Review on Indoor RGB-D Semantic Segmentation with Deep Convolutional Neural Networks

被引:10
|
作者
Barchid, Sami [1 ]
Mennesson, Jose [1 ,2 ]
Djeraba, Chaabane [1 ]
机构
[1] Univ Lille, CNRS, Cent Lille, UMR 9189 CRIStAL, F-59000 Lille, France
[2] IMT Lille Douai, Inst Mines Telecom, Ctr Digital Syst, Douai, France
关键词
RGB-D Indoor Semantic Segmentation; Deep Convolutional Neural Networks; Deep Learning;
D O I
10.1109/CBMI50038.2021.9461875
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Many research works focus on leveraging the complementary geometric information of indoor depth sensors in vision tasks performed by deep convolutional neural networks, notably semantic segmentation. These works deal with a specific vision task known as "RGB-D Indoor Semantic Segmentation". The challenges and resulting solutions of this task differ from its standard RGB counterpart. This results in a new active research topic. The objective of this paper is to introduce the field of Deep Convolutional Neural Networks for RGB-D Indoor Semantic Segmentation. This review presents the most popular public datasets, proposes a categorization of the strategies employed by recent contributions, evaluates the performance of the current state-of-the-art, and discusses the remaining challenges and promising directions for future works.
引用
收藏
页码:199 / 202
页数:4
相关论文
共 50 条
  • [21] An improved deep network-based RGB-D semantic segmentation method for indoor scenes
    Ni, Jianjun
    Zhang, Ziru
    Shen, Kang
    Tang, Guangyi
    Yang, Simon X.
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2024, 15 (02) : 589 - 604
  • [22] Semantic Segmentation and 6DoF Pose Estimation using RGB-D Images and Deep Neural Networks
    Van Luan Tran
    Lin, Huei-Yung
    PROCEEDINGS OF 2021 IEEE 30TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE), 2021,
  • [23] Recurrent Convolutional Neural Networks for Object-Class Segmentation of RGB-D Video
    Pavel, Mircea Serban
    Schulz, Hannes
    Behnke, Sven
    2015 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2015,
  • [24] Multi-scale fusion for RGB-D indoor semantic segmentation
    Jiang, Shiyi
    Xu, Yang
    Li, Danyang
    Fan, Runze
    SCIENTIFIC REPORTS, 2022, 12 (01):
  • [25] ObjectFusion: An object detection and segmentation framework with RGB-D SLAM and convolutional neural networks
    Tian, Guanzhong
    Liu, Liang
    Ri, JongHyok
    Liu, Yong
    Sun, Yiran
    NEUROCOMPUTING, 2019, 345 : 3 - 14
  • [26] Multi-scale fusion for RGB-D indoor semantic segmentation
    Shiyi Jiang
    Yang Xu
    Danyang Li
    Runze Fan
    Scientific Reports, 12 (1)
  • [27] Object class segmentation of RGB-D video using recurrent convolutional neural networks
    Pavel, Mircea Serban
    Schulz, Hannes
    Behnke, Sven
    NEURAL NETWORKS, 2017, 88 : 105 - 113
  • [28] RGB-D indoor semantic segmentation network based on wavelet transform
    Runze Fan
    Yuhong Liu
    Shiyi Jiang
    Rongfen Zhang
    Evolving Systems, 2023, 14 : 981 - 991
  • [29] Locality-Sensitive Deconvolution Networks with Gated Fusion for RGB-D Indoor Semantic Segmentation
    Cheng, Yanhua
    Cai, Rui
    Li, Zhiwei
    Zhao, Xin
    Huang, Kaiqi
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 1475 - 1483
  • [30] RGB-D indoor semantic segmentation network based on wavelet transform
    Fan, Runze
    Liu, Yuhong
    Jiang, Shiyi
    Zhang, Rongfen
    EVOLVING SYSTEMS, 2023, 14 (06) : 981 - 991