陈勇,李松,晋伟平,谢珉,杨永昆
CHEN Yong,LI Song,JIN Weiping,XIE Min,YANG Yongkun

• 1:云南电网有限责任公司
• 2:云南电网有限责任公司红河供电局

摘要(Abstract)：

卷积神经网络由于其有限的感受野无法高效捕捉到电力场景中避雷器、GIS进线套管等设备的上下文信息，进而影响检测效果。为解决上述问题，引入基于Transformer的体素注意力网络，提出局部注意力和空洞注意力机制来分别捕获图像体积像素中的近程和远程特征联系，在保证计算开销不增大的同时，有效扩大注意力范围。同时，设计子流形体素模块和稀疏体素模块来分别提取非空体素位置和空白体素位置上的特征信息。最后，在通用数据集Waymo和KITTI以及云南省某输变电区域的图像数据集上与主流模型进行比较，证明所提模型对于电力设备的检测具有更加优越的性能。
Convolutional neural networks(CNNs) struggle to efficiently capture contextual information of power equipment such as arresters and GIS inlet casings due to their limited receptive fields, thereby affecting detection performance. To address this issue, the paper introduces a Transformer-based voxel-graph attention network. Local attention and dilated attention mechanisms are proposed to respectively capture short-range and long-range feature correlations within image volume pixels, effectively expanding the attention scope while keeping computational costs unchanged. Additionally, submanifold voxel modules and sparse voxel modules are designed to extract feature information from non-empty voxel positions and empty voxel positions, respectively. Finally, through comparative analysis with mainstream models on the general datasets Waymo and KITTI, as well as on an image dataset from a transmission and transformation area in Yunnan Province, the superior performance of the proposed model in detecting power equipment is demonstrated.

关键词(KeyWords)： 注意力网络;目标检测;几何流形;体积像素
attention network;object detection;geometric manifold;volume pixel

Abstract:

Keywords:

基金项目(Foundation): 云南电网有限责任公司科技项目（YNKJXM20210149）

作者(Author): 陈勇,李松,晋伟平,谢珉,杨永昆
CHEN Yong,LI Song,JIN Weiping,XIE Min,YANG Yongkun

DOI: 10.19585/j.zjdl.202404013

参考文献(References)：

• [1]韩肖清，李廷钧，张东霞，等.双碳目标下的新型电力系统规划新问题及关键技术[J].高电压技术，2021,47(9):3036-3046.HAN Xiaoqing,LI Tingjun,ZHANG Dongxia,et al.New issues and key technologies of new power system planning under double carbon goals[J].High Voltage Engineering,2021,47(9):3036-3046.
• [2]王成山，李鹏.分布式发电、微网与智能配电网的发展与挑战[J].电力系统自动化，2010,34(2):10-14.WANG Chengshan,LI Peng.Development and challenges of distributed generation,the micro-grid and smart distribution system[J]. Automation of Electric Power Systems,2010,34(2):10-14.
• [3] AFIFI M,ABDELHAMED A,ABUOLAIM A,et al.CIE XYZ net:unprocessing images for low-level computer vision tasks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(9):4688-4700.
• [4] ZHOU L,ZHANG C,LIU F,et al. Application of deep learning in food:a review[J].Comprehensive Reviews in Food Science and Food Safety,2019,18(6):1793-1811.
• [5] CHU S Y,AVESTRUZ A T. Electromagnetic modelbased foreign object detection for wireless power transfer[C]//2019 20th Workshop on Control and Modeling for Power Electronics(COMPEL). Toronto,ON,Canada.IEEE,2019:1-8.
• [6] WEN L H,JO K H.Three-attention mechanisms for onestage 3-D object detection based on LiDAR and camera[J].IEEE Transactions on Industrial Informatics,2021,17(10):6655-6663.
• [7] LANG A H,VORA S,CAESAR H,et al.PointPillars:fast encoders for object detection from point clouds[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Long Beach,CA,USA.IEEE,2019:12689-12697.
• [8] HE C H,ZENG H,HUANG J Q,et al.Structure aware single-stage 3D object detection from point cloud[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Seattle,WA,USA.IEEE,2020:11870-11879.
• [9] SHI S S,GUO C X,JIANG L,et al.PV-RCNN:pointvoxel feature set abstraction for 3D object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Seattle,WA,USA.IEEE,2020:10526-10535.
• [10] WANG H,CHEN Z Y,CAI Y F,et al. Voxel-RCNNcomplex:an effective 3-D point cloud object detector for complex traffic conditions[J]. IEEE Transactions on Instrumentation and Measurement,2022,71:2507112.
• [11] YANG Z T,SUN Y N,LIU S,et al. STD:sparse-todense 3D object detector for point cloud[C]//2019 IEEE/CVF International Conference on Computer Vision(ICCV).Seoul,Korea(South).IEEE,2019:1951-1960.
• [12] GUAN T R,WANG J,LAN S Y,et al.M3DETR:multirepresentation,multi-scale,mutual-relation 3D object detection with transformers[C]//2022 IEEE/CVF Winter Conference on Applications of Computer Vision(WACV).Waikoloa,HI,USA.IEEE,2022:2293-2303.
• [13] CHARLES R Q,HAO S,MO K C,et al.PointNet:deep learning on point sets for 3D classification and segmentation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu,HI,USA.IEEE,2017:77-85.
• [14] QI C R,YI L,SU H,et al.PointNet++:deep hierarchical feature learning on point sets in a metric space[EB/OL]. 2017:arXiv:1706.02413. http：//arxiv. org/abs/1706.02413.pdf
• [15] SHI S S,WANG X G,LI H S. PointRCNN:3D object proposal generation and detection from point cloud[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Long Beach,CA,USA.IEEE,2019:770-779.
• [16] YAN Y,MAO Y X,LI B.SECOND:sparsely embedded convolutional detection[J].Sensors,2018,18(10):3337.
• [17]李亚锦，刘英男，于大洋.基于小样本及贝叶斯推理的避雷器缺陷分类技术[J].电工电能新技术，2021,40(11):56-63.LI Yanan,LIU Yingnan,YU Dayang.Classification of arrester defects based on small sample data and Bayesian inference[J].Advanced Technology of Electrical Engineering and Energy,2021,40(11):56-63.
• [18]赵永强，饶元，董世鹏，等.深度学习目标检测方法综述[J].中国图象图形学报，2020,25(4):629-654.ZHAO Yongqiang,RAO Yuan,DONG Shipeng,et al.Survey on deep learning object detection[J].Journal of Image and Graphics,2020,25(4):629-654.
• [19] MINAEE S,BOYKOV Y,PORIKLI F,et al.Image segmentation using deep learning:a survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(7):3523-3542.