Restauração de imagens subaquáticas baseada em prior de diferença média de intensidade

  • role: First author第一作者
  • Affiliation:

    Navigation College, Dalian Maritime University, Dalian 116026, China

  • Email:shuojs757@126.com
  • Introduction:商家硕(1997-),男,辽宁沈阳人,博士研究生,2022年于沈阳化工大学获得硕士学位,现为大连海事大学交通信息工程及控制专业博士研究生,主要从事水下图像处理方面的研究。E-mail: shuojs757@126.com
SHANG Jiashuo,  
  • role: Corresponding author通信作者
  • Affiliation:

    Navigation College, Dalian Maritime University, Dalian 116026, China

  • Email:yldmu@dlmu.edu.cn
  • Introduction:李 颖(1968-),女,辽宁锦州人,教授,博士生导师,1997年于日本东北大学获得博士学位,现为海上交通安全与空间信息技术国家重点领域创新团队负责人,主要从事海洋环境感知方面的研究。E-mail: yldmu@dlmu.edu.cn
LI Ying*,  
  • Affiliation:

    Navigation College, Dalian Maritime University, Dalian 116026, China

YUAN Jingyi,  
  • Affiliation:

    Navigation College, Dalian Maritime University, Dalian 116026, China

GUO Shen,  
  • Affiliation:

    Navigation College, Dalian Maritime University, Dalian 116026, China

XING Hu

Resumo

Diante da degradação das imagens subaquáticas causada pela absorção seletiva da água e pela dispersão múltipla, resultando em baixo contraste, fortes desvios de cor e detalhes borrados, propõe-se um modelo de restauração de imagens subaquáticas baseado em um prior de diferença média de intensidade. Primeiramente, calcula-se em paralelo a diferença média de intensidade para dois ramos “azul~verde, vermelho” e “verde~azul, vermelho” dentro de uma janela local, e tira-se a média para construir um prior de atenuação acoplada de três canais robusto ao ruído, usado para estimar a diferença de intensidade. Em seguida, com base na relação física encadeada “diferença de intensidade~profundidade de campo~transmissão”, introduz-se um mapeamento exponencial de inclinação adaptativa, combinado com uma expansão de Taylor de primeira ordem e aproximação diferencial, para estimar com precisão o mapa de transmissão de três canais. Simultaneamente, calcula-se a média do conjunto de pixels com a maior diferença de intensidade para estimar a luz de fundo. Finalmente, ao inserir o mapa de transmissão e a luz de fundo no modelo inverso de formação de imagem subaquática, alcança-se a restauração de imagens com cores naturais e detalhes nítidos. Experimentos qualitativos e quantitativos em conjuntos de dados reais subaquáticos UIEB e UCCS demonstram que o modelo proposto atinge o melhor desempenho integrado nas métricas UIQM, UCIQE, CCF e MWF, melhorando significativamente a fidelidade das cores, o contraste e a nitidez dos detalhes. Experimentos aplicados mostram um aumento significativo na quantidade de pontos-chave detectados nas imagens restauradas, uma expressão de bordas mais coerente e clara, bem como limites de objetos mais nítidos com menor taxa de detecção falsa nos resultados de segmentação. Este modelo pode se adaptar a diferentes ambientes aquáticos, restaurando imagens subaquáticas com cores reais e detalhes nítidos, fornecendo suporte confiável para dados em tarefas subsequentes de percepção visual subaquática.

Palavras-chave

restauração de imagens subaquáticas;melhoria de imagens de baixa qualidade;prior de diferença de intensidade;estimativa de mapa de transmissão;estimativa de luz de fundo

References

  1. 1.
    LIU C Y, CHEN Y S, JING T Y, et al. Adaptive color compensation and multi-scale fusion for underwater image enhancement[J]. Opt. Precision Eng., 2025, 33(5): 802-817. (in Chinese). doi:
  2. 2.
    FAN J Y, XU J, ZHOU J C, et al. See through water: heuristic modeling toward color correction for underwater image enhancement[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2025, 35(5): 4039-4054. doi:
  3. 3.
    LI B C, CHEN Z Q, LU L Y, et al. Cascaded frameworks in underwater optical image restoration[J]. Information Fusion, 2025, 117: 102809. doi:
  4. 4.
    WANG Y D, GUO J C, HE W R, et al. Is underwater image enhancement all object detectors need?[J]. IEEE Journal of Oceanic Engineering, 2024, 49(2): 606-621. doi:
  5. 5.
    SONG W, WANG Y, HUANG D M, et al. A Rapid Scene Depth Estimation Model based on Underwater Light Attenuation Prior for Underwater Image Restoration[M]. Advances in Multimedia Information Processing-PCM 2018. Cham: Springer International Publishing, 2018: 678-688. doi:
  6. 6.
    ZHOU J C, WANG Y Y, LI C Y, et al. Multicolor light attenuation modeling for underwater image restoration[J]. IEEE Journal of Oceanic Engineering, 2023, 48(4): 1322-1337. doi:
  7. 7.
    ZHOU J C, LIU Q, JIANG Q P, et al. Underwater camera: improving visual perception via adaptive dark pixel prior and color correction[J]. International Journal of Computer Vision, 2023: 1-19. doi:
  8. 8.
    MISHRA A K, KUMAR M, CHOUDHRY M S. Underwater image enhancement by using transmission optimization and background light estimation via principal component analysis fusion[J]. Signal, Image and Video Processing, 2024, 18(4): 3855-3865. doi:
  9. 9.
    LIU Q, HE Z X, ZHANG D H, et al. DRC: Chromatic aberration intensity priors for underwater image enhancement[J]. Journal of Visual Communication and Image Representation, 2024, 98: 104065. doi:
  10. 10.
    ZHANG W D, WANG Y D, LI C Y. Underwater image enhancement by attenuated color channel correction and detail preserved contrast enhancement[J]. IEEE Journal of Oceanic Engineering, 2022, 47(3): 718-735. doi:
  11. 11.
    ZHANG W D, ZHOU L, ZHUANG P X, et al. Underwater image enhancement via weighted wavelet visual perception fusion[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(4): 2469-2483. doi:
  12. 12.
    LIANG Z, ZHANG W D, RUAN R, et al. Underwater image quality improvement via color, detail, and contrast restoration[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(3): 1726-1742. doi:
  13. 13.
    LIN S, ZHA Z Y. Underwater image restoration method combining color compensation and dual background light fusion[J]. Opt. Precision Eng., 2024, 32(7): 1059-1074. (in Chinese). doi:
  14. 14.
    ISLAM M J, XIA Y Y, SATTAR J. Fast underwater image enhancement for improved visual perception[J]. IEEE Robotics and Automation Letters, 2020, 5(2): 3227-3234. doi:
  15. 15.
    NAIK A, SWARNAKAR A, MITTAL K. Shallow-UWnet: compressed model for underwater image enhancement (student abstract)[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(18): 15853-15854. doi:
  16. 16.
    XUE X W, LI Z X, MA L, et al. Investigating intrinsic degradation factors by multi-branch aggregation for real-world underwater image enhancement[J]. Pattern Recognition, 2023, 133: 109041. doi:
  17. 17.
    WANG H W, YANG M, YIN G, et al. Self-adversarial generative adversarial network for underwater image enhancement[J]. IEEE Journal of Oceanic Engineering, 2024, 49(1): 237-248. doi:
  18. 18.
    ZHANG D H, ZHOU J C, ZHANG W S, et al. ReX-Net: a reflectance-guided underwater image enhancement network for extreme scenarios[J]. Expert Systems with Applications, 2023, 231: 120842. doi:
  19. 19.
    SHANG J S, LI Y, XING H, et al. LGT: Luminance-guided transformer-based multi-feature fusion network for underwater image enhancement[J]. Information Fusion, 2025, 118: 102977. doi:
  20. 20.
    YAO T T, FENG Z H, ZHAO H X. Underwater image enhancement by integrating domain transfer and attention mechanisms[J]. Opt. Precision Eng., 2025, 33(2): 298-310. (in Chinese). doi:
  21. 21.
    JAFFE J S. Computer modeling and the design of optimal underwater imaging systems[J]. IEEE Journal of Oceanic Engineering, 1990, 15(2): 101-111. doi:
  22. 22.
    HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior[C]. 2009 IEEE Conference on Computer Vision and Pattern Recognition.20-25,2009, Miami, FL, USA. IEEE, 2009: 1956-1963. doi:
  23. 23.
    DREWS P JR, NASCIMENTO EDO, MORAES F, et al. Transmission estimation in underwater single images[C]. 2013 IEEE International Conference on Computer Vision Workshops.2-8,2013, Sydney, NSW, Australia. IEEE, 2013: 825-830. doi:
  24. 24.
    GALDRAN A, PARDO D, PICÓN A, et al. Automatic Red-Channel underwater image restoration[J]. Journal of Visual Communication and Image Representation, 2015, 26: 132-145. doi:
  25. 25.
    PENG Y T, CAO K M, COSMAN P C. Generalization of the dark channel prior for single image restoration[J]. IEEE Transactions on Image Processing, 2018, 27(6): 2856-2868. doi:
  26. 26.
    SONG W, WANG Y, HUANG D M, et al. Enhancement of underwater images with statistical model of background light and optimization of transmission map[J]. IEEE Transactions on Broadcasting, 2020, 66(1): 153-169. doi:
  27. 27.
    JIN Z M, MA Y, MIN L H, et al. Variational image dehazing with a novel underwater dark channel prior[J]. Inverse Problems and Imaging, 2024. doi:
  28. 28.
    CARLEVARIS-BIANCO N, MOHAN A, EUSTICE R M. Initial results in underwater single image dehazing[C]. OCEANS 2010 MTS/IEEE SEATTLE.20-23,2010, Seattle, WA, USA. IEEE, 2010: 1-8. doi:
  29. 29.
    YU H F, LI X B, LOU Q, et al. Underwater image enhancement based on DCP and depth transmission map[J]. Multimedia Tools and Applications, 2020, 79(27): 20373-20390. doi:
  30. 30.
    LI C Y, GUO C L, REN W Q, et al. An underwater image enhancement benchmark dataset and beyond[J]. IEEE Transactions on Image Processing, 2019. doi:
  31. 31.
    LIU R S, FAN X, ZHU M, et al. Real-world underwater enhancement: challenges, benchmarks, and solutions under natural light[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30(12): 4861-4875. doi:
  32. 32.
    YANG M, SOWMYA A. An underwater color image quality evaluation metric[J]. IEEE Transactions on Image Processing, 2015, 24(12): 6062-6071. doi:
  33. 33.
    PANETTA K, GAO C, AGAIAN S. Human-visual-system-inspired underwater image quality measures[J]. IEEE Journal of Oceanic Engineering, 2016, 41(3): 541-551. doi:
  34. 34.
    WANG Y, LI N, LI Z Y, et al. An imaging-inspired no-reference underwater color image quality assessment metric[J]. Computers & Electrical Engineering, 2018, 70: 904-913. doi:
  35. 35.
    CANNY J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI-8(6): 679-698. doi:
  36. 36.
    BAY H, TUYTELAARS T, VAN GOOL L. SURF: speeded up robust features[C]. Computer Vision-ECCV 2006. Berlin, Heidelberg: Springer Berlin Heidelberg, 2006: 404-417. doi:
  37. 37.
    ZHOU L, LIU Q M, JIN K J, et al. Research progress of underwater image restoration and enhancement methods[J]. Journal of Image and Graphics, 2025, 30(1): 51-65. (in Chinese). doi:
  38. 38.
    CHENG Z, FAN G D, ZHOU J C, et al. FDCE-net: underwater image enhancement with embedding frequency and dual color encoder[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2025, 35(2): 1728-1744. doi:
  39. 39.
    ISLAM M J, EDGE C, XIAO Y Y, et al. Semantic segmentation of underwater imagery: dataset and benchmark[C]. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).24-24,2021, Las Vegas, NV, USA. IEEE, 2020: 1769-1776. doi:
  40. 40.
    LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).21-26,2017, Honolulu, HI, USA. IEEE, 2017: 936-944. doi:

Leia o texto completo

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website