Zeng Bing, Zhou Yu, He Dilin, Zhou Zhihao, Hao Shitao, Yi Kexin, Li Zhilong, Zhang Wenhua, Xie Yunmin
Nanchang Institute of Technology, Nanchang 330099, China.
State Grid Shanghai Municipal Electric Power Company Maintenance Company, Shanghai 200063, China.
Sensors (Basel). 2024 Sep 12;24(18):5910. doi: 10.3390/s24185910.
Aiming at the problems of a large volume, slow processing speed, and difficult deployment in the edge terminal, this paper proposes a lightweight insulator detection algorithm based on an improved SSD. Firstly, the original feature extraction network VGG-16 is replaced by a lightweight Ghost Module network to initially achieve the lightweight model. A Feature Pyramid structure and Feature Pyramid Network (FPN+PAN) are integrated into the Neck part and a Simplified Spatial Pyramid Pooling Fast (SimSPPF) module is introduced to realize the integration of local features and global features. Secondly, multiple Spatial and Channel Squeeze-and-Excitation (scSE) attention mechanisms are introduced in the Neck part to make the model pay more attention to the channels containing important feature information. The original six detection heads are reduced to four to improve the inference speed of the network. In order to improve the recognition performance of occluded and overlapping targets, DIoU-NMS was used to replace the original non-maximum suppression (NMS). Furthermore, the channel pruning strategy is used to reduce the unimportant weight matrix of the model, and the knowledge distillation strategy is used to fine-adjust the network model after pruning, so as to ensure the detection accuracy. The experimental results show that the parameter number of the proposed model is reduced from 26.15 M to 0.61 M, the computational load is reduced from 118.95 G to 1.49 G, and the mAP is increased from 96.8% to 98%. Compared with other models, the proposed model not only guarantees the detection accuracy of the algorithm, but also greatly reduces the model volume, which provides support for the realization of visible light insulator target detection based on edge intelligence.
针对边缘终端存在的体积大、处理速度慢、部署困难等问题，本文提出了一种基于改进SSD的轻量级绝缘子检测算法。首先，将原始特征提取网络VGG - 16替换为轻量级Ghost模块网络，初步实现模型轻量化。在Neck部分集成特征金字塔结构和特征金字塔网络（FPN + PAN），并引入简化空间金字塔池化快速（SimSPPF）模块，实现局部特征与全局特征的融合。其次，在Neck部分引入多个空间和通道挤压与激励（scSE）注意力机制，使模型更加关注包含重要特征信息的通道。将原来的6个检测头减少为4个，以提高网络的推理速度。为了提高对遮挡和重叠目标的识别性能，采用DIoU - NMS替换原来的非极大值抑制（NMS）。此外，使用通道剪枝策略减少模型中不重要的权重矩阵，并采用知识蒸馏策略在剪枝后对网络模型进行微调，以确保检测精度。实验结果表明，所提模型的参数数量从26.15M减少到0.61M，计算量从118.95G减少到1.49G，mAP从96.8%提高到98%。与其他模型相比，所提模型不仅保证了算法的检测精度，还大幅减小了模型体积，为基于边缘智能的可见光绝缘子目标检测的实现提供了支持。
