Search

This paper proposes a lightweight coal and gangue detection algorithm based on Yolov7-tiny for the current target detection algorithms, which have problems such as large model computation, low detection accuracy and low real-time detection performance. Firstly, we make cuts for the ShuffleNetV2 network and replace the Stage1 and Stage2 layers with CONV convolutional blocks to construct a new backbone network that improves the speed of feature extraction. Secondly, the neck of the original model is redesigned by fusing the original two paths of up-sampling and down-sampling into one path, introducing the CBAM attention mechanism to further improve the information extraction, fusion and interaction capabilities of the model, and the detection heads are reduced from three to two to improve the real-time inference capability of the model. Finally, SIoU is used to replace the loss function of the original network to improve the convergence ability and robustness of the model. The experimental results show that the accuracy and FPS of the lightweight model proposed in this paper reach 0.981 and 208, respectively. The improved model has higher real-time and accuracy, and the reduction of computation provides the possibility of deploying it on the edge devices. [ABSTRACT FROM AUTHOR]

Meter reading recognition is an important link for robots to complete inspection tasks. To solve the problems of low detection accuracy and inaccurate localization of current meter reading recognition algorithms, the YOLOV7-SSWD (YOLOV7–SiLU–SimAM–Wise-IoU–DyHeads) model is proposed, a novel detection model based on the multi-head attention mechanism, which is improved on the YOLOV7-Tiny model. First, the Wise-IoU loss function is used to solve the problem of sample quality imbalance and improve the model's detection accuracy. Second, a new convolutional block is constructed using the SiLU activation function and applied to the YOLOV7-Tiny model to enhance the model's generalization ability. The dynamic detection header is then built as the header of YOLOV7-Tiny, which realizes the fusion of multi-scale feature information and improves the target recognition performance. Finally, we introduce SimAM to improve the feature extraction capability of the network. In this paper, the importance of each component is fully verified by ablation experiments and comparative analysis. The experiments showed that the mAP and F1-scores of the YOLOV7-SSWD model reached 89.8% and 0.84. Compared with the original network, the mAP increased by 8.1% and the F1-scores increased by 0.1. The YOLOV7-SSWD algorithm has better localization and recognition accuracy and provides a reference for deploying inspection robots to perform automatic inspections. [ABSTRACT FROM AUTHOR]

Intelligent sorting of coal and gangue is of great significance to the intelligent construction of coal mines as well as green development. In this study, we propose a coal and gangue segmentation method with an improved classical segmentation network Mask R‐CNN, denoted as Multichannel Forward‐Linked Confusion Convolution Module (MFCCM)‐Mask R‐CNN. First, we design a MFCCM to construct the feature extraction network by stacking, second, we design a multiscale high‐resolution feature pyramid network structure to realize multipath fusion of feature information to enhance the position and contour information of the target, and finally, we propose a multiscale Mask head to enhance the diversity of information, and capture the more representative and unique features. Training and testing models using self‐built RGB coal and gangue data sets, the accuracy of the improved algorithm reaches 97.38%, which is an improvement of 1.66% compared to the original model. Compared with other segmentation models Unet, Deeplab V3+, Yoloact, Yolov7, and the model after replacing the backbone network, the MFCCM‐Mask R‐CNN has higher precision and recall, and can more accurately realize the efficient segmentation of coal and gangue. [ABSTRACT FROM AUTHOR]

It is vital to differentiate between coal and gangue in coal mining effectively. In recent years, classification methods for images of coal‐ and gangue‐based convolutional neural networks have emerged, which makes the analysis process simple and fast. However, these methods still have the limitation of balancing recognition performance and computational efficiency due to the limitation of device hardware. This research proposes a group convolution and channel shuffle augmentation Ghost network (GSAGNet) for the classification task of coal and gangue images. First, we design a new Ghost module with group convolution and channel shuffle to improve the stability of the Ghost module for better extraction of features of coal and gangue. Second, we redesign GhostNet to improve the model's classification accuracy while guaranteeing similar floating‐point operations. Finally, an efficient channel attention module is embedded in the prediction output of the model to improve the model's prediction results further. Extensive experiments on actual image datasets of coal and gangue show the feasibility and superiority of our proposed GSAG module. The GSAG module is applied to models such as AlexNet, VGG13, and ResNet50, and the accuracy of the models is improved by 0.27%, 1.24%, and 1.25%, respectively, compared to the Ghost module. The classification accuracy and F1‐score of the proposed GSAGNet model reach 97.50% and 97.50%, respectively, which are 1.01% and 1.04% higher than that of GhostNet. The GSAGNet model in this study can classify coal and gangue efficiently, which can effectively enable the separation of underground coal and gangue and has specific practical application significance and value. [ABSTRACT FROM AUTHOR]

Aiming at the problems of insufficient attention to spatial information, long classification training time, and high model complexity in current gangue image classification algorithms, a lightweight fast recognition model for gangue based on improved MobileNetV3-small is proposed. First, we optimize the feature extraction part by introducing the CeLU activation function to alleviate the neuron death and gradient vanishing problems, thus improving the performance of the model. Second, Bneck is further optimized using an improved Triplet Attention Module to achieve almost parameter-free spatial and channel dimension interactions, which drastically reduces the complexity of the model. Finally, we construct a new Efficient Last Stage structure, which improves the model performance while successfully reducing the computation and model size by replacing the traditional convolution with Ghost Module and introducing Mix-pool as a pooling layer. In addition, the effectiveness of each component was fully demonstrated through ablation experiments, visualization analysis, and comparative experiments. The experimental results show that training the homemade gangue dataset using the improved MobilenetV3-small model improves Accuracy and F1-Score on the validation set by 0.48% and 0.42%, respectively, compared to the original network, and in terms of model complexity, we can see that FLOPs, number of parameters, and Weight size are reduced by 2.8%, 33.0%, and 32.3%, respectively, and FPS reaches 28 frames per second. The improved algorithm greatly reduces the model complexity and decreases the dependence on hardware devices while improving the classification accuracy and anti-interference capability. This provides an important reference basis for deploying automated underground coal gangue sorting, which helps to realize intelligent integrated mining. [ABSTRACT FROM AUTHOR]