A Defect Detection Method Based on BC-YOLO for Transmission Line Components in UAV Remote Sensing Images

Abstract

Vibration dampers and insulators are important components of transmission lines, and it is therefore important for the normal operation of transmission lines to detect defects in these components in a timely manner. In this paper, we provide an automatic detection method for component defects through patrolling inspection by an unmanned aerial vehicle (UAV). We constructed a dataset of vibration dampers and insulators (DVDI) on transmission lines in images obtained by the UAV. It is difficult to detect defects in vibration dampers and insulators from UAV images, as these components and their defective parts are very small parts of the images, and the components vary greatly in terms of their shape and color and are easily confused with the background. In view of this, we use the end-to-end coordinate attention and bidirectional feature pyramid network “you only look once” (BC-YOLO) to detect component defects. To make the network focus on the features of vibration dampers and insulators rather than the complex backgrounds, we added the coordinate attention (CA) module to YOLOv5. CA encodes each channel separately along the vertical and horizontal directions, which allows the attention module to simultaneously capture remote spatial interactions with precise location information and helps the network locate targets of interest more accurately. In the multiscale feature fusion stage, different input features have different resolutions, and their contributions to the fused output features are usually unequal. However, PANet treats each input feature equally and simply sums them up without distinction. In this paper, we replace the original PANet feature fusion framework in YOLOv5 with a bidirectional feature pyramid network (BiFPN). BiFPN introduces learnable weights to learn the importance of different features, which can make the network focus more on the feature mapping that contributes more to the output features. To verify the effectiveness of our method, we conducted a test in DVDI, and its mAP@0.5 reached 89.1%, a value 2.7% higher than for YOLOv5.

CN-YOLO: cascaded network based defect detection approach for insulator aerial images with complex background

“…In order to enhance the spatial and location information of insulator defects and eliminate the inconsistent information features between feature layers, this paper redesigns the neck structure of network and compares evaluation indexes with four different neck structures: FPN-PAN, BiFPN, 36 FPNNet-ASFF, 37 and GOLD-Net, 38 to verify the superiority and effectiveness of the proposed CRFPN-MATT. The evaluation metric results are shown in Table 3.…”

Real‐time defect detection method based on YOLO‐GSS at the edge end of a transmission line

“…Reference [7] developed a spatial region attention block and introduced a multitask framework, combining a RPN to create AGMNet for component detection in transmission lines. Reference [8] improved the YOLOv5 algorithm using an end‐to‐end attention mechanism and a bidirectional feature pyramid network to achieve high‐precision identification of vibration dampers and insulators in transmission lines. In reference [9], typical defects in transmission lines were accurately identified by introducing attention mechanisms and a small object detection layer into the YOLOv5 algorithm.…”

Improved algorithm for small target detection in remote sensing images based on YOLOv5s

“…To address the detection problems in remote sensing images, researchers have continuously proposed improvements based on YOLOv5: HOU Y [11] proposed adding the MS Transformer module to enhance the algorithm's feature extraction ability and improve detection performance; Bao W [12] added an attention mechanism to enhance the algorithm's focus on effective features in complex backgrounds; Liu C [13] added multiple attention mechanisms to better utilize features and improve detection performance. The above algorithms have achieved certain results in remote sensing image detection tasks, but their performance is still lacking when detecting small targets.…”