A Multi-Stage Progressive Network with Feature Transmission and Fusion for Marine Snow Removal

被引:0
|
作者
Liu, Lixin [1 ,2 ]
Liao, Yuyang [1 ,2 ]
He, Bo [1 ]
Kwan, Chiman
机构
[1] Chinese Acad Sci, Inst Deep Sea Sci & Engn, Sanya 572000, Peoples R China
[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
关键词
marine snow; underwater image processing; multi-stage; deep learning; ALGORITHMS;
D O I
10.3390/s24020356
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Improving underwater image quality is crucial for marine detection applications. However, in the marine environment, captured images are often affected by various degradation factors due to the complexity of underwater conditions. In addition to common color distortions, marine snow noise in underwater images is also a significant issue. The backscatter of artificial light on marine snow generates specks in images, thereby affecting image quality, scene perception, and subsequently impacting downstream tasks such as target detection and segmentation. Addressing the issues caused by marine snow noise, we have designed a new network structure. In this work, a novel skip-connection structure called a dual channel multi-scale feature transmitter (DCMFT) is implemented to reduce information loss during downsampling in the feature encoding and decoding section. Additionally, in the feature transfer process for each stage, iterative attentional feature fusion (iAFF) modules are inserted to fully utilize marine snow features extracted at different stages. Finally, to further optimize the network's performance, we incorporate the multi-scale structural similarity index (MS-SSIM) into the loss function to ensure more effective convergence during training. Through experiments conducted on the Marine Snow Removal Benchmark (MSRB) dataset with an augmented sample size, our method has achieved significant results. The experimental results demonstrate that our approach excels in removing marine snow noise, with a peak signal-to-noise ratio reaching 38.9251 dB, significantly outperforming existing methods.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Multi-stage feature-fusion dense network for motion deblurring
    Guo, Cai
    Wang, Qian
    Dai, Hong-Ning
    Li, Ping
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2023, 90
  • [2] A multi-stage feature fusion defogging network based on the attention mechanism
    Song, Yuqin
    Zhao, Jitao
    Shang, Chunliang
    [J]. JOURNAL OF SUPERCOMPUTING, 2024, 80 (04): : 4577 - 4599
  • [3] Multi-stage Feature Fusion Network for Edge Detection of Dunhuang Murals
    Wang, Jianhua
    Liu, Baokai
    Li, Jiacheng
    Liu, Wenjie
    Du, Shiqiang
    [J]. 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC, 2023, : 4684 - 4689
  • [4] Multi-Stage Feature Fusion Network for Video Super-Resolution
    Song, Huihui
    Xu, Wenjie
    Liu, Dong
    Liu, Bo
    Liu, Qingshan
    Metaxas, Dimitris N.
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 : 2923 - 2934
  • [5] A multi-stage feature fusion defogging network based on the attention mechanism
    Yuqin Song
    Jitao Zhao
    Chunliang Shang
    [J]. The Journal of Supercomputing, 2024, 80 (4) : 4577 - 4599
  • [6] A Multi-Stage Adaptive Feature Fusion Neural Network for Multimodal Gait Recognition
    Zou, Shinan
    Xiong, Jianbo
    Fan, Chao
    Yu, Shiqi
    Tang, Jin
    [J]. 2023 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS, IJCB, 2023,
  • [7] Multi-stage Progressive Speech Enhancement Network
    Xu, Xinmeng
    Wang, Yang
    Xu, Dongxiang
    Peng, Yiyuan
    Zhang, Cong
    Jia, Jie
    Chen, Binbin
    [J]. INTERSPEECH 2021, 2021, : 2691 - 2695
  • [8] Multi-Stage Frequency Attention Network for Progressive Optical Remote Sensing Cloud Removal
    Wu, Caifeng
    Xu, Feng
    Li, Xin
    Wang, Xinyuan
    Xu, Zhennan
    Fang, Yiwei
    Lyu, Xin
    [J]. REMOTE SENSING, 2024, 16 (15)
  • [9] MSPNet: Multi-stage progressive network for image denoising
    Bai, Yu
    Liu, Meiqin
    Yao, Chao
    Lin, Chunyu
    Zhao, Yao
    [J]. NEUROCOMPUTING, 2023, 517 : 71 - 80
  • [10] MuSeFFF: Multi-stage feature fusion framework for traffic prediction
    Kumar, Arun
    Sunitha, R.
    [J]. Intelligent Systems with Applications, 2023, 18