MSEDNet: Multi-scale fusion and edge-supervised network for RGB-T salient object detection

被引:11
|
作者
Peng, Daogang [1 ]
Zhou, Weiyi [1 ]
Pan, Junzhen [1 ]
Wang, Danhao [1 ]
机构
[1] Shanghai Univ Elect Power, Coll Automat Engn, 2588 Changyang Rd, Shanghai 200090, Peoples R China
关键词
RGB-T; Salient object detection; Multi-scale fusion; Edge fusion loss; SEGMENTATION;
D O I
10.1016/j.neunet.2023.12.031
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
RGB-T Salient object detection (SOD) is to accurately segment salient regions in both visible light images and thermal infrared images. However, most of existing methods for SOD neglects the critical complementarity between multiple modalities images, which is beneficial to further improve the detection accuracy. Therefore, this work introduces the MSEDNet RGB-T SOD method. We utilize an encoder to extract multi-level modalities features from both visible light images and thermal infrared images, which are subsequently categorized into high, medium, and low level. Additionally, we propose three separate feature fusion modules to comprehensively extract complementary information between different modalities during the fusion process. These modules are applied to specific feature levels: the Edge Dilation Sharpening module for low-level features, the Spatial and Channel-Aware module for mid-level features, and the Cross-Residual Fusion module for high-level features. Finally, we introduce an edge fusion loss function for supervised learning, which effectively extracts edge information from different modalities and suppresses background noise. Comparative demonstrate the superiority of the proposed MSEDNet over other state-of-the-art methods. The code and results can be found at the following link: https://github.com/Zhou-wy/MSEDNet.
引用
收藏
页码:410 / 422
页数:13
相关论文
共 50 条
  • [11] CGFNet: Cross-Guided Fusion Network for RGB-T Salient Object Detection
    Wang, Jie
    Song, Kechen
    Bao, Yanqi
    Huang, Liming
    Yan, Yunhui
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (05) : 2949 - 2961
  • [12] ECFFNet: Effective and Consistent Feature Fusion Network for RGB-T Salient Object Detection
    Zhou, Wujie
    Guo, Qinling
    Lei, Jingsheng
    Yu, Lu
    Hwang, Jenq-Neng
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (03) : 1224 - 1235
  • [13] TSFNet: Two-Stage Fusion Network for RGB-T Salient Object Detection
    Guo, Qinling
    Zhou, Wujie
    Lei, Jingsheng
    Yu, Lu
    IEEE SIGNAL PROCESSING LETTERS, 2021, 28 : 1655 - 1659
  • [14] EDGE-Net: an edge-guided enhanced network for RGB-T salient object detection
    Zheng, Xin
    Wang, Boyang
    Ai, Liefu
    Tang, Pan
    Liu, Deyang
    JOURNAL OF ELECTRONIC IMAGING, 2023, 32 (06)
  • [15] Multi-enhanced Adaptive Attention Network for RGB-T Salient Object Detection
    Hao, Hao-Zhou
    Cheng, Yao
    Ji, Yi
    Li, Ying
    Liu, Chun-Ping
    2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [16] PSNet: Parallel symmetric network for RGB-T salient object detection
    Bi, Hongbo
    Wu, Ranwan
    Liu, Ziqi
    Zhang, Jiayuan
    Zhang, Cong
    Xiang, Tian-Zhu
    Wang, Xiufang
    NEUROCOMPUTING, 2022, 511 (410-425) : 410 - 425
  • [17] SIA: RGB-T salient object detection network with salient-illumination awareness
    Song, Kechen
    Wen, Hongwei
    Ji, Yingying
    Xue, Xiaotong
    Huang, Liming
    Yan, Yunhui
    Meng, Qinggang
    OPTICS AND LASERS IN ENGINEERING, 2024, 172
  • [18] MMNet: Multi-Stage and Multi-Scale Fusion Network for RGB-D Salient Object Detection
    Liao, Guibiao
    Gao, Wei
    Jiang, Qiuping
    Wang, Ronggang
    Li, Ge
    MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, : 2436 - 2444
  • [19] MAGNet: Multi-scale Awareness and Global fusion Network for RGB-D salient object detection
    Zhong, Mingyu
    Sun, Jing
    Ren, Peng
    Wang, Fasheng
    Sun, Fuming
    KNOWLEDGE-BASED SYSTEMS, 2024, 299
  • [20] Dual attention guided multi-scale fusion network for RGB-D salient object detection
    Gao, Huan
    Guo, Jichang
    Wang, Yudong
    Dong, Jianan
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2023, 118