Study on recognition of coal and gangue based on multimode feature and image fusion

Abstract

Aiming at the problems of low accuracy of coal gangue recognition and difficult recognition of mixed gangue rate, a coal rock recognition method based on modal fusion of RGB and infrared is proposed. A fully mechanized coal gangue transportation test bed is built, RGB images are obtained by camera, and infrared images are obtained by industrial microwave heating system and infrared thermal imager. the image data of the whole coal, whole gangue, and coal gangue with different gangue mixing as training and test samples, identify the released coal gangue and its mixing rate. The AlexNet, VGG-16, ResNet-18 classification networks and their convolutional neural networks with modal feature fusion are constructed. results: The classification accuracy of ResNet networks on RGB and infrared image data is higher than AlexNet and VGG-16 networks. The early convergence network performance of ResNet is verified through the convergence of different models. The recognition rate of the network is 97.92 the confusion matrix statistics, which verifies the feasibility of the application of modal fusion method in the field of coal gangue recognition. The fusion of modal features and early models of ResNet coal gangue, which is the basic premise for realizing intelligent coal caving.