edge images are obtained. Then, non-local means filtering algorithm is improved from the perspective of extraction method of similar image blocks and weighting calculation method, and the improved algorithm is adopted to filter noise in the non-edge images. Finally, the edge images and the filtered non-edge images are fused. Median filtering algorithm, average filtering algorithm, non-local means filtering algorithm and the improved algorithm were used to deal with field images. The test results indicate that the improved algorithm has better image processing effect than the other algorithms.