Dense distribution and significant size difference of transmission line connecting fittings are difficult to maintain, and long-term exposure to the outdoor environment is vulnerable to adverse environmental effects of rust failure. The common image processing methods and deep learning algorithms are not competent for this kind of dense small target detection task, so the target detection model based on an image processing hierarchical algorithm is proposed in this paper, which uses anchor free and decoupled head design ideas, through ASFF multi-scale information feature fusion strategy and ECA + Varifocal Loss interactive saliency area capture strategy to construct a dense small target detection network suitable for a complex environment. The experimental results show that the comprehensive performance of Deformable YOLOX is superior to 13 current advanced target detection algorithms. Compared with the baseline model, Deformable YOLOX can better understand the multi-scale semantic information of the image and learn the small details that are more difficult to distinguish. Combined with a target detection algorithm, an early warning algorithm for rust grade assessment of connecting fittings is proposed, and an online monitoring system is designed, which has practical engineering application value.
20 May 2024 in IEEE Transactions on Instrumentation and Measurement
To address the low accuracy and moderate speed of traditional foreign object detection in transmission line image inspection, the FusionNet is proposed based foreign object detection algorithm in severe weather. First, the FB module(Fusion Block) is proposed in this algorithm, combined with the CA attention(Coordinate Attention) 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 FSB module (Fusion Speed Block)is proposed to extract the space more efficiently. In addition, the FMB module(Fusion Memory Block) 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 detection precision. Experimental results show that on the dataset in this paper, the improved algorithm mAP@0.5 reaches 98.27%, the model parameters are reduced by 130.42M compared with the Faster-RCNN model, and the accuracy is improved by 19.62% and 4.63% compared with SSD and YOLOv7 models, respectively. The performance on the 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 to 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.
26 December 2023 in IET Generation, Transmission & Distribution
The distribution of transmission lines is complex, influenced by terrain and topography, making their maintenance and management challenging. With the advancement of global mechanization, various types of construction machinery and large‐scale mechanical equipment are continually increasing. Accidental contact of construction machinery near transmission lines poses a serious threat to the stability of the power system. Traditional drones and inspection robots face difficulties in achieving real‐time monitoring of construction machinery and equipment around transmission lines, quickly identifying potential risks. Conventional image processing techniques and convolutional neural networks struggle with effective handling of small targets and densely packed detection tasks involving multiple targets. To address these challenges, this paper proposes an intelligent detection algorithm Swin Transformer attention efficient algorithm‐you only look once (YOLO) (STAE‐YOLO). It is based on the Swin Transformer global self‐attention mechanism, cross‐channel fusion attention mechanism, enhanced small object detection framework, and a focused and efficient regression loss function. The experimental results show that the STAE‐YOLO algorithm model improved by 6.3% in mean average precision, 3.7% in precision, and 3.1% in recall compared to the baseline model. Meanwhile, deploying the window multi‐head self‐attention global self‐attention mechanism in the model can strengthen the global multi‐scale semantic information in detection.
9 May 2024 in Journal of Real-Time Image Processing