MBFILNet: A Multi-Branch Detection Network for Autonomous Mining Trucks in Dusty Environments

As a critical technology of autonomous mining trucks, object detection directly determines system safety and operational reliability. However, autonomous mining trucks often work in dusty open-pit environments, in which dusty interference significantly degrades the accuracy of object detection. To overcome the problem mentioned above, a multi-branch feature interaction and location detection network (MBFILNet) is proposed in this study, consisting of multi-branch feature interaction with differential operation (MBFI-DO) and depthwise separable convolution-enhanced non-local attention (DSC-NLA). On one hand, MBFI-DO not only strengthens the extraction of channel-wise semantic features but also improves the representation of salient features of images with dusty interference. On the other hand, DSC-NLA is used to capture long-range spatial dependencies to focus on target-object structural information. Furthermore, a custom dataset called Dusty Open-pit Mining (DOM) is constructed, which is augmented using a cycle-consistent generative adversarial network (CycleGAN). Finally, a large number of experiments based on DOM are conducted to evaluate the performance of MBFILNet in dusty open-pit environments. The results show that MBFILNet achieves a mean Average Precision (mAP) of 72.0% based on the DOM dataset, representing a 1.3% increase compared to the Featenhancer model. Moreover, in comparison with YOLOv8, there is an astounding 2% increase in the mAP based on MBFILNet, demonstrating detection accuracy in dusty open-pit environments can be effectively improved with the method proposed in this paper.