Abstract
The complex underwater environment, such as foreign object occlusion and dim light, causes the feature of underwater objects to be seriously missing. And ripple causes deformation of objects, which greatly increases the difficulty of feature extraction. Existing object recognition models cannot accurately recognize obscured objects due to incomplete features of underwater objects. To solve the above problems, this paper proposes an underwater occlusion object recognition method based on two-stage image reconstruction strategy. Firstly, the salient feature extraction network and the relevant environment feature extraction network are constructed to extract the salient feature and the relevant environment feature respectively. Secondly, the two-stage image reconstruction model with gradient penalty constraints is constructed to obtain finely reconstructed images. Finally, the object recognition with feature adaptive boundary regression is constructed to realize the recognition of finely reconstructed images. To prove the effectiveness of the proposed algorithm, it is compared with the existing object recognition model in datasets with different levels of complexity. The average recognition accuracy of the proposed model is 78.36%, and the recognition rate is improved by 14.16% compared to the original image. Experiments show that the object recognition algorithm proposed in this paper is effective and superior to the existing algorithms.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15658-6/MediaObjects/11042_2023_15658_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15658-6/MediaObjects/11042_2023_15658_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15658-6/MediaObjects/11042_2023_15658_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15658-6/MediaObjects/11042_2023_15658_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15658-6/MediaObjects/11042_2023_15658_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15658-6/MediaObjects/11042_2023_15658_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15658-6/MediaObjects/11042_2023_15658_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-15658-6/MediaObjects/11042_2023_15658_Fig8_HTML.png)
Similar content being viewed by others
References
Berman D, Levy D, Avidan S et al (2020) Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset. IEEE Transactions on Pattern Analysis and Machine Intelligence 43(8):2822–2837
Bo D, Lin D (2017) Contrastive Learning for Image Captioning. IEEE/CVF International Conference on Computer Vision and Pattern Recognition 2017:898–907
Bochkovskiy A, Wang CY, Mark Liao HY (2020) YOLOv4: Optimal speed and accuracy of object detection. ar**v:2004.10934
Cai L et al (2021) “derwater Distortion Target Recognition Network (UDTRNet) via Enhanced Image Features.". Comput Intell Neurosci 1:10
Chen Z, Huang S, Tao D (2018) Context refinement for object detection. European Conference on Computer Vision 71–86
Garcia R, Nicosevici T, Gracias N et al (2017) Exploring the seafloor with underwater robots: land, sea & air. Computer vision in vehicle technology 75–99
Girshick R (2015) Fast r-cnn. IEEE International Conference on Computer Vision 2015:1440–1448
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2014:580–587
Goodfellow J, Pouget-Abadie J, Mirza M et al (2014) Generative adversarial nets. In: Advances in neural information processing systems pp 2672–2680
Guo Y, Song H, Liu H et al (2016) Model-based restoration of underwater spectral images captured with narrowband filters. Optics Express 24(12):13101–1312
He Y, Zhu C, Wang, et al (2019) Bounding Box Regression With Uncertainty for Accurate Object Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2883–2892
Huo G, Wu Z, Li J et al (2018) Underwater Target Detection and 3D Reconstruction System Based on Binocular Vision. Sensors 8(18)
Ji D, Li H, Chen CW et al (2018) Visual detection and feature recognition of underwater target using a novel model-based method. Int J Adv Robot Syst 15(6):1–10
Jia S, Zhang Y (2018) Saliency-based deep convolutional neural network for no-reference image quality assessment. Multimedia Tools Appl 77:14859–14872
Jiahui Y, Zhe L, Jimei YX et al (2018) Generative image inpainting with contextual attention. IEEE Conference on Computer Vision and Pattern Recognition 2018:5505–5514
Jiaqi W, Chen K, Yang S et al (2019) Region Proposal by Guided Anchoring. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019:2960–2969
Kamalyan AG, Simonyan VV (2002) On the number of solutions of a certain type of one-dimensional pseudodifferential equations in the Sobolev-Slobedetski space. J Shellfish Res 21(1):201–210
Knausgrd KM, Wiklund A, Srdalen TK et al (2021) Temperate fish detection and classification: a deep learning based approach. Appl Intell 1–14
Langis KD, Fulton M, Sattar J (2021) ”An Analysis of Deep Object Detectors For Diver Detection.” Retrieved from the Data Repository for the University of Minnesota
Lei C, Qiankun S, Tao X, Yukun M, Zhenxue C (2020) Multi-AUV Collaborative Target Recognition Based on Transfer-Reinforcement Learning. IEEE Access 8:39273–39284
Li C, Guo C, Ren W et al (2019) An Underwater Image Enhancement Benchmark Dataset and Beyond. IEEE Trans Image Process 29:4376–4389
Li C, Guo C, Ren W et al (2020) An Underwater Image Enhancement Benchmark Dataset and Beyond. IEEE Trans Image Process 95(12):4376–4389
Li M, Mathai A, Lau SLH et al (2021) Underwater Object Detection and Reconstruction Based on Active Single-Pixel Imaging and Super-Resolution Convolutional Neural Network. Sensors 21(1):313
Liu W, Anguelov D, Erhan D et al (2016) Ssd: Single shot multibox detector. European Conference on Computer Vision (ECCV) 2016:21–37
Liu H, Jiang B, **ao Y et al (2020) Coherent Semantic Attention for Image Inpainting. IEEE/CVF International Conference on Computer Vision and Pattern Recognition 2020:4169–4178
Li H, Yang X, Li ZM et al (2021) Underwater image enhancement with Image Colorfulness Measure. Signal Processing Image Communication. 95(10)
Pathak D, Krahenbuhl P, Donahue J et al (2016) Context encoders: Feature learning by inpainting. IEEE Conference on Computer Vision and Pattern Recognition 2016:2536–2544
Pfeffer A, Wu C, Fry G et al (2019) Software Adaptation for an Unmanned Undersea Vehicle. IEEE Software. 36(2):91–96
Raihan JA, Abas PE, De Silva LC (2019) Review of underwater image restoration algorithms. Iet Image Process 13(10):1587–1596
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. 2016 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 779–788
Sanjeev A, Hrishikesh K, Mikhail K et al (2019) A Theoretical Analysis of Contrastive Unsupervised Representation Learning. International Conference on Machine Learning 9904–9923
Shaoqing R, Kaiming H, Girshick R, Sun J (2017) Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(6):1137–1149
Shi T, Liu M, Niu Y et al (2020) Underwater targets detection and classification in complex scenes based on an improved YOLOv3 algorithm. J Electron Imaging 29(4):1–10
Tamou AB, Benzinou A (2021) Nasreddine K Multi-stream Fish Detection in Unconstrained Underwater Videos by the Fusion of Two Convolutional Neural Network Detectors. Appl Intell 15(2):5809–5821
Tengyue L, Shenghui R, Xueting C et al (2020) Underwater image enhancement framework and its application on an autonomous underwater vehicle platform. Opt Eng 59(8):1–12
Tianning Y, Wan F, Mengying F (2021) Multiple Instance Active Learning for Object Detection. Computer Vision and Pattern Recognition
Tuanji W, Jianhua L, Yi L et al (2003) Image quality evaluation based on image weighted separating block peak signal to noise ratio. International Conference on Neural Networks & Signal Processing 994–997
Tuncel E, Ferhatosmanoglu H, Rose K (2002) VQ-Index: An Index Structure for Similarity Searching in Multimedia Databases. International Conference of Multimedia 543–552
Wang D, He D (2021) Channel pruned YOLO V5s-based deep learning approach for rapid and accurate apple fruitlet detection before fruit thinning. Biosyst Eng 210(6):271–281
Wang X, Ouyang J, Dayu LI et al (2019) Underwater Object Recognition Based on Deep Encoding-Decoding Network. J Ocean Univ China 18(2):120–126
Wynn RB, Huvenne V, Murton BJ et al (2014) Autonomous Underwater Vehicles (AUVs): Their past, present and future contributions to the advancement of marine geoscience. Marine Geol 352:451–468
Yamashita A, Fujii M, Kaneko T (2007) Color registration of underwater images for underwater sensing with consideration of light attenuation. Proceedings of 2007 IEEE international conference on robotics and automation 4570–4575
Yang S, Wang J, Deng B et al (2021) Neuromorphic Context-Dependent Learning Framework With Fault-Tolerant Spike Routing. IEEE Transactions on Neural Networks and Learning Systems 99:1–15
Yang S, Wang J, Zhang N et al (2021) CerebelluMorphic: Large-Scale Neuromorphic Model and Architecture for Supervised Motor Learning. IEEE Transactions on Neural Networks and Learning Systems 99:1–15
Yang S, Deng B, Wang J et al (2019) Scalable Digital Neuromorphic Architecture for Large-Scale Biophysically Meaningful Neural Network With Multi-Compartment Neurons. IEEE Transactions on Neural Networks and Learning Systems 1–15
Yang S, Gao T, Wang J et al (2021) Efficient Spike-Driven Learning With Dendritic Event-Based Processing. Frontiers in neuroscience 15
Yu X, **ng X, Zheng H et al (2018) Man-made object recognition from underwater optical images using deep learning and transfer learning. IEEE international conference on acoustics, speech and signal processing (ICASSP) 1852–1856
Zhang Y, Aydin TO (2021) Deep HDR estimation with generative detail reconstruction. Comput Graphics Forum 40(2):179–190
Acknowledgements
This work was supported by the Major Science and Technology Project in Henan Province [221100110500], Science and Technology Project of Henan Province [232102320338, 222102210157].
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare no conflicts of interest regarding the publication of this paper. And The datasets generated and/or analyzed during the present study are available from the corresponding author on reasonable request.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Jiyong Zhou, Tao Xu, Wantao Guo, Weishuo Zhao and Lei Cai contributed equally to this work.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhou, J., Xu, T., Guo, W. et al. Underwater occluded object recognition with two-stage image reconstruction strategy. Multimed Tools Appl 83, 11127–11146 (2024). https://doi.org/10.1007/s11042-023-15658-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15658-6