Visual saliency detection for RGB-D images under a Bayesian framework

被引:2
作者
Wang S. [1 ,2 ]
Zhou Z. [1 ]
Jin W. [2 ]
Qu H. [2 ]
机构
[1] The Higher Educational Key Laboratory for Measuring and Control Technology and Instrumentations of Heilongjiang Province, Harbin University of Science and Technology, Harbin
[2] Res. Center for Artif. Intell. and Big Data Anal., Beijing Academy of Science and Technology, Beijing
关键词
Bayesian fusion; Deep learning; Generative model; RGB-D images; Saliency detection;
D O I
10.1186/s41074-017-0037-0
中图分类号
学科分类号
摘要
In this paper, we propose a saliency detection model for RGB-D images based on the deep features of RGB images and depth images within a Bayesian framework. By analysing 3D saliency in the case of RGB images and depth images, the class-conditional mutual information is computed for measuring the dependence of deep features extracted using a convolutional neural network; then, the posterior probability of the RGB-D saliency is formulated by applying Bayes’ theorem. By assuming that deep features are Gaussian distributions, a discriminative mixed-membership naive Bayes (DMNB) model is used to calculate the final saliency map. The Gaussian distribution parameters can be estimated in the DMNB model by using a variational inference-based expectation maximization algorithm. The experimental results on RGB-D images from the NLPR dataset and NJU-DS400 dataset show that the proposed model performs better than other existing models. © 2018, The Author(s).
引用
收藏
相关论文
共 50 条
  • [31] HFNet: Hierarchical feedback network with multilevel atrous spatial pyramid pooling for RGB-D saliency detection
    Zhou, Wujie
    Liu, Chang
    Lei, Jingsheng
    Yu, Lu
    Luo, Ting
    NEUROCOMPUTING, 2022, 490 : 347 - 357
  • [32] A novel unsupervised 3D skeleton detection in RGB-D images for video surveillance
    Cheng, Shyi-Chyi
    Hsiao, Kuei-Fang
    Yang, Chen-Kuei
    Hsiao, Po-Fu
    Yu, Wan-Hsuan
    MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (23-24) : 15829 - 15857
  • [33] 3D Texture Recognition for RGB-D Images
    Zhong, Guoqiang
    Mao, Xin
    Shi, Yaxin
    Dong, Junyu
    COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2015, PT II, 2015, 9257 : 518 - 528
  • [34] Self-Supervised Pretraining With Multimodality Representation Enhancement for Salient Object Detection in RGB-D Images
    Gao, Lina
    Liu, Bing
    Fu, Ping
    Xu, Mingzhu
    Zhang, Yonggang
    Huang, Yulong
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2025, 74
  • [35] A novel unsupervised 3D skeleton detection in RGB-D images for video surveillance
    Shyi-Chyi Cheng
    Kuei-Fang Hsiao
    Chen-Kuei Yang
    Po-Fu Hsiao
    Wan-Hsuan Yu
    Multimedia Tools and Applications, 2020, 79 : 15829 - 15857
  • [36] Holistic and local patch framework for 6D object pose estimation in RGB-D images
    Zhang, Haoruo
    Cao, Qixin
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2019, 180 : 59 - 73
  • [37] Individual Identification of Cattle Based on RGB-D Images
    Liu S.
    Chang R.
    Li B.
    Wei Y.
    Wang H.
    Jia N.
    Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery, 2023, 54 : 260 - 266
  • [38] RGB-D Saliency Detection with 3D Cross-modal Fusion and Mid-level Integration
    Liu, Taoqi
    Li, Bo
    2022 IEEE 34TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2022, : 1328 - 1335
  • [39] VISUAL SALIENCY DETECTION BASED ON BAYESIAN MODEL
    Xie, Yulin
    Lu, Huchuan
    2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2011, : 645 - 648
  • [40] Accelerated DNA-SLAM for RGB-D images
    Ameli, Mina
    Wasenmuller, Oliver
    Soheili, Mohammad Reza
    Shanbehzadeh, Jamshid
    Stricker, Didier
    PROCEEDINGS OF 2018 INTERNATIONAL CONFERENCE ON IMAGE AND GRAPHICS PROCESSING (ICIGP 2018), 2018, : 185 - 190