基于小波变换的水下显著性目标快速检测算法

doi:10.19678/j.issn.1000-3428.0064278

摘要/Abstract

摘要： 目前地面显著性目标检测取得了较大进展，而水下场景具有较高的复杂性，导致水下显著性目标检测仍然面临诸多挑战。为了实现复杂水下环境的显著性目标快速检测，提出一种基于小波变换的水下显著性目标检测算法。对水下采集图像进行多级小波变换预处理，针对提取的低频子带图像，利用自适应中值滤波去除其中的斑点颗粒，对相应的高频子带进行显著性边缘检测以强化目标边缘信息。在此基础上，利用小尺度超像素分割与合并策略分割处理后的低频子带图像，通过基于区域对比度的显著性检测方法进行图像显著性计算。融合低频子带显著图和高频子带显著边缘图，得到最终的显著性检测结果。USOD公开数据集上的实验结果表明，在进行水下显著性目标检测时该算法的整体度量值达到93.9%，平均绝对误差低至3.08%，能较好地实现水下大目标和成群小目标的准确检测，且在处理大分辨率水下图像时具有良好的实时性，在CPU平台上每帧的显著性目标检测时间为168 ms，算法适用于水下机器人显著性目标快速检测应用场景。

关键词: 水下目标, 显著性检测, 小波变换, 超像素分割, 区域对比度

Abstract: Ground-based salient object detection has made significant advances;however, the complexity of underwater scenes has led to many challenges in underwater salient object detection.For rapid detection of salient objects in complex underwater environments, an underwater salient object detection algorithm based on wavelet transform has been proposed in this study.The underwater image is preprocessed by multilevel wavelet transforms.For the extracted low-frequency sub-band image, the speckle particles are removed by an adaptive median filter, and the corresponding high-frequency sub-band is identified by significant edge detection to strengthen the object edge information.Based on this, the low-frequency sub-band image is segmented using a small-scale super-pixel segmentation and merging strategy, and the regional contrast-based saliency detection method is applied to calculate the image saliency.The final saliency detection result is obtained by fusing the low-frequency sub-band saliency and high-frequency sub-band saliency edge images.Experimentally, the Underwater Salient Object Detection(USOD) public dataset revealed that the overall measurement value of the algorithm is 93.9% with a Mean Absolute Error(MAE) of 3.08%, making it suitable for accurate detection of large underwater objects and small groups of objects while also providing good real-time performance in processing high-resolution underwater images.The average salient object detection time of each frame on the CPU platform was 168 ms, and the algorithm is applicable to the rapid detection of salient objects of underwater vehicles.

Key words: underwater object, salient detection, wavelet transform, superpixel segmentation, region contrast

中图分类号:

TP391

孙欣悦, 李庆忠. 基于小波变换的水下显著性目标快速检测算法[J]. 计算机工程, 2023, 49(4): 249-255.

SUN Xinyue, LI Qingzhong. Wavelet-Transform Based Fast Underwater Salient Object Detection Algorithm[J]. Computer Engineering, 2023, 49(4): 249-255.

http://www.ecice06.com/CN/Y2023/V49/I4/249

图/表 7

20230417190220

20230417190223

20230417190226

20230417190229

20230417190232

20230417190235

20230417190238

参考文献

[1] ZHANG L, LI C, SUN H.Object detection/tracking toward underwater photographs by Remotely Operated Vehicles(ROVs)[J].Future Generation Computer Systems, 2022, 126:163-168.
[2] PRANAV M V, SHREYAS MADHAV A V, MEENA J.DeepRecog:threefold underwater image deblurring and object recognition framework for AUV vision systems[J].Multimedia Systems, 2022, 28(2):583-593.
[3] KUMAR N, SARDANA H K, SHOME S N, et al.Saliency-based classification of objects in unconstrained underwater environments[J].Multimedia Tools and Applications, 2020, 79(35):25835-25851.
[4] LIU J J, HOU Q B, CHENG M M, et al.A simple pooling-based design for real-time salient object detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:3912-3921.
[5] LI X, HAO J, SHANG M, et al.Saliency segmentation and foreground extraction of underwater image based on localization[C]//Proceedings of OCEANS'16.Washington D.C., USA:IEEE Press, 2016:1-4.
[6] JIAN M, QI Q, DONG J, et al.Integrating QDWD with pattern distinctness and local contrast for underwater saliency detection[J].Journal of Visual Communication and Image Representation, 2018, 53:31-41.
[7] KUMAR N, SARDANA H K, SHOME S N.Saliency based shape extraction of objects in unconstrained underwater environment[J].Multimedia Tools and Applications, 2019, 78(11):15121-15139.
[8] CHEN Z, GAO H, ZHANG Z, et al.Underwater salient object detection by combining 2D and 3D visual features[J].Neurocomputing, 2020, 391:249-259.
[9] FENG H, XU L Z, YIN X H, et al.Underwater salient object detection based on red channel correction[C]//Proceedings of the 2nd IEEE International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering.Washington D.C., USA:IEEE Press, 2021:446-449.
[10] 孙杨, 陈哲, 王慧斌, 等.融合区域和边缘特征的水平集水下图像分割[J].中国图象图形学报, 2020, 25(4):824-835. SUN Y, CHEN Z, WANG H B, et al.Level set method combining region and edge features for segmenting underwater images[J].Journal of Image and Graphics, 2020, 25(4):824-835.(in Chinese)
[11] 郭继昌, 汪昱东, 刘迪, 等.基于图像风格转换的水下图像显著性检测算法[J].数据采集与处理, 2021, 36(1):35-44. GUO J C, WANG Y D, LIU D, et al.Underwater image salient object detection algorithm based on image style transfer[J].Journal of Data Acquisition and Processing, 2021, 36(1):35-44.(in Chinese)
[12] HUANG S Q, HUANG M X, ZHANG Y, et al.Under water object detection based on convolution neural network[C]//Proceedings of International Conference on Web Information Systems and Applications.Berlin, Germany:Springer, 2019:47-58.
[13] LI S C, JIN X, YAO S B, et al.Underwater small target recognition based on convolutional neural network[EB/OL].[2022-02-05].https://www.semanticscholar.org/paper/Underwater-Small-Target-Recognition-Based-on-Neural-Li-Jin/8923b852a95535181c011c11f7a280e6773cb4ca.
[14] PENG Y T, LIN Y C, PENG W Y.Blurriness guided underwater salient object detection[C]//Proceedings of OCEANS'21.Washington D.C., USA:IEEE Press, 2022:1-5.
[15] 李景玉, 张荣芬, 刘宇红.基于小波变换的多尺度图像融合增强算法[J].光学技术, 2021, 47(2):217-222. LI J Y, ZHANG R F, LIU Y H.Multiscale image fusion and enhancement algorithm based on wavelet transform[J].Optical Technique, 2021, 47(2):217-222.(in Chinese)
[16] 丁陈梅, 王涛, 孙权森.基于多尺度超像素和图割的交互式图像分割算法[J].计算机与数字工程, 2019, 47(12):3160-3163, 3172. DING C M, WANG T, SUN Q S.An interactive segmentation algorithm combined with multi-scale superpixel and graph cut[J].Computer & Digital Engineering, 2019, 47(12):3160-3163, 3172.(in Chinese)
[17] 刘晓阳, 薛纯.基于多尺度的水下图像显著性区域检测[J].微型机与应用, 2017, 36(9):45-48. LIU X Y, XUE C.Underwater image saliency detection based on multi-scale[J].Microcomputer & Its Applications, 2017, 36(9):45-48.(in Chinese)
[18] ACHANTA R, SHAJI A, SMITH K, et al.SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11):2274-2282.
[19] CHENG M M, MITRA N J, HUANG X L, et al.Global contrast based salient region detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3):569-582.
[20] CHEN B, ZHANG X, WANG R T, et al.Detect concrete cracks based on OTSU algorithm with differential image[J].The Journal of Engineering, 2019(23):9088-9091.
[21] ISLAM M J, WANG R B, SATTAR J.SVAM:saliency-guided visual attention modeling by autonomous underwater robots[EB/OL].[2022-02-05].https://arxiv.org/abs/2011.06252.
[22] YANG C, ZHANG L H, LU H C, et al.Saliency detection via graph-based manifold ranking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2013:3166-3173.
[23] CHEN Z, SUN Y, GU Y P, et al.Underwater object segmentation integrating transmission and saliency features[J].IEEE Access, 2019, 7:72420-72430.
[24] QIN X B, ZHANG Z C, HUANG C Y, et al.BASNet:boundary-aware salient object detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:7471-7481.
[25] ISLAM M J, LUO P G, SATTAR J.Simultaneous enhancement and super-resolution of underwater imagery for improved visual perception[EB/OL].[2022-02-05].https://arxiv.org/abs/2002.01155.

选择文件类型/文献管理软件名称

选择包含的内容