粒子群优化的深海图像暗边缘检测优化算法

doi:10.3969/j.issn.0255-8297.2023.01.012

摘要/Abstract

摘要： 为解决深海资源探测图像识别难题，提出一种基于粒子群优化的图像暗边缘检测优化算法。该算法通过指数型线性单元和高斯误差线性单元改进激活函数，根据Marr-Hildreth算子检测结果并结合改进激活函数构建暗边缘检测算法，利用粒子群对改进暗边缘检测算法进行训练和优化。最后，采用不同算法对水下11个数据集进行比较的结果表明：改进算法的峰值信噪比、结构相似度和边缘保持指数最高，分别达到18.769 6 dB、0.660 7和0.834 5；图像均方误差最低，为3 750.225 3；平均检测时间为0.667 4 s，比其他对比实验中性能最好的算法缩短了14%。

关键词: 深海勘测, 粒子群优化, Marr-Hildreth算子, 暗边缘检测

Abstract: In order to solve the problem of image recognition for deep-sea resource detection, an optimization algorithm of image dark edge detection based on particle swarm optimization is proposed. The algorithm improves activation functions by using exponential linear unit and Gaussian error linear unit, constructs a dark edge detection algorithm in combination with the improved activation function according to the detection results of Marr-Hildreth operator, and uses particle swarm to train and optimize the improved dark edge detection algorithm. Finally, the proposed and several existing algorithms are applied and compared on 11 underwater data sets. Experimental results show that the proposed algorithm has the highest peak signal-to-noise ratio, structural similarity and edge retention index, reaching 18.769 6 dB, 0.660 7 and 0.834 5, respectively, and has the lowest mean square error of image of 3 750.225 3. Its average detection time is 0.667 4 s, about 14% shorter than that of the second best performance algorithm in the experiment.

Key words: deep-sea exploration, particle swarm optimization, Marr-Hildreth operator, dark edge detection

中图分类号:

TP391.41

邹倩颖, 陈晖阳, 李永生, 胡力雯, 王小芳. 粒子群优化的深海图像暗边缘检测优化算法[J]. 应用科学学报, 2023, 41(1): 153-169.

ZOU Qianying, CHEN Huiyang, LI Yongsheng, HU Liwen, WANG Xiaofang. Optimization Algorithm for Dark Edge Detection of Deep-Sea Image Based on Particle Swarm Optimization[J]. Journal of Applied Sciences, 2023, 41(1): 153-169.

参考文献

[1] 高岩, 李波. 我国深海微生物资源研发现状、挑战与对策[J]. 生物资源, 2018, 40(1):13-17. DOI:10.14188/j.ajsh.2018.01.003. Gao Y, Li B. Advances and challenges in deep sea microbial resource research and development of China[J]. Biotic Resources, 2018, 40(1):13-17. DOI:10.14188/j.ajsh.2018.01.003. (in Chinese)
[2] 刘峰, 刘予, 宋成兵, 等. 中国深海大洋事业跨越发展的三十年[J]. 中国有色金属学报, 2021, 31(10):2613-2623. DOI:10.11817/j.ysxb.1004.0609.2021-42112. Liu F, Liu Y, Song C B, et al. Three decades' development of China in deepsea field[J]. The Chinese Journal of Nonferrous Metals, 2021, 31(10):2613-2623. DOI:10.11817/j.ysxb.1004.0609.2021-42112. (in Chinese)
[3] Otsu N. A threshold selection method from gray level histograms[J]. IEEE Transactions on Systems Man and Cybernetics, 1979, 9(1):62-66.
[4] Canny J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6):679-698.
[5] He Y, Zheng B, Ding Y, et al. Underwater image edge detection based on K-means algorithm[C]//2014 Oceans-St. John's Conference & Exhibition, IEEE, 2014:1-4.
[6] 刘建思, 尹丽菊, 潘金凤, 等. 基于参数化对数图像处理模型的光照不均匀图像的边缘检测算法[J]. 激光与光电子学进展, 2021, 58(22):140-149.Liu J S, Yin L J, Pan J F, et al. Edge detection algorithm for unevenly inuminated images based on parameterized logarithmic image processing model[J]. Laser & Optoelectronics Progress, 2021, 58(22):140-149. (in Chinese)
[7] 李庆忠, 刘晓丽, 谷娜娜. 水下人造目标线特征快速检测算法[J]. 计算机工程与应用, 2014, 50(11):180-183, 228. Li Q Z, Liu X L, Gu N N. Fast line detection algorithm for underwater man-made objects[J]. Computer Engineering and Applications, 2014, 50(11):180-183, 228. (in Chinese)
[8] 颜明重, 黄冰逸, 朱大奇. 基于灰度波动的水下图像分割[J]. 哈尔滨工程大学学报, 2020, 41(9):1268-1273. Yan M Z, Huang B Y, Zhu D Q. Underwater image segmentation based on grayscale wave[J]. Journal of Harbin Engineering University, 2020, 41(9):1268-1273. (in Chinese)
[9] 陈凯峰, 梁鉴如, 陈强, 等. 基于FPGA和CNN的水下目标识别系统[J]. 传感器与微系统, 2021, 40(4):103-105, 109. DOI:10.13873/J.1000-9787(2021)04-0103-03. Chen K F, Liang J R, Chen Q, et al. Underwater target recognition system based on FPGA and CNN[J]. Transducer and Microsystem Technologies, 2021, 40(4):103-105, 109. DOI:10.13873/J.1000-9787(2021)04-0103-03. (in Chinese)
[10] 闫晓鹏. 离散小波变换在水下航行器目标图像降噪中的应用[J]. 舰船科学技术, 2021, 43(22):67-69. Yan X P. Application of discrete wavelet transform in underwater vehicle target image denoising[J]. Ship Science and Technology, 2021, 43(22):67-69. (in Chinese)
[11] Dong X H, Li M H, Miao J S, et al. Edge detection operator for underwater target image[C]//2018 IEEE 3rd International Conference on Image, Vision and Computing, 2018:91-95.
[12] 盛明伟, 唐松奇, 万磊, 等. 基于改进CNN-RANSAC的水下图像特征配准方法[J]. 计算机工程与科学, 2020, 42(5):859-868. Sheng M W, Tang S Q, Wan L, et al. An underwater image feature registration method based on improved CNN-RANSAC[J]. Computer Engineering & Science, 2020, 42(5):859-868. (in Chinese)
[13] 宋绍剑, 朱靖旭. 基于Mask R-CNN和迁移学习的水下生物目标识别研究[J]. 计算机应用研究, 2020, 37(增刊2):386-388, 391. Song S J, Zhu J X. Object recognition research of underwater creature based on mask R-CNN and transfer learning[J]. Application Research of Computers, 2020, 37(Suppl.2):386-388, 391. (in Chinese)
[14] Kamal S, Mohammed S K, Pillai P R S, et al. Deep learning architectures for underwater target recognition[C]//2013 International Symposium on Ocean Electronics, IEEE, 2013:48-54.
[15] 刘有用, 张江梅, 王坤朋, 等. 不平衡数据集下的水下目标快速识别方法[J]. 计算机工程与应用, 2020, 56(17):236-242. Liu Y Y, Zhang J M, Wang K P, et al. Fast underwater target recognition with unbalanced data set[J]. Computer Engineering and Applications, 2020, 56(17):236-242. (in Chinese)
[16] 刘波, 林焰, 王运龙. 水下图像边缘特征提取的BEMD自适应算法[J]. 哈尔滨工业大学学报, 2013, 45(2):117-122. Liu B, Lin Y, Wang Y L. Bi-dimensional empirical mode decomposition algorithm for underwater image edge detecting[J]. Journal of Harbin Institute of Technology, 2013, 45(2):117-122. (in Chinese)
[17] 郭雷. Marr-Hildreth边界检测器定位性能分析[J]. 自动化学报, 1990, 16(1):40-45. Guo L. Marr-Hildreth edge detector location error[J]. Acta Automatica Sinica, 1990, 16(1):40-45. (in Chinese)
[18] Trottier L, Giguere P, Chaib-Draa B. Parametric exponential linear unit for deep convolutional neural networks[C]//201716th IEEE International Conference on Machine Learning and Applications, 2017:207-214.
[19] Hendrycks D, Gimpel K. Gaussian error linear units (GELUs)[DB/OL]. (2020-07-08)[2022-10-15]. https://arxiv.org/abs/1606.08415.
[20] Kennedy J, Eberhart R. Particle swarm optimization[C]//Proceedings of ICNN'95-International Conference on Neural Networks, IEEE, 1995, 4:1942-1948.
[21] Cutter G, Stierhoff K, Zeng J. Automated detection of rockfish in unconstrained underwater videos using Haar cascades and a new image dataset:labeled fishes in the wild[C]//2015 IEEE Winter Applications and Computer Vision Workshops, 2015:57-62.
[22] Li J, Skinner K A, Eustice R M, et al. WaterGAN:unsupervised generative network to enable real-time color correction of monocular underwater images[J]. IEEE Robotics and Automation Letters, 2017, 3(1):387-394.
[23] Duarte A, Codevilla F, Gaya J D O, et al. A dataset to evaluate underwater image restoration methods[C]//OCEANS 2016-Shanghai, IEEE, 2016:1-6.
[24] Jian M, Qi Q, Dong J, et al. The OUC-vision large-scale underwater image database[C]//2017 IEEE International Conference on Multimedia and Expo, 2017:1297-1302.
[25] Underwater photography fish database[DB/OL]. (2018-01-01)[2022-10-15]. http://www. fishdb.co.uk/.
[26] Northeast Fisheries Science Center. Habitat mapping camera (HAB-CAM)[DB/OL]. (2012-06-01)[2022-10-15]. https://inport.nmfs.noaa.gov/inport/item/27598.
[27] 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.
[28] Marques T P, Albu A B, Hoeberechts M. A contrast-guided approach for the enhancement of low-lighting underwater images[J]. Journal of Imaging, 2019, 5(10):79-83.
[29] Berman D, Levy D, Avidan S, et al. Underwater single image color restoration using hazelines and a new quantitative dataset[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 43(8):2822-2837.