3D Object Detection in Substation Scene Based on Voxelization

被引：0
|
作者：
Wang, Dawei [1 ]
Hu, Fan [1 ]
Zhang, Na [1 ]
Yang, Gang [1 ]
Lu, Jiyuan [2 ]
Zhang, Xingzhong [2 ]
机构：
[1] Electric Power Research Institute, State Grid Shanxi Electric Power Company, Taiyuan,030002, China
[2] Shanxi Hongshuntong Technology Co., Ltd., Taiyuan,030024, China
来源：
Computer Engineering and Applications | 2024年 / 60卷 / 11期
关键词：
Aiming at the problem of low detection accuracy caused by insufficient target feature extraction in substation 3D scene; a voxelization-based 3D object detection model AugSecond for substation scene is proposed; which is designed based on the Second network structure. It introduces a triple attention mechanism in the voxel feature encoding stage; which focuses on multi-dimensional attention to enhance the key information of the target and reduce the interference of irrelevant feature information. It designes asymmetric sparse convolutional networks; uses asymmetric convolution to improve convolutional kernel representation capabilities and fuses multi-scale features to enrich target geometry information. Meanwhile; the position regression loss is optimized; and CIoU Loss is used to further consider the geometric correlation between bounding boxes to speed up the network convergence. Experiments on self-built power scene data sets and public data sets show that compared with the benchmark model; AugSecond model significantly improves recognition accuracy and has real-time reasoning speed; which proves the effectiveness of the proposed model. © 2024 Journal of Computer Engineering and Applications Beijing Co; Ltd; Science Press. All rights reserved;
D O I：
10.3778/j.issn.1002-8331.2302-0331
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：328 / 335
相关论文
共 50 条
  • [31] Heuristic 3D Object Shape Completion based on Symmetry and Scene Context
    Schiebener, David
    Schmidt, Andreas
    Vahrenkamp, Nikolaus
    Asfour, Tamim
    2016 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2016), 2016, : 74 - 81
  • [32] Viewpoint Recommendation Based on Object-Oriented 3D Scene Reconstruction
    Li, Ke
    Wu, Yuxia
    Xue, Yao
    Qian, Xueming
    IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23 : 257 - 267
  • [33] MonoSAID: Monocular 3D Object Detection based on Scene-Level Adaptive Instance Depth Estimation
    Chenxing Xia
    Wenjun Zhao
    Huidan Han
    Zhanpeng Tao
    Bin Ge
    Xiuju Gao
    Kuan-Ching Li
    Yan Zhang
    Journal of Intelligent & Robotic Systems, 2024, 110
  • [34] Multi-View Fusion-Based 3D Object Detection for Robot Indoor Scene Perception
    Wang, Li
    Li, Ruifeng
    Sun, Jingwen
    Liu, Xingxing
    Zhao, Lijun
    Seah, Hock Soon
    Quah, Chee Kwang
    Tandianus, Budianto
    SENSORS, 2019, 19 (19)
  • [35] MonoSAID: Monocular 3D Object Detection based on Scene-Level Adaptive Instance Depth Estimation
    Xia, Chenxing
    Zhao, Wenjun
    Han, Huidan
    Tao, Zhanpeng
    Ge, Bin
    Gao, Xiuju
    Li, Kuan-Ching
    Zhang, Yan
    JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2024, 110 (01)
  • [36] A workpiece grasp detection method based on 3D object detection
    Li, Huijun
    Duan, Longbo
    Wang, Qirun
    Zhang, Yilun
    Ye, Bin
    INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION, 2025,
  • [37] Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scene
    Zhang, Ruiyang
    Zhang, Hu
    Yu, Hang
    Zheng, Zhedong
    COMPUTER VISION - ECCV 2024, PT XI, 2025, 15069 : 249 - 266
  • [38] 3D point cloud recognition of substation equipment based on plane detection
    Yuan, Qianjin
    Luo, Yong
    Wang, HeShan
    RESULTS IN ENGINEERING, 2022, 15
  • [39] 3D Line voxelization and connectivity control
    Tel-Aviv Univ, Israel
    IEEE Comput Graphics Appl, 6 (80-87):
  • [40] 3D scene modeling for activity detection
    Ma, YQ
    Bazakos, M
    Wang, Z
    Au, W
    PERSPECTIVES IN CONCEPTUAL MODELING, 2005, 3770 : 300 - 309
12345