基于三维图像特征的矸石含煤率在线检测方法

On-line detection of coal content in gangue based on 3D image features

矸石含煤率是选煤生产的关键指标之一,目前还不能在线检测。因此,提出一种基于机器视觉和粒子群支持向量机的新方法来检测矸石含煤率。首先将采集到的矸石胶带上的单目图像进行分割,识别出属于煤和矸石类别的各个区域。从各区域中提取出尺寸特征参数和密度特征参数,分别得到煤和矸石的特征参数,再将矸石的特征参数除以煤的特征参数,得到样本图片的二维特征参数。同时在胶带上采集双目图像,获取图像的高度信息,计算高度比三维图像特征,通过计算Pearson相关系数筛选出八个最优特征,最后利用支持向量机预测矸石含煤率并通过粒子群优化算法对模型进行优化。建立平面特征模型与三维特征模型,对比分析两个模型的预测结果,三维特征模型的性能明显优于平面特征模型,平均相对误差为7.57%。

The coal content of gangue is one of the key indicators of coal preparation production,while it cannot be detected online at present. A new method based on machine vision and a particle swarm optimization-support vector machine( PSOSVM) was proposed to detect the coal content of gangue. First,the sample pictures on the gangue belt are segmented to identify the areas belonging to the category of coal and gangue. The size feature parameters and density feature parameters are extracted from each region. The characteristic parameters of coal and gangue are obtained respectively,and then the feature parameters of the gangue are divided by the feature parameters of coal to obtain the two-dimensional feature parameters of the sample picture.At the same time,the binocular images are collected on the belt,the height information of the image is obtained,the height ratio 3D image characteristics are calculated. Eight optimal features are screened by calculating the Pearson correlation coefficient,and finally the support vector machine is used to predict the coal content of the gangue and optimize it through particle swarm optimization. A plane feature model and a 3D feature model are established,prediction results of the two models are compared,and performance of the 3D feature model is significantly better with an average relative error of 7. 57%.