基于图神经网络的变电站场景三维目标检测

doi:10.3778/j.issn.1002-8331.2111-0264

摘要/Abstract

摘要： 在变电站三维场景中，对巡检人员和带电设备的精确定位与识别是提高人员安全管控水平的前提。针对变电站复杂场景中目标定位与识别不准的问题，提出了一种基于图神经网络的变电站场景三维目标检测方法。该方法基于point-GNN结构设计，在顶点特征提取阶段，提出PCS（point-channel-sphere）注意力结构，提取更加丰富的关键点特征信息；在GNN边缘特征聚合阶段，采用统筹性池化机制，兼顾最大池化和均值池化从而获取更丰富的全局特征；改进模型损失函数，将Focal Loss作为分类损失使训练更加关注前景点，将DIoU Loss作为回归损失使回归任务更高效。在自建的变电站场景数据集上进行训练与测试，实验表明该方法mAP值达到73.81%，优于基准模型，能够改善变电站场景中目标的检测效果，对提高人员安全管控水平具有一定的实用价值。

关键词: 图神经网络, 三维目标检测, 点云, 注意力, 统筹性池化, 损失函数

Abstract: In the three-dimensional scene of a substation，the precise positioning and identification of inspectors and live equipment is a prerequisite for improving the level of personnel safety management and control. Aiming at the problem of inaccurate target positioning and recognition in complex scenes of substations, a method of 3D object detection in substation scene based on graph neural network is proposed. The method is designed based on the point-GNN structure. In the vertex feature extraction stage, the PCS（point-channel-sphere） attention structure is proposed to extract more abundant key point feature information. In the GNN edge feature aggregation stage, an overall pooling mechanism is adopted to take into account the maximum pooling and the mean pooling to obtain richer global features, improving the model loss function, using Focal Loss as the classification loss to make the training pay more attention to the previous scenic spots, and using DIoU Loss as the regression loss to make the regression task more efficient. Training and testing on the self-built substation scene dataset, experiments show that the mAP value of this method reaches 73.81%, which is better than the benchmark model. It can improve the detection effect of objects in the substation scene and has certain practical value for improving the level of personnel safety management and control.

Key words: graph neural network, 3D object detection, point cloud, attention, overall pooling, loss function

张婷, 张兴忠, 王慧民, 杨罡, 王大伟. 基于图神经网络的变电站场景三维目标检测[J]. 计算机工程与应用, 2023, 59(9): 329-336.

ZHANG Ting, ZHANG Xingzhong, WANG Huimin, YANG Gang, WANG Dawei. 3D Object Detection in Substation Scene Based on Graph Neural Network[J]. Computer Engineering and Applications, 2023, 59(9): 329-336.

参考文献

[1] 刘一凡.基于机器视觉的变电站检修区域监测关键技术研究[D].保定：河北农业大学，2018.
LIU Y F.The key technology of substation maintenance area monitoring based on machine vision[D].Baoding：Hebei Agricultural University，2018.
[2] 胡文慧.无人值班变电站智能视频监控系统的设计与实现[D].长春：吉林大学，2015.
HU W H.Design and implementation of intelligent video monitoring system for unattended substation[D].Changchun：Jilin University，2015.
[3] 郭琳，马玫.基于视频监控的变电站远方辅助巡视操作系统[J].信息系统工程，2017（1）：23-24.
GUO L，MA M.Remote auxiliary patrol operating system of substation based on video surveillance[J].China CIO News，2017（1）：23-24.
[4] 马一鸣.智能巡检机器人在无人值守变电站的应用[D].保定：华北电力大学，2017.
MA Y M.The application of intelligent inspection robot in unattended substation[D].Baoding：North China Electric Power University，2017.
[5] 罗俊豪，颜雨薇.变电站自动巡检机器人系统及其关键技术[J].电气应用，2014（13）：80-84.
LUO J H，YAN Y W.Automatic inspection robot system for substation and its key technology[J].Electrotechnical Application，2014（13）：80-84.
[6] LIU Z，ZHAO X，HUANG T，et al.TaNet：robust 3D object detection from point clouds with triple attention[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020，34（7）：11677-11684.
[7] 侯向丹，于习欣，刘洪普.基于图卷积网络的三维点云分类分割模型[J].激光与光电子学进展，2020，57（18）：181019.
HOU X D，YU X X，LIU H P.3D point cloud classification and segmentation model based on graph convolutional network[J].Laser & Optoelectronics Progress，2020，57（18）：181019.
[8] 徐俊，杜宣萱，宋俊锋，等.融合图注意力的摄影测量点云语义分割研究[J].小型微型计算机系统，2022，43（7）：1464-1470.
XU J，DU X X，SONG J F，et al.Research on semantic segmentation of photogrammetric point clouds with image attention[J].Journal of Chinese Computer Systems，2022，43（7）：1464-1470.
[9] 赵毅强，艾西丁·艾克白尔，陈瑞，等.基于体素化图卷积网络的三维点云目标检测方法[J].红外与激光工程，2021（10）：273-281.
ZHAO Y Q，ARXIDIN·A，CHEN R，et al.3D point cloud object detection method in view of voxel based graph convolution network[J].Infrared and Laser Engineering，2021（10）：273-281.
[10] YANG B，LUO W，URTASUN R.Pixor：real-time 3D object detection from point clouds[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7652-7660.
[11] SIMONY M，MILZY S，AMENDEY K，et al.Complex-YOLO：an euler-region-proposal for real-time 3D object detection on point clouds[C]//Proceedings of the European Conference on Computer Vision（ECCV）Workshops，2018.
[12] BELTRáN J，GUINDEL C，MORENO F M，et al.Birdnet：a 3D object detection framework from lidar information[C]//Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems（ITSC），2018：3517-3523.
[13] CHEN X，MA H，WAN J，et al.Multi-view 3D object detection network for autonomous driving[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：1907-1915.
[14] ZHOU Y，TUZEL O.Voxelnet：end-to-end learning for point cloud based 3d object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：4490-4499.
[15] LI B.3D fully convolutional network for vehicle detection in point cloud[C]//Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems（IROS），2017：1513-1518.
[16] ENGELCKE M，RAO D，WANG D Z，et al.Vote3deep：fast object detection in 3D point clouds using efficient convolutional neural networks[C]//Proceedings of the 2017 IEEE International Conference on Robotics and Automation（ICRA），2017：1355-1361.
[17] SHI S，WANG Z，WANG X，et al.Part-a 2 net：3D part-aware and aggregation neural network for object detection from point cloud[J].arXiv：1907.03670，2019.
[18] SHI S，WANG X，LI H.Pointrcnn：3D object proposal generation and detection from point cloud[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：770-779.
[19] YANG Z，SUN Y，LIU S，et al.3DSSD：point-based 3d single stage object detector[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：11040-11048.
[20] 梁振明，翟正利，周炜.基于多尺度动态图卷积网络的3D点云分类[J].计算机应用与软件，2021，38（5）：263-267.
LIANG Z M，ZHAI Z L，ZHOU W.3D point clouds classification based on multi-scale dynamic graph convolution network[J].Computer Applications and Software，2021，38（5）：263-267.
[21] SIMONOVSKY M，KOMODAKIS N.Dynamic edge-conditioned filters in convolutional neural networks on graphs[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：3693-3702.
[22] WANG Y，SUN Y，LIU Z，et al.Dynamic graph CNN for learning on point clouds[J].ACM Transactions on Graphics（TOG），2019，38（5）：1-12.
[23] HU Q，YANG B，XIE L，et al.Randla-Net：efficient semantic segmentation of large-scale point clouds[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：11108-11117.
[24] 马京晖，潘巍，王茹.基于K-means聚类的三维点云分类[J].计算机工程与应用，2020，56（17）：181-186.
MA J H，PAN W，WANG R.3D point cloud classification based on K-means clustering[J].Computer Engineering and Applications，2020，56（17）：181-186.
[25] QI X，LIAO R，JIA J，et al.3D graph neural networks for RGBD semantic segmentation[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：5199-5208.
[26] LANDRIEU L，SIMONOVSKY M.Large-scale point cloud semantic segmentation with superpoint graphs[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：4558-4567.
[27] BI Y，CHADHA A，ABBAS A，et al.Graph-based object classification for neuromorphic vision sensing[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：491-501.
[28] SHI W，RAJKUMAR R.Point-GNN：graph neural network for 3D object detection in a point cloud[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：1711-1719.
[29] QI C R，SU H，MO K，et al.PointNet：deep learning on point sets for 3d classification and segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：652-660.
[30] 张新良，付鹏飞，赵运基，等.融合图卷积和差异性池化函数的点云数据分类分割模型[J].中国图象图形学报，2020，25（6）：1201-1208.
ZHANG X L，FU P F，ZHAO Y J，et al.Point cloud data classification and segmentation model using graph CNN and different pooling functions[J].Journal of Image and Graphics，2020，25（6）：1201-1208.
[31] 柴玉晶，马杰，刘红.用于点云语义分割的深度图注意力卷积网络[J].激光与光电子学进展，2021，58（12）：1210016.
CHAI Y J，MA J，LIU H.Deep graph attention convolution network for point cloud semantic segmentation[J].Laser & Optoelectronics Progress，2021，58（12）：1210016.
[32] ZHENG Z，WANG P，LIU W，et al.Distance-IoU loss：faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：12993-13000.
[33] BRAZIL G，LIU X.M3D-RPN：Monocular 3D region proposal network for object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：9287-9296.
[34] QI C R，LIU W，WU C，et al.Frustum pointnets for 3D object detection from RGB-D data[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：918-927.