Fusion Transformer Model-Based Segmentation Algorithm for Laser Point Cloud of Distribution Lines

doi:10.12141/j.issn.1000-565X.240542

Abstract

Abstract:

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.

Key words: Transformer model, distribution line channel, feature fusion, laser point cloud, neural network

CLC Number:

TM863

DAI Zhou, LIU Yan, MAO Xianyin, GUO Tao, XU Lianggang, CHENG Guixian. Fusion Transformer Model-Based Segmentation Algorithm for Laser Point Cloud of Distribution Lines[J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(5): 139-146.

Figures/Tables 13

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Table 1

Table 2

Fig.6

Table 3

Table 4

Table 5

Table 6

Table 7

References 28

1	袁宸胤，陈泉智，陈力．多物理量传感的输电线路安全距离测量及数据在线融合处理技术［J］．电子器件，2023，46（2）：548-586．
	YUAN Chenyin， CHEN Quanzhi， CHEN Li ．Transmission line safety distance measurement and data online fusion processing technology based on multi physical quantity sensing［J］．Chinese Journal of Electron Devices，2023，46（2）：548-586．
2	范长俊，刘伟诚．基于三维激光扫描的风电机组塔筒倾斜及结构形变检测应用［J］．广东电力，2022，35（10）：29-35．
	FAN Changjun， LlU Weicheng ．Detection on inclination and structural deformation of fan tower tube based on 3D laser scanning［J］．Guangdong Electric Power，2022，35（10）：29-35．
3	易琳，王柯，钱金菊．搭载于无人机的电力廊道数据采集系统设计［J］．广东电力，2020，33（4）：120-125．
	YI Lin， WANG Ke， QIAN Jinju ．Design of UAV-airborne power corridor data acquisition system［J］．Guangdong Electric Power，2020，33（4）：120-125．
4	刘传洋，吴一全．基于深度学习的输电线路视觉检测方法研究进展［J］．中国电机工程学报，2023，43（19）：7423-7445．
	LIU Chuanyang， WU Yiquan ．Research progress of vision detection methods based on deep learning for transmission lines［J］．Proceedings of the CSEE，2023，43（19）：7423-7445．
5	彭浚桓．基于图像分割的启发式无人机配电线巡检规划［D］．北京：华北电力大学（北京），2022．
6	TANG W， YANG Q， DAI Z，et al ．Module defect detection and diagnosis for intelligent maintenance of solar photovoltaic plants：techniques，systems and perspectives［J］．Energy，2024（297）：131222．
7	邵瑰玮，刘壮，付晶，等．架空配电线路无人机巡检技术研究进展［J］．高电压技术，2020，46（1）：14-22．
	SHAO Guiwei， LIU Zhuang， FU Jing，et al ．Research progress in unmanned aerial vehicle inspection techno-logy on overhead transmission lines［J］．High Voltage Engineering，2020，46（1）：14-22．
8	刘兰兰，李勃铖，毛盾，等．基于卫星遥感影像的线树距离测量与树障预警技术［J］．南方电网技术，2021，15（8）：130-138．
	LIU Lanlan， LI Bocheng， MAO Dun，et al ．Line-tree distance measurement and tree barrier early warning technology based on satellite remote sensing monitoring［J］．Southern Power System Technology，2021，15（8）：130-138．
9	刘长磊．基于改进运动恢复结构的配电线路倾斜影像重建方法［J］．广东电力，2023，36（6）：94-101．
	LIU Changlei ．Oblique image reconstruction method of transmission lines based on improved motion recovery structure［J］．Guangdong Electric Power，2023，36（6）：94-101．
10	ZHOU Y， TUZEL O ．VoxelNet：end-to-end learning for point cloud based 3D object detection［C］∥Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition．Salt Lake City：IEEE，2018：4490-4499．
11	MATURANA D， SCHERER S ．VoxNet：a 3D convolutional neural network for real-time object recognition［C］∥Proceedings of IEEE/RSJ International Confe-rence on Intelligent Robots and Systems．Hamburg：IEEE，2015：922-928．
12	RIEGLER G， ULUSOY A O， GEIGER A ．OctNet：learning deep 3D representations at high resolutions［C］∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition．Honolulu：IEEE，2017：6620-6629．
13	SU H， MAJI S， KALOGERAKIS E，et al ．Multi-view convolutional neural networks for 3D shape recognition［C］∥Proceedings of IEEE International Confe-rence on Computer Vision．Santiago：IEEE，2015：945-953．
14	GOYAL A， LAW H， LIU B W，et al ．Revisiting point cloud shape classification with a simple and effective baseline［C］∥Proceedings of the 38th International Conference on Machine Learning．Online：Cornell University，2021：3809-3820．
15	CHARLES R Q， HAO S， MO K C，et al ．Guibas，PointNet：deep learning on point sets for 3D classification and segmentation［C］∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition．Honolulu：IEEE，2017：77-85．
16	QI C， YI L， SU H，et al ．PointNet++：deep hierarchical feature learning on point sets in a metric space［C］∥Proceedings of the 31st International Conference on Neural Information Processing Systems．Long Beach：［s.n.］，2017：5105-5114．
17	LI Y， BU R， SUN M，et al ．PointCNN：convolution on X-transformed points［C］∥Proceedings of the 32nd International Conference on Neural Information Processing Systems．Montreal：［s.n.］，2018：828-838．
18	LIU Y， FAN B， XIANG S，et al ．Relation-shape convolutional neural network for point cloud analysis［C］∥Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition．Long Beach：IEEE，2019：8887-8896．
19	LIU Z， HU H， CAO Y，et al ．A closer look at local aggregation operators in point cloud analysis［C］∥Proceedings of the 16th European Conference on Computer Vision．Glasgow：Springer International Publishing AG，2020：326-342．
20	WANG Y， SUN Y， LIU Z，et al ．Dynamic graph CNN for learning on point clouds［J］．ACM Transactions on Graphics，2019，38（5）：1-12．
21	XIANG T， ZHANG C， SONG Y，et al ．Walk in the cloud：learning curves for point clouds shape analysis［C］∥Proceedings of the IEEE/CVF International Conference on Computer Vision．Montreal：IEEE，2021：895-904．
22	GUO M， CAI J， LIU Z，et al ．PCT：point cloud transformer［J］．Computational Visual Media，2021，7（2）：187-199．
23	ZHAO H， JIANG L， JIA J，et al ．Point transformer［C］∥Proceedings of IEEE/CVF International Confe-rence on Computer Vision．Montreal：IEEE，2021：16239-16248．
24	LIU Z， LIN Y， CAO Y，et al ．Swin transformer：hierarchical vision transformer using shifted windows［C］∥Proceedings of IEEE/CVF International Confe-rence on Computer Vision．Montreal：IEEE，2021：9992-10002．
25	PARK N， KIM S ．How do vision transformers work？［C］∥Proceedings of the 10th International Conference on Learning Representations．Online：［s.n.］，2022：1-26．
26	DONG Y， WEI P， WANG R，et al ．Hiding image with inception transformer［J］．IET Image Processing，2024，18（13）：3961-3975．
27	LIU Y， TIAN B， LV Y，et al ．Point cloud classification using content-based transformer via clustering in feature space［J］．IEEE/CAA Journal of Automatica Sinica，2023，11（1）：231-239．
28	HU Q， YANG B， XIE L，et al ．RandLA-Net：efficient semantic segmentation of large-scale point clouds［J］．IEEE Transactions on Pattern Analysis and Machine Intelligence，2022，44（11）：8338-8354．

部件	训练集点数量	验证集点数量
导线	562 316	140 579
杆塔	943 162	235 790
绝缘子	72 693	18 173
其他	84 632 352	21 158 088

平台	参数
显卡	NVIDIA A100
显存	80 GB
CPU	Intel（R） Xeon（R） Silver 4208 CPU @ 2.10 GHz
操作系统	Ubuntu20.04
深度学习平台	Pytorch

模型	数据增强方式			P_m/%	R_m/%	I_m/%
模型	Ⅰ	Ⅱ	Ⅲ	P_m/%	R_m/%	I_m/%
1				73.69	87.52	60.49
2	√			73.83	88.29	60.21
3		√		74.28	88.94	60.98
4			√	69.36	85.52	60.32
5	√	√		74.68	89.36	64.59
6	√		√	73.29	88.41	63.56
7		√	√	72.16	85.93	61.39
8	√	√	√	73.51	87.76	62.63

模型编号	MLP模块	高频模块	低频模块	P_m/%	R_m/%	I_m/%
1	√			27.82	39.63	26.35
2		√		57.38	68.53	51.72
3			√	68.16	82.29	59.63
4	√	√		62.57	73.48	53.39
5	√		√	71.22	84.73	60.76
6		√	√	73.65	86.81	61.23
7	√	√	√	74.68	89.36	64.59

模块数量	P_m/%	R_m/%	I_m/%
2	62.45	73.39	49.73
3	70.34	81.75	58.32
4	74.68	89.36	64.59
5	73.28	89.75	64.63
6	74.21	89.34	63.64
7	73.31	88.68	63.12