FusionNet: Detection of Foreign Objects in Transmission Lines During Inclement Weather

To address the low accuracy and moderate speed of traditional foreign object detection in transmission line image inspection, the FusionNet is proposed based on the foreign object detection algorithm in severe weather. First, the fusion block (FB) module is proposed in this algorithm, combined with the coordinate attention (CA) mechanism and the Hardswish activation function, so that the network can increase the learning of the location information based on the attention on the overall classification information and reduce the network parameters. Then, based on FasterNet, the fusion speed block (FSB) module is proposed to extract the space more efficiently. In addition, the fusion memory block (FMB) module is proposed, which makes full use of the accumulated information in the past to extract more accurate and abundant features. Finally, the utilization of EfficiCIoU as a loss function serves to expedite model convergence and enhance the detection precision. Experimental results show that on the dataset in this article, the improved algorithm mean average precision (mAP@0.5) reaches 98.27%, the model parameters are reduced by 130.42M compared with the Faster-region with CNN feature (RCNN) model, and the accuracy is improved by 19.62% and 4.63% compared with single shot multibox detector (SSD) and YOLOv7 models, respectively. The performance on China Power Line Insulator Dataset (CPLID) is also excellent, reaching 99.17% mAP@0.5, an improvement of 1.85% compared with the baseline model. Compared with the existing models, the FusionNet model is smaller in size and has higher detection accuracy. It can accurately detect targets in inclement weather and perform the task of foreign body detection in transmission lines.