Analyzing point cloud of coal mining process in much dust environment based on dynamic graph convolution neural network

A Big Coal Block Alarm Detection Method for Scraper Conveyor Based on YOLO-BS

With the aim of solving the problem of coal congestion caused by big coal blocks in underground mine scraper conveyors, in this paper we proposed the use of a YOLO-BS (YOLO-Big Size) algorithm to detect the abnormal phenomenon of coal blocks on scraper conveyors. Given the scale of the big coal block targets, the YOLO-BS algorithm replaces the last layer of the YOLOv4 algorithm feature extraction backbone network with the transform module. The YOLO-BS algorithm also deletes the redundant branch which detects small targets in the PAnet module, which reduces the overall number of parameters in the YOLO-BS algorithm. As the up-sampling and down-sampling operations in the PAnet module of the YOLO algorithm can easily cause feature loss, YOLO-BS improves the problem of feature loss and enhances the convergence performance of the model by adding the SimAM space and channel attention mechanism. In addition, to solve the problem of sample imbalance in big coal block data, in this paper, it was shown that the YOLO-BS algorithm selects focal loss as the loss function. In view of the problem that the same lump coal in different locations on the scraper conveyor led to different congestion rates, we conducted research and proposed a formula to calculate the congestion rate. Finally, we collected 12,000 image datasets of coal blocks on the underground scraper conveyor in Daliuta Coal Mine, China, and verified the performance of the method proposed in this paper. The results show that the processing speed of the proposed method can reach 80 fps, and the correct alarm rate can reach 93%. This method meets the real-time and accuracy requirements for the detection of abnormal phenomena in scraper conveyors.

Research on imaging method of driver's attention area based on deep neural network

In the driving process, the driver's visual attention area is of great significance to the research of intelligent driving decision-making behavior and the dynamic research of driving behavior. Traditional driver intention recognition has problems such as large contact interference with wearing equipment, the high false detection rate for drivers wearing glasses and strong light, and unclear extraction of the field of view. We use the driver's field of vision image taken by the dash cam and the corresponding vehicle driving state data (steering wheel angle and vehicle speed). Combined with the interpretability method of the deep neural network, a method of imaging the driver's attention area is proposed. The basic idea of this method is to perform attention imaging analysis on the neural network virtual driver based on the vehicle driving state data, and then infer the visual attention area of the human driver. The results show that this method can realize the reverse reasoning of the driver's intention behavior during driving, image the driver's visual attention area, and provide a theoretical basis for the dynamic analysis of the driver's driving behavior and the further development of traffic safety analysis.