Deep Learning-Based Object Detection for Digital Inspection in the Mining Industry

In the mining industry, belt conveyors are essential for transporting large quantities of materials efficiently and inexpensively. The rollers are one of the main components of a belt conveyor. Their maintenance and operation are critical for material transportation during the mining activities. Despite that, its inspection has been done in the same way for almost 20 years, with little technological innovation. The inspection of the belt conveyor rollers automatically via object detection and thermal imaging can improve this process. Therefore, we propose a new system capable of running the detection of defective rollers in real time and with better precision and recall metrics than those of previous works. We based the object detection models on the YOLOv2 deep learning architecture. Comparing our results with previous work, we observe reductions on false discovery and false negative rates of 52.46% and 61.03%, respectively. We also evaluated three computing infrastructures, and the GPU-based one was the only that enabled real-time performance.