基于区域对比和随机森林的设备故障红外图像敏感区域提取

Infrared Image ROI Extraction Based on Region Contrast and Random Forest

基于红外图像的设备故障诊断需要从图像中选择敏感区域,由于红外图像具有干扰背景多、对比度低的特点,敏感区域提取过程中需要进行背景移除和图像分割,但常用的二值化分割算法在分割红外图像时易出现过分割问题。因此,本文提出了基于区域对比和随机森林的敏感区域提取方法。首先使用区域对比方法对红外图像进行显著性检测,以去除干扰背景;然后通过OTSU算法进行图像分割,实现敏感区域初步提取;最后结合随机森林分类结果对图像分割过程的阈值进行迭代优化,实现敏感区域的优化提取。经过转子实验台6种不同状态的红外图像数据验证,将本文方法提取出的故障敏感区域用于故障诊断时,分类的准确率提高了3.3个百分点,比人工选择的区域更加准确。

For the infrared image-based fault diagnosis,the region of interest(ROI)needs to be selected.Due to the characteristics of many interference background and low contrast in infrared image,it is necessary to remove the background and image segmentation to extract ROI.However,the common two value segmentation algorithm has the limitation of over-segmentation in the infrared image segmentation.Therefore,a method of infrared image ROI extraction based on region contrast and random forest is proposed in this paper.Firstly,the region contrast method is used to detect the infrared image significantly to remove the interference background.Then,image segmentation is conducted by applying OTSU algorithm in order to extract ROIinitially.Finally,aiming at realizing the optimal extraction of ROI,the threshold of image segmentation based on the results of random forest classification is iterated and optimized.Infrared images under 6 different conditions derived from the rotors test-bed are utilized for fault diagnosis,applying the ROI extracted by the proposed method to fault diagnosis,the accuracy of the classification increased by 3.3 percentage points,which is more accurate than that of the artificial selected area.