Bridge Crack Extraction Based on Weighted Entropy and Hybrid Bald Eagle-Aquila Optimization FCM Clustering

doi:10.16183/j.cnki.jsjtu.2024.119

Abstract

Abstract:

To address the problems of low recognition accuracy and loss of feature information caused by shadows and uneven lighting in traditional clustering algorithms for bridge crack extraction, this paper proposes a bridge crack extraction method based on an improved fuzzy C-means (FCM) clustering algorithm using a hybrid bald eagle-aquila optimizer (HBAO) with cross-iteration enhancement. First, a coupled chaotic mapping initialization was introduced, and refraction learning was integrated to increase population diversity. Next, to enhance the performance of the global search phase of the bald eagle search (BES) algorithm, this phase was replaced with the expanded and narrowed search strategy of the BES optimization, significantly improving the convergence behavior and global search ability of BES, thereby increasing the success rate of FCM in finding optimal cluster centers. Then, the HBAO was combined with a weighted entropy method to jointly optimize the FCM clustering algorithm, improving robustness while enhancing search accuracy to achieve better clustering results. Finally, the clustering performance evaluation experiment was conducted on the UCI standard datasets against six comparative algorithms, demonstrating the superior overall performance of the proposed algorithm. Furthermore, the proposed algorithm was tested on four different fracture patterns. Experimental results show that compared with other similar algorithms, the proposed algorithm has the best performance in crack extraction.

Key words: fuzzy C-means (FCM) clustering, bald eagle search (BES) algorithm, bridge crack extraction, information entropy

CLC Number:

TP391.9

WEN Xialu, HUANG He, WANG Huifeng, GAO Tao. Bridge Crack Extraction Based on Weighted Entropy and Hybrid Bald Eagle-Aquila Optimization FCM Clustering[J]. Journal of Shanghai Jiao Tong University, 2026, 60(5): 751-761.

Figures/Tables 13

Fig.1

Fig.2

Tab.1

Fig.3

Tab.2

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Tab.3

Fig.10

References 20

[1]	MUNAWAR H S, HAMMAD A W, HADDAD A, et al. Image-based crack detection methods: A review[J]. Infrastructures, 2021, 6(8): 115-115. doi: 10.3390/infrastructures6080115 URL
[2]	ZHANG J, QIAN S, TAN C. Automated bridge surface crack detection and segmentation using computer vision-based deep learning model[J]. Engineering Applications of Artificial Intelligence, 2022, 115: 105225. doi: 10.1016/j.engappai.2022.105225 URL
[3]	TRAN T S, NGUYEN S D, LEE H J, et al. Advanced crack detection and segmentation on bridge decks using deep learning[J]. Construction and Building Materials, 2023, 400: 132839. doi: 10.1016/j.conbuildmat.2023.132839 URL
[4]	XIAO Y, LI J. Crack detection algorithm based on the fusion of percolation theory and adaptive canny operator[C]// Chinese Control Conference (CCC). Wuhan, China: IEEE, 2018: 859-863.
[5]	LIANG Z, LUO W, XU Y. Bridge crack image segmentation based on improved watershed algorithm[C]// Chinese Control and Decision Conference (CCDC). Shenyang, China: IEEE, 2018: 770-774.
[6]	GEHRI N, MATA-FALCON J, KAUFMANN W. Automated crack detection and measurement based on digital image correlation[J]. Construction and Building Materials, 2020, 256: 119383. doi: 10.1016/j.conbuildmat.2020.119383 URL
[7]	ZHAO H, DING Y, LI A, et al. Live-load strain evaluation of the prestressed concrete box-girder bridge using deep learning and clustering[J]. Structural Health Monitoring, 2020, 19(4): 1051-1063. doi: 10.1177/1475921719875630 URL
[8]	ZHANG Z, SHEN Z, LIU J, et al. A binocular vision-based crack detection and measurement method incorporating semantic segmentation[J]. Sensors, 2023, 24(1): 3. doi: 10.3390/s24010003 URL
[9]	ZHANG H, SHEN Z, LIN Z, et al. Deep learning-based automatic classification of three-level surface information in bridge inspection[J]. Computer-Aided Civil and Infrastructure Engineering, 2023, 39(10): 1431-1451. doi: 10.1111/mice.13117 URL
[10]	鲁斌, 范晓明. 基于改进自适应k均值聚类的三维点云骨架提取的研究[J]. 自动化学报, 2022, 48(8): 1994-2006.
	LU Bin, FAN Xiaoming. Research on 3D point cloud skeleton extraction based on improved adaptive k-means clustering[J]. Journal of Automation, 2022, 48 (8): 1994-2006.
[11]	CHENG F, NIU G, ZHANG Z, et al. Improved CNN-based indoor localization by using RGB images and DBSCAN algorithm[J]. Sensors, 2022, 22(23): 9531. doi: 10.3390/s22239531 URL
[12]	SHI Y. Application of FCM clustering algorithm in digital library management system[J]. Electronics, 2022, 11(23): 3916-3916. doi: 10.3390/electronics11233916 URL
[13]	LI Z, YI J, WANG G. A new swarm intelligence approach for clustering based on krill herd with elitism strategy[J]. Algorithms, 2015, 8(4): 951-964. doi: 10.3390/a8040951 URL
[14]	ZHANG L, WANG J, AN Z. FCM fuzzy clustering image segmentation algorithm based on fractional particle swarm optimization[J]. Journal of Intelligent & Fuzzy Systems, 2020, 38(4): 3575-3584.
[15]	ALSATTAR A H, ZAIDAN A A, ZAIDAN B B. Novel meta-heuristic bald eagle search optimisation algorithm[J]. Artificial Intelligence Review, 2020, 53(8): 2237-2264. doi: 10.1007/s10462-019-09732-5
[16]	DEHGHANI M. Pelican optimization algorithm: A novel nature-inspired algorithm for engineering applications[J]. Sensors, 2022, 22(3): 855. doi: 10.3390/s22030855 URL
[17]	黄鹤, 李文龙, 杨澜, 等. DHSSA优化的K均值互补迭代车型信息数据聚类[J]. 汽车工程, 2022, 44(5): 691-700.
	HUANG He, LI Wenlong, YANG Lan, et al. K-means complementary iterative vehicle information data clustering based on DHSSA optimization[J]. Automotive Engineering, 2022, 44(5): 691-700.
[18]	ZHU S, XIA X, ZHANG Q, et al. An image segmentation algorithm in image processing based on threshold segmentation[C]// 2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System. Shanghai, China: IEEE, 2007: 673-678.
[19]	SONG R, ZHANG Z, LIU H. Edge connection based Canny edge detection algorithm[J]. Pattern Recognition and Image Analysis, 2017, 27(4): 740-747. doi: 10.1134/S1054661817040162
[20]	黄鹤, 李文龙, 杨澜, 等. 跳跃跟踪SSA交叉迭代AP聚类算法[J]. 电子学报, 2024, 52(3): 977-990. doi: 10.12263/DZXB.20220209
	HUANG He, LI Wenlong, YANG Lan, et al. Jump tracking SSA cross iterative AP clustering algorithm[J]. Journal of Electronics, 2024, 52 (3): 977-990.

数据集	n	D	C	各类别样本数
Aggregation	788	2	7	170, 34, 273, 102, 130, 45, 34
Iris	150	4	3	50, 50, 50
Cancer	683	9	2	444, 239
Vowel	871	3	6	72, 89, 172, 151, 207, 180

数据集	算法	T_ACC /%	T_rand /%	T_ARI /%
Aggregation	KMC	90.86	92.50	76.32
	DHSSA-KMC	90.36	93.74	82.71
	DBSCAN	69.80	91.74	63.79
	FCM	79.18	92.73	72.43
	BES-FCM	84.39	92.66	76.42
	POA-FCM	86.68	92.84	77.35
	本文算法	96.86	94.01	82.30
Iris	KMC	90.00	77.24	40.88
	DHSSA-KMC	91.20	80.44	52.68
	DBSCAN	89.33	77.97	43.02
	FCM	68.00	77.66	46.38
	BES-FCM	88.00	86.79	70.74
	POA-FCM	90.00	88.59	74.37
	本文算法	94.33	89.97	75.94
Cancer	KMC	96.78	85.72	71.72
	DHSSA-KMC	96.63	85.58	71.44
	DBSCAN	94.06	82.39	62.65
	FCM	75.26	63.67	53.63
	BES-FCM	96.05	92.40	84.65
	POA-FCM	96.19	92.67	85.20
	本文算法	97.02	94.53	88.84
Vowel	KMC	59.70	80.47	34.56
	DHSSA-KMC	56.95	78.20	29.63
	DBSCAN	58.44	80.16	32.26
	FCM	56.75	72.87	30.11
	BES-FCM	58.11	80.55	33.32
	POA-FCM	58.22	79.99	31.58
	本文算法	60.28	88.49	34.67

裂缝分割方法	R_pre	R_rec	R_F1	耗时/s
全局阈值分割	0.936	0.928	0.932	0.296
Canny边缘检测	0.952	0.963	0.957	0.879
KMC聚类分割	0.967	0.972	0.969	1.485
AP聚类分割	0.977	0.983	0.979	1.462
本文算法	0.983	0.987	0.985	1.273