Moving Object Detection with Single Moving Camera and IMU Sensor using Mask R-CNN Instance Image Segmentation

被引：9
|
作者：
Jung, Sukwoo [1 ]
Cho, Youngmok [1 ]
Lee, KyungTaek [2 ]
Chang, Minho [1 ]
机构：
[1] Korea Univ, Dept Mech Engn, Seoul, South Korea
[2] Korea Elect Technol Inst, Contents Convergence Res Ctr, Seoul, South Korea
来源：
INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING | 2021年 / 22卷 / 06期
关键词：
Moving camera; Motion estimation; Moving object detection; Deep learning; TRACKING; ROBUST; RECOGNITION;
D O I：
10.1007/s12541-021-00527-9
中图分类号：
T [工业技术];
学科分类号：
08 ;
摘要：
This paper describes a new method for the moving object detection using the IMU sensor and instance image segmentation. In the proposed method, the feature points are extracted by the detector, and the initial fundamental matrix is calculated from the IMU data. Next, the epipolar line is used to classify the extracted feature points. From the background feature point matching, fundamental matrix is calculated iteratively to minimize the error of classification. After the feature point classification, image segmentation is used to enhance the quality of the classification result. The proposed method is implemented and tested with real-world driving videos, and compared with the previous works.
引用
下载
收藏
页码：1049 / 1059
页数：11
相关论文
共 50 条
  • [31] Contour Extraction of Individual Cattle From an Image Using Enhanced Mask R-CNN Instance Segmentation Method
    Bello, Rotimi-Williams
    Mohamed, Ahmad Sufril Azlan
    Talib, Abdullah Zawawi
    IEEE ACCESS, 2021, 9 : 56984 - 57000
  • [32] Object detection based on RGC mask R-CNN
    Wu, Minghu
    Yue, Hanhui
    Wang, Juan
    Huang, Yongxi
    Liu, Min
    Jiang, Yuhan
    Ke, Cong
    Zeng, Cheng
    IET IMAGE PROCESSING, 2020, 14 (08) : 1502 - 1508
  • [33] Potato Detection and Segmentation Based on Mask R-CNN
    Lee H.-S.
    Shin B.-S.
    Journal of Biosystems Engineering, 2020, 45 (4) : 233 - 238
  • [34] Object detection of aerial image using mask-region convolutional neural network (mask R-CNN)
    Musyarofah
    Schmidt, Valentina
    Kada, Martin
    FIFTH INTERNATIONAL CONFERENCES OF INDONESIAN SOCIETY FOR REMOTE SENSING: THE REVOLUTION OF EARTH OBSERVATION FOR A BETTER HUMAN LIFE, 2020, 500
  • [35] A deep learning approach to the screening of malaria infection: Automated and rapid cell counting, object detection and instance segmentation using Mask R-CNN
    Loh, De Rong
    Yong, Wen Xin
    Yapeter, Jullian
    Subburaj, Karupppasamy
    Chandramohanadas, Rajesh
    Computerized Medical Imaging and Graphics, 2021, 88
  • [36] A deep learning approach to the screening of malaria infection: Automated and rapid cell counting, object detection and instance segmentation using Mask R-CNN
    Loh, De Rong
    Wen Xin Yong
    Yapeter, Jullian
    Subburaj, Karupppasamy
    Chandramohanadas, Rajesh
    COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2021, 88
  • [37] Instance Segmentation Model for Microscopic Image of Citrus Main Leaf Vein Based on Mask R-CNN
    Weng H.
    Li X.
    Xiao K.
    Ding R.
    Jia L.
    Ye D.
    Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery, 2023, 54 (07): : 252 - 258and271
  • [38] Instance segmentation of low contrast and high density cell images using Mask R-CNN
    Huang, Hejun
    Chen, Zuguo
    4TH INTERNATIONAL CONFERENCE ON INFORMATICS ENGINEERING AND INFORMATION SCIENCE (ICIEIS2021), 2022, 12161
  • [39] Automatic in-situ instance and semantic segmentation of planktonic organisms using Mask R-CNN
    Bergum, Sondre
    Saad, Aya
    Stahl, Annette
    GLOBAL OCEANS 2020: SINGAPORE - U.S. GULF COAST, 2020,
  • [40] Instance Segmentation by Using Mask R-CNN Based on Feature Fusion of RGB and Depth Images
    Sun, Jinyu
    Jin, Chengxiong
    Ma, Shiwei
    2019 INTERNATIONAL CONFERENCE ON IMAGE AND VIDEO PROCESSING, AND ARTIFICIAL INTELLIGENCE, 2019, 11321
12345