Distribution line insulators play a key role in electrical insulation and supporting lines in distribution lines. Insulator defects due to overvoltage, thermal stress, and environmental pollution may trigger power transmission instability and line collapse, thus threatening the safe operation of distribution networks. However, distribution line insulators often present detection challenges due to their compact dimensions, diverse flaw types, and frequent installation in populated areas with visually cluttered environments. The combination of these factors, including small defect sizes, varying failure patterns, and complex background interference, in both urban and rural settings, creates significant difficulties for precise defect identification in these critical components. In response to these challenges, this paper proposes a defect recognition algorithm for distribution line insulators based on the improved YOLO11 model. Firstly, the algorithm combines the detection head of the original model with the Adaptively Spatial Feature Fusion (ASFF) module to effectively fuse defect features at different resolution levels and improve the model’s ability to recognize multi-scale defect features. Secondly, a Bidirectional Feature Pyramid Network (BiFPN) replaces the FPN + PAN structure of the original model to achieve a more effective transfer of contextual information in order to facilitate the model’s efficiency in performing defect feature fusion, and the Convolutional Block Attention Module (CBAM) Attention mechanism is embedded in the BiFPN output so that the model is able to give priority attention to defective features on insulators in complex recognition environments. Finally, the ShuffleNetV2 module is used to reduce the parameters of the improved model by replacing the large-parameter C3k2 module at the end of the backbone network for easy deployment on lightweight and small devices. The experimental results show that the improved model performs well in the distribution line insulator defect detection task, with an accuracy precision (AP) and mean accuracy precision (mAP) of 97.0% and 98.1%, respectively, which are 1.4% and 0.7% higher than the original YOLO11 model.

To address the challenges of high missed detection rates for minute transmission line defects, strong complex background interference, and limited computational power on edge devices in UAV-assisted power line inspection, this paper proposes a lightweight improved YOLOv12 real-time detection model. First, a Bidirectional Weighted Feature Fusion Network (BiFPN) is introduced to enhance bidirectional interaction between shallow localization information and deep semantic features through learnable feature layer weighting, thereby improving detection sensitivity for line defects. Second, a Cross-stage Channel-Position Collaborative Attention (CPCA) module is embedded in the BiFPN’s cross-stage connections, jointly modeling channel feature significance and spatial contextual relationships to effectively suppress complex background noise from vegetation occlusion and metal reflections while enhancing defect feature representation. Furthermore, the backbone network is reconstructed using ShuffleNetV2’s channel rearrangement and grouped convolution strategies to reduce model complexity. Experimental results demonstrate that the improved model achieved 98.7% mAP@0.5 on our custom transmission line defect dataset, representing a 3.0% improvement over the baseline YOLOv12, with parameters compressed to 2.31M (8.3% reduction) and real-time detection speed reaching 142.7 FPS. This method effectively balances detection accuracy and inference efficiency, providing reliable technical support for unmanned intelligent inspection of transmission lines.

In ultra-high-speed networks, identifying hosts with high source or destination cardinality, or large cardinality changes, provides compact measurements for network monitoring and security analysis. Currently, schemes for super-host identification have demonstrated good performance, and most of them target one type of super host. However, real networks contain multiple types of super hosts with different distributions. Supporting source cardinalities, destination cardinalities, and inter-cycle changes within one memory-bounded structure requires coordinating measurement and address recovery. To address this challenge, we present H-TD Sketch, a novel sketch structure that enables rapid and accurate identification of multiple super-host types under limited memory constraints by maintaining counts of both source and destination cardinalities. The H-shaped Bloom filter and information groups enable direct traceability of super-host addresses at the end of the measurement cycle. We conduct a theoretical analysis of H-TD Sketch, covering its space and time complexity and the accuracy of its cardinality estimates. We evaluate cardinality estimation and super-host identification on a CPU platform using real-world CAIDA traces. We also integrate H-TD Sketch into Open vSwitch and evaluate its packet-processing throughput using generated traffic. Our experimental findings demonstrate that H-TD Sketch exhibits superior accuracy and performance in both host-cardinality estimation and super-host identification tasks.