As laser point cloud models are crucial for distribution line inspection and management, most distribution channels have constructed laser point cloud models at present. With the increase of the number of models, extracting key component locations (e. g., conductors, insulators) becomes vital. In order to enhance the accuracy and efficiency of segmenting key components such as lines, towers and insulators, this paper presents a segmentation algorithm for laser point cloud of distribution lines based on a fusion Transformer model. Given the need for detailed features in the point clouds of distribution lines, a dual-channel parallel feature extraction module is designed to capture high-frequency and low-frequency features. The low-frequency features are processed via average pooling and a fusion Transformer-based extractor, while the high-frequency features are handled through max pooling and a multi-layer perceptron (MLP) module with convolutional layers. The feature vectors from both channels are then fused to improve the ability of detail feature extraction. Additionally, the fused features are fed back into the MLP module for further refinement, achieving precise point cloud target segmentation. Extensive experiments demonstrate the accuracy and effectiveness of the proposed algorithm. It has potential advantages in many aspects, such as improving the inspection accuracy of unmanned aerial vehicles, enhancing the level of automation, improving the robustness, integrating multi-source data and reducing inspection costs.

A differential chaos shift keying scheme that fuses noise reduction with full carrier indexing (FCI-DCSK-NR) is proposed for power-line channels. The scheme integrates noise reduction and full-carrier index techniques into differential chaos shift keying (DCSK) modulation to effectively tackle the complex power line channel environment, especially the interference caused by impulsive noise. Firstly, in this scheme, all subcarriers except the reference carrier are divided into two categories, namely Type-1 active carriers and Type-2 active carriers. The two types of carriers are distinguished via index bits; the carriers selected by the index bits serve as Type-1 active carriers, while the remaining subcarriers function as Type-2 active carriers. Subsequently, Type-1 and Type-2 active carriers transmit Type-1 and Type-2 modulation bits using chaotic signals and their Hilbert-transformed signals, respectively. Moreover, identical information is transmitted in multiple distinct time slots at the transmitter, and the received replicas are averaged at the receiver to mitigate impulsive noise. A closed-form bit-error-rate (Bit error rate, BER) expression for FCI-DCSK-NR over power line channels is derived and verified by Monte-Carlo simulations. Analytical and numerical results show that the proposed scheme effectively mitigates impulse noise in power line channels. Compared to traditional DCSK and Generalized Carrier Index DCSK (GCI-DCSK) schemes, the proposed method exhibits improvements in both BER performance and data rate. Additionally, this experimental scheme is well-suited for integration into training programs of power grid companies, universities, and research institutes, contributing to the cultivation of relevant technical talent.