Data-driven model SSD-BSP for multi-target coal-gangue detection

Recent rapid advancements in the coal industry have led to the development of intelligent visual coal-gangue sorting. Combining deep learning and machine vision can effectively improve the accuracy of coal-gangue detection; however, the increasing model complexity also increases the computational cost. In order to achieve fast and accurate detection, a coal-gangue detection model driven by data optimisation for multi-target detection tasks is proposed in this paper. To this end, a multi-object coal-gangue image synthesis model named BSP is also proposed. Combining BSP with SSD enables fast and accurate coal gangue detection. Compared to the original SSD model, the proposed model improved the detection accuracy by 7%; compared with the structure-optimised object detection model, the proposed model is almost two times faster while exceeding the accuracy by 0.46%. The proposed model effectively improved detection accuracy and achieved fast detection of coal and gangue.

Automated summary

Recent advancements in the coal industry have led to the development of intelligent visual coal-gangue sorting, which combines deep learning and machine vision to improve the accuracy of coal-gangue detection. In this paper, a coal-gangue detection model driven by data optimization for multi-target detection tasks is proposed, along with a multi-object coal-gangue image synthesis model called BSP. The proposed model improves detection accuracy by 7% compared to the original SSD model and achieves almost two times faster detection with higher accuracy compared to the structure-optimized object detection model.