Underwater Object Detection and Reconstruction Based on Active Single-Pixel Imaging and Super-Resolution Convolutional Neural Network

Due to medium scattering, absorption, and complex light interactions, capturing objects from the underwater environment has always been a difficult task. Single-pixel imaging (SPI) is an efficient imaging approach that can obtain spatial object information under low-light conditions. In this paper, we propose a single-pixel object inspection system for the underwater environment based on compressive sensing super-resolution convolutional neural network (CS-SRCNN). With the CS-SRCNN algorithm, image reconstruction can be achieved with 30% of the total pixels in the image. We also investigate the impact of compression ratios on underwater object SPI reconstruction performance. In addition, we analyzed the effect of peak signal to noise ratio (PSNR) and structural similarity index (SSIM) to determine the image quality of the reconstructed image. Our work is compared to the SPI system and SRCNN method to demonstrate its efficiency in capturing object results from an underwater environment. The PSNR and SSIM of the proposed method have increased to 35.44% and 73.07%, respectively. This work provides new insight into SPI applications and creates a better alternative for underwater optical object imaging to achieve good quality.

[1]  Ayman Alfalou,et al.  Enhancing underwater optical imaging by using a low-pass polarization filter. , 2019, Optics express.

[2]  Monica Mordonini,et al.  Food Image Recognition Using Very Deep Convolutional Networks , 2016, MADiMa @ ACM Multimedia.

[3]  Chen-zhi Guan,et al.  Realtime Multi-Person 2D Pose Estimation using ShuffleNet , 2019, 2019 14th International Conference on Computer Science & Education (ICCSE).

[4]  Xiping Xu,et al.  Active Mode Single Pixel Imaging in the Highly Turbid Water Environment Using Compressive Sensing , 2019, IEEE Access.

[5]  Jens T. Thielemann,et al.  Range-Gated Imaging System for Underwater Monitoring in Ocean Environment , 2018, Sustainability.

[6]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[7]  Zhuo Xu,et al.  Underwater computational ghost imaging. , 2017, Optics express.

[8]  Ying Zhang,et al.  High-visibility underwater ghost imaging in low illumination , 2019, Optics Communications.

[9]  Xiping Xu,et al.  A brief review on 2D and 3D image reconstruction using single-pixel imaging , 2020, Laser Physics.

[10]  Kui Yang,et al.  Polarization-based exploration for clear underwater vision in natural illumination. , 2019, Optics express.

[11]  Anumol Mathai,et al.  3D Transparent Object Detection and Reconstruction Based on Passive Mode Single-Pixel Imaging , 2020, Sensors.

[12]  Roderick Murray-Smith,et al.  Deep learning for real-time single-pixel video , 2018, Scientific Reports.

[13]  Yu Wang,et al.  Efficient underwater image and video enhancement based on Retinex , 2019, Signal Image Video Process..

[14]  Wen-Kai Yu,et al.  Three-dimensional single-pixel compressive reflectivity imaging based on complementary modulation , 2015 .

[15]  Jian Wei Yam,et al.  Characterizing the performance impacts of target surface on underwater pulse laser ranging system , 2020 .

[16]  E.J. Candes.  Compressive Sampling , 2022 .

[17]  Wei Wang,et al.  Deep Learning for Single Image Super-Resolution: A Brief Review , 2018, IEEE Transactions on Multimedia.

[18]  Sarp Ertürk,et al.  Visual enhancement of underwater images using Empirical Mode Decomposition , 2012, Expert Syst. Appl..

[19]  Anumol Mathai,et al.  Transparent Object Detection Using Single-pixel Imaging and Compressive Sensing , 2019, 2019 13th International Conference on Sensing Technology (ICST).

[20]  Anumol Mathai,et al.  A Study into the Effects of Factors Influencing an Underwater, Single-Pixel Imaging System’s Performance , 2019, Photonics.

[21]  Junko Ota,et al.  Super-Resolution Imaging of Mammograms Based on the Super-Resolution Convolutional Neural Network , 2017 .

[22]  Enrique Tajahuerce,et al.  Single-pixel imaging of the retina through scattering media. , 2019, Biomedical optics express.

[23]  Ying Bi,et al.  Underwater Turbulence Detection Using Gated Wavefront Sensing Technique , 2018, Sensors.

[24]  Chengbo Li.  An efficient algorithm for total variation regularization with applications to the single pixel camera and compressive sensing , 2010 .

[25]  Junho Yeom,et al.  Cost-effective Framework for Rapid Underwater Mapping with Digital Camera and Color Correction Method , 2019, KSCE Journal of Civil Engineering.

[26]  Huimin Lu,et al.  Low illumination underwater light field images reconstruction using deep convolutional neural networks , 2018, Future Gener. Comput. Syst..

[27]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  E Tajahuerce,et al.  Single-pixel imaging with Fourier filtering: application to vision through scattering media. , 2018, Optics letters.

[29]  S. Frick,et al.  Compressed Sensing , 2014, Computer Vision, A Reference Guide.

[30]  Florian Willomitzer,et al.  Compressive ghost imaging through scattering media with deep learning. , 2020, Optics express.

[31]  Na Li,et al.  Multi-scale adversarial network for underwater image restoration , 2019, Optics & Laser Technology.

[32]  Liesbet Lagae,et al.  Pixel super-resolution for lens-free holographic microscopy using deep learning neural networks. , 2019, Optics express.

[33]  Fraser Dalgleish,et al.  Underwater laser serial imaging using compressive sensing and digital mirror device , 2011, Defense + Commercial Sensing.

[34]  Dong Xu,et al.  Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey , 2018, IEEE Signal Processing Magazine.

[35]  Qun Hao,et al.  Improving Imaging Quality of Real-time Fourier Single-pixel Imaging via Deep Learning , 2019, Sensors.

[36]  Daniel Buschek,et al.  Neural network identification of people hidden from view with a single-pixel, single-photon detector , 2017, Scientific Reports.

[37]  Xiping Xu,et al.  Non-line-of-sight object detection based on the orthogonal matching pursuit compressive sensing reconstruction , 2020, Other Conferences.

[38]  Josh Harguess,et al.  Image quality assessment for determining efficacy and limitations of Super-Resolution Convolutional Neural Network (SRCNN) , 2019, Optical Engineering + Applications.