3D Object Detection Using Scale Invariant and Feature Reweighting Networks

被引:0
|
作者
Zhao, Xin [1 ]
Liu, Zhe [2 ]
Hu, Ruolan [2 ]
Huang, Kaiqi [1 ]
机构
[1] Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Syst & Engn, Beijing 100190, Peoples R China
[2] Huazhong Univ Sci & Technol, Wuhan 430074, Hubei, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
3D object detection plays an important role in a large number of real-world applications. It requires us to estimate the localizations and the orientations of 3D objects in real scenes. In this paper, we present a new network architecture which focuses on utilizing the front view images and frustum point clouds to generate 3D detection results. On the one hand, a PointSIFT module is utilized to improve the performance of 3D segmentation. It can capture the information from different orientations in space and the robustness to different scale shapes. On the other hand, our network obtains the useful features and suppresses the features with less information by a SENet module. This module reweights channel features and estimates the 3D bounding boxes more effectively. Our method is evaluated on both KITTI dataset for outdoor scenes and SUN-RGBD dataset for indoor scenes. The experimental results illustrate that our method achieves better performance than the state-of-the-art methods especially when point clouds are highly sparse.
引用
收藏
页码:9267 / 9274
页数:8
相关论文
共 50 条
  • [1] Scale invariant point feature (SIPF) for 3D point clouds and 3D multi-scale object detection
    Lin, Baowei
    Wang, Fasheng
    Zhao, Fangda
    Sun, Yi
    NEURAL COMPUTING & APPLICATIONS, 2018, 29 (05): : 1209 - 1224
  • [2] Retraction Note: Scale invariant point feature (SIPF) for 3D point clouds and 3D multi-scale object detection
    Baowei Lin
    Fasheng Wang
    Fangda Zhao
    Yi Sun
    Neural Computing and Applications, 2024, 36 (18) : 11065 - 11065
  • [3] RETRACTED ARTICLE: Scale invariant point feature (SIPF) for 3D point clouds and 3D multi-scale object detection
    Baowei Lin
    Fasheng Wang
    Fangda Zhao
    Yi Sun
    Neural Computing and Applications, 2018, 29 : 1209 - 1224
  • [4] Scale and rotation invariant 3D object detection using spherical nonlinear correlations
    Garcia-Martinez, Pascuala
    Valles, Jose J.
    Ferreira, Carlos
    OPTICAL AND DIGITAL IMAGE PROCESSING, 2008, 7000
  • [5] 3D object representation using transform and scale invariant 3D features
    Akagunduz, Erdem
    Ulusoy, Ilkay
    2007 IEEE 11TH INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1-6, 2007, : 55 - 62
  • [6] 3D object recognition using scale-invariant features
    Jeonghun Lim
    Kunwoo Lee
    The Visual Computer, 2019, 35 : 71 - 84
  • [7] 3D object recognition using scale-invariant features
    Lim, Jeonghun
    Lee, Kunwoo
    VISUAL COMPUTER, 2019, 35 (01): : 71 - 84
  • [8] FCNet: Stereo 3D Object Detection with Feature Correlation Networks
    Wu, Yingyu
    Liu, Ziyan
    Chen, Yunlei
    Zheng, Xuhui
    Zhang, Qian
    Yang, Mo
    Tang, Guangming
    ENTROPY, 2022, 24 (08)
  • [9] MonoFENet: Monocular 3D Object Detection With Feature Enhancement Networks
    Bao, Wentao
    Xu, Bin
    Chen, Zhenzhong
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 : 2753 - 2765
  • [10] 3D OBJECT RECOGNITION USING INVARIANT FEATURE INDEXING OF INTERPRETATION TABLES
    FLYNN, PJ
    JAIN, AK
    CVGIP-IMAGE UNDERSTANDING, 1992, 55 (02): : 119 - 129