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
  • [21] Boundary points based scale invariant 3D point feature
    Lin, Baowei
    Wang, Fasheng
    Sun, Yi
    Qu, Wen
    Chen, Zheng
    Zhang, Shuo
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2017, 48 : 136 - 148
  • [22] Optimized feature exploitation for 3D object recognition using ART neural networks
    Walter, P
    IECON '98 - PROCEEDINGS OF THE 24TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-4, 1998, : 2063 - 2068
  • [23] Feature Decoupling and Uncertainty Estimation for 3D Object Detection
    Zhi, Peiyuan
    Zhou, Kaiyue
    Li, Yali
    Wang, Shengjin
    2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 1133 - 1138
  • [24] Monocular 3D Object Detection With Motion Feature Distillation
    Hu, Henan
    Li, Muyu
    Zhu, Ming
    Gao, Wen
    Liu, Peiyu
    Chan, Kwok-Leung
    IEEE ACCESS, 2023, 11 : 82933 - 82945
  • [25] Scale Adaptive Feature Pyramid Networks for 2D Object Detection
    He, Lifei
    Jiang, Ming
    Ohbuchi, Ryutarou
    Furuya, Takahiko
    Zhang, Min
    Li, Pengfei
    SCIENTIFIC PROGRAMMING, 2020, 2020
  • [26] STEREO BASED 3D HEAD POSE TRACKING USING THE SCALE INVARIANT FEATURE TRANSFORM
    Akan, Batu
    Cetin, Muejdat
    Ercil, Aytuel
    2008 IEEE 16TH SIGNAL PROCESSING, COMMUNICATION AND APPLICATIONS CONFERENCE, VOLS 1 AND 2, 2008, : 661 - 664
  • [27] Semantic Consistency Networks for 3D Object Detection
    Wei, Wenwen
    Wei, Ping
    Zheng, Nanning
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 2861 - 2869
  • [28] Viewpoint-independent object class detection using 3D feature maps
    Liebelt, Joerg
    Schmid, Cordelia
    Schertler, Klaus
    2008 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-12, 2008, : 2118 - +
  • [29] Scale, rotation and pose invariant 3D object detection using log-polar transform and singular value decomposition
    Ren Xianyi
    Dan Tangren
    Ding Tianhuai
    Liu Yan
    Zhang Wei
    Zhang Guilin
    Zhang Tianxu
    2006 INTERNATIONAL CONFERENCE ON COMMUNICATIONS, CIRCUITS AND SYSTEMS PROCEEDINGS, VOLS 1-4: VOL 1: SIGNAL PROCESSING, 2006, : 480 - +
  • [30] Deep 3D Object Detection Networks Using LiDAR Data: A Review
    Wu, Yutian
    Wang, Yueyu
    Zhang, Shuwei
    Ogai, Harutoshi
    IEEE SENSORS JOURNAL, 2021, 21 (02) : 1152 - 1171