Image online monitoring technology has been widely used in transmission lines inspection, but the intelligent and efficient foreign object detection still has a gap with the ideal. In this paper, we propose a deep learning method to detect invading foreign objects for power transmission line inspection. Specifically, we design our network based on the regression strategy with oriented bounding boxes to accurately predict spatial location and orientation angle of foreign objects, as well as their categories in cluttered backgrounds. Moreover, an easy yet effective Scale Histogram Matching method is proposed to be applied to the publicly available dataset, allowing useful patterns to be exploited to detect tiny foreign objects during the pretraining procedure and boosting detection performance even with limited annotated samples. Besides, we construct an image dataset that contains common foreign objects in transmission line scenarios to evaluate proposed methods, on which experiment results show our full model achieves accuracy with 88.1% mean Average Precision (mAP). Additionally, the efficient and compact network structure allows our network to run in real-time, which provides possibilities for practical use. INDEX TERMS Image online monitoring technology, power transmission line inspection, deep learning, oriented bounding boxes, scale histogram matching.

In this paper, we study the conducted interference to an electronic current transformer introduced in the process of bus-charging currents which are caused by switching a gas insulated switchgear (GIS) disconnector. To cope with these issues, the EMTP-ATP and Matlab/Simulink software are used to carry out equivalent modeling simulations and experimental research, respectively. More specifically, the very fast transient current generated by disconnector switching (DS) is used as the input source of the equivalent simulation model of the Rogowski coil, and the characteristics of conducted interference waveforms of the Rogowski coil, the active integrator and filter outputs under single and multiple breakdowns are analyzed step by step. Moreover, several anti-interference methods are proposed to improve the resistance to the high-voltage and high-frequency conducted interference for the Rogowski coil, such as reducing the Rogowski cut-off frequency, increasing the transient voltage suppressor (TVS), active filter, and Cy capacitor. Besides, the study also reveals that the residual charge of the integral capacitor will discharge with a time constant τ = 1 s after arc quenching with the first-order discharge circuit, which is composed of the feedback resistance and the integral capacitor C. Lastly, the experimental results demonstrate the correctness of the modeling method proposed in this paper and the effectiveness of anti-interference measures.