ENGD-BiFPN: a remote sensing object detection model based on grouped deformable convolution for power transmission towers

The object detection of transmission towers is of great significance for transmission and transformation channel monitoring, engineering evaluation, operation and maintenance management. This paper aims to detect different types of transmission towers in satellite remote sensing images according to the characteristics of transmission tower shadow. However, different shooting angles lead to great changes in the shape of the tower shadow. At the same time, the shadows of different types of towers may be very similar. In order to further improve the accuracy of object detection, we first conduct the image preprocessing and image enhancement. Then, the deformable convolution is introduced to better extract the features of transmission tower shadow. At the same time, in order to neutralize the influence of the increase of model parameters caused by deformable convolution, this paper introduces the idea of grouped convolution and proposes a modified bi-directional feature pyramid network (GD-BiFPN) based on the grouped deformable convolution (GDConv). Finally, a lightweight satellite remote sensing object detection model for transmission towers with accuracy up to 96% is implemented with EfficientNet as the backbone and GD-BiFPN as the enhanced feature extraction network. Through ablation and comparison experiments, the effectiveness and advancement of the proposed model in transmission tower remote sensing object detection are verified.