Identification Method of Top Plate Pallet of Underground Roadways in Coal Mines Based on Improved Faster R-CNN

Abstract Pallets are an important feature in intelligent coal mine applications based on machine vision technology such as coal mine roadway roof monitoring and automatic equipment positioning, where whether pallets can be accurately identified is the key to such application technology. A roof pallet recognition method based on improved Faster R-CNN is designed. Firstly, the ResNet50 network with better feature extraction effect is selected to replace the VGG16 feature extraction network in the original Faster R-CNN model; Secondly, according to the aspect ratio of pallets and incomplete pallets, the candidate box size in the region suggestion network is optimized based on K-means++ clustering algorithm to fit the pallet size, so that the model can accurately locate the borders; finally, for the coal mine underground environment, low visibility and other problems that affect the pallet is difficult to be detected, the attention mechanism module is introduced in the feature extraction network ResNet50 to enhance the saliency of the pallet in the image and strengthen the attention of the network to the pallet, thus improving the efficiency and accuracy of pallet detection. In the simulated roadway, the AGV trolley is used to simulate the roadheader, and the tray image is collected by the airborne camera for the test. The proposed algorithm is compared with three classical algorithms. The experimental results show that the improved Faster R-CNN model has good robustness, and the average mean accuracy (mAP) of recognizing pallets is 92.53%, which is 7.59% higher than the original Faster R-CNN network.