The convergence of deep learning (DL) and the Internet of Things (IoT) is revolutionizing vision-based structural health monitoring (SHM) by enabling unprecedented levels of intelligence and remote operability. However, the effective integration of SHM, DL, and IoT into a synergistic system remains significantly challenged by persistent disciplinary silos and a lack of systematic understanding regarding cross-domain knowledge transfer. This gap impedes the translation of domain-specific knowledge into practical engineering applications. To address this, we propose a vision-based smart structural health monitoring (VS-SHM) system framework and conceptualize the core interdisciplinary integration challenges as six forces. These forces effectively interconnect the three distinct domains of SHM, DL, and IoT: between SHM and IoT lie (1) Efficient Data Acquisition and Uninterrupted Flow, and (2) Fundamental Procedures for Processing Massive SHM Data; between DL and IoT are (3) Techniques for DL Model Light-weighting, (4) Hardware Acceleration for DL Deployment; between DL and SHM exist, (5) Ensuring Model Robustness and Data Augmentation in Real-World Scenarios, and (6) Optimizing DL Models for Specific Defect Characteristics. By synthesizing current research addressing these forces, this review establishes VS-SHM as a distinct interdisciplinary field and a pivotal enabler for intelligent infrastructure management in practical applications.
FuRHCaoMSNovákD, et al. Extended efficient convolutional neural network for concrete crack detection with illustrated merits. Autom Constr2023; 156: 23.
2.
MaheepalaMJoordensMAKouzaniAZ.Low power processors and image sensors for vision-based IoT devices: a review. IEEE Sensors J2020; 21: 1172–1186.
3.
ChaY-JAliRLewisJ, et al. Deep learning-based structural health monitoring. Autom Constr2024; 161: 105328.
4.
BaeHJangKAnY-K.Deep super resolution crack network (SrcNet) for improving computer vision–based automated crack detectability in in situ bridges. Struct Health Monit2021; 20: 1428–1442.
5.
TanYYiWChenP, et al. An adaptive crack inspection method for building surface based on BIM, UAV and edge computing. Autom Constr2024; 157: 105161.
6.
QiuQLauD.Real-time detection of cracks in tiled sidewalks using YOLO-based method applied to unmanned aerial vehicle (UAV) images. Autom Constr2023; 147: 104745.
7.
TsaiYCJLiF. Critical assessment of detecting asphalt pavement cracks under different lighting and low intensity contrast conditions using emerging 3D laser technology. J Trans Eng2012; 138: 649–656.
8.
ChenJLiuYHouJ-A.A lightweight deep learning network based on knowledge distillation for applications of efficient crack segmentation on embedded devices. Struct Health Monit2023; 22: 3027–3046.
9.
FuRZhangYZhuK, et al. Real-time detection of concrete cracks via enhanced You Only Look Once Network: algorithm and software. Adv Eng Softw2024; 195: 103691.
10.
MishraAGangisettiGKhazanchiD.An investigation into the advancements of edge-AI capabilities for structural health monitoring. IEEE Access2024; 12: 25325–25345.
11.
HuyanJLiWTigheS, et al. Detection of sealed and unsealed cracks with complex backgrounds using I (A) deep convolutional neural network. Autom Constr2019; 107: 102946.
12.
ZhangCBChangCCJamshidiM.Concrete bridge surface damage detection using a single-stage detector. Comput Aided Civ Infrastruct Eng2020; 35: 389–409.
13.
MeiQGülMAzimMR.Densely connected deep neural network considering connectivity of pixels for automatic crack detection. Autom Constr2020; 110: 103018.
14.
FlahMSuleimanARNehdiML.Classification and quantification of cracks in concrete structures using deep learning image-based techniques. Cem Concr Compos2020; 114: 103781.
15.
ZhangSLiYDongQ.Autonomous navigation of UAV in multi-obstacle environments based on a deep reinforcement learning approach. Appl Soft Comput2022; 115: 108194.
16.
ZhangRHaoGZhangK, et al. Unmanned aerial vehicle navigation in underground structure inspection: a review. Geol J2023; 58: 2454–2472.
17.
TedeschiABenedettoF.A real-time automatic pavement crack and pothole recognition system for mobile android-based devices. Adv Eng Inform2017; 32: 11–25.
18.
HuWWangWAiC, et al. Machine vision-based surface crack analysis for transportation infrastructure. Autom Constr2021; 132: 103973.
19.
DongC-ZCatbasFN.A review of computer vision–based structural health monitoring at local and global levels. Struct Health Monit2021; 20: 692–743.
20.
ZhouSLCanchilaCSongW.Deep learning-based crack segmentation for civil infrastructure: data types, architectures, and benchmarked performance. Autom Constr2022; 146: 104678.
21.
HsiehY-ATsaiYJ.Machine learning for crack detection: review and model performance comparison. J Comput Civil Eng2020; 34: 04020038.
22.
PanellaFLipaniABoehmJ.Semantic segmentation of cracks: data challenges and architecture. Autom Constr2022; 135: 104110.
23.
ZhaiGNarazakiYWangS, et al. Synthetic data augmentation for pixel-wise steel fatigue crack identification using fully convolutional networks. Smart Struct Syst2022; 29: 237–250.
24.
LiYBaoTLiT, et al. A robust real-time method for identifying hydraulic tunnel structural defects using deep learning and computer vision. Comput Aided Civ Infrastruct Eng2023; 38: 1381–1399.
25.
HeZJiangSZhangJ, et al. Automatic damage detection using anchor-free method and unmanned surface vessel. Autom Constr2022; 133: 104017.
26.
ZakariaMKaraaslanECatbasFN.Advanced bridge visual inspection using real-time machine learning in edge devices. Adv Bridge Eng2022; 3: 27.
27.
PozziRRossiTSecchiR. Industry 4.0 technologies: critical success factors for implementation and improvements in manufacturing companies. Product Plan Control2023; 34: 139–158.
RusciMRossiDLeccaM, et al. An event-driven ultra-low-power smart visual sensor. IEEE Sensors J2016; 16: 5344–5353.
32.
ZhangZXShiQFHeTYY, et al. Artificial intelligence of toilet (AI-Toilet) for an integrated health monitoring system (IHMS) using smart triboelectric pressure sensors and image sensor. Nano Energy2021; 90: 106517.
33.
FerzliRKaramLJ.A no-reference objective image sharpness metric based on the notion of just noticeable blur (JNB). IEEE Trans Image Process2009; 18: 717–728.
34.
MavridakiEMezarisV. No-reference blur assessment in natural images using fourier transform and spatial pyramids. In: 2014 IEEE international conference on image processing (ICIP), Paris, France, 27–30 October 2014. New York, NY: IEEE, pp. 566–570.
35.
HassenRWangZSalamaMM.Image sharpness assessment based on local phase coherence. IEEE Trans Image Process2013; 22: 2798–2810.
36.
SieberthTWackrowRChandlerJH.Automatic detection of blurred images in UAV image sets. ISPRS J Photogramm Remote Sens2016; 122: 1–16.
37.
FangYMaKWangZ, et al. No-reference quality assessment of contrast-distorted images based on natural scene statistics. IEEE Signal Proc Lett2014; 22: 838–842.
38.
PanZYuanFLeiJ, et al. VCRNet: visual compensation restoration network for no-reference image quality assessment. IEEE Trans Image Process2022; 31: 1613–1627.
WangFZouYChenX, et al. Rapid in-flight image quality check for UAV-enabled bridge inspection. ISPRS J Photogramm Remote Sens2024; 212: 230–250.
41.
LiuWAnguelovDErhanD, et al. SSD: single shot multibox detector. In: European conference on computer vision, Amsterdam, The Netherlands, 11–14 October 2016. Cham: Springer, pp. 21–37.
42.
GeZLiuSWangF, et al. Yolox: exceeding yolo series in 2021. arXiv. arXiv:210708430, 2021. DOI: 10.48550/arXiv.2107.08430.
43.
RenSHeKGirshickR, et al. Faster R-CNN: towards real-time object detection with region proposal networks. Adv Neural Inform Proc Syst2015; 1: 91–99.
44.
ChaYJChoiWSuhG, et al. Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types. Comput Aided Civ Infrastruct Eng2018; 33: 731–747.
45.
MandalVUongLAdu-GyamfiY. Automated road crack detection using deep convolutional neural networks. In: 2018 IEEE international conference on big data (Big Data), Seattle, WA, USA, 10–13 December 2018. New York, NY: IEEE, pp. 5212–5215.
46.
LongJShelhamerEDarrellT. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Boston, MA, USA, 23–28 June 2014, pp. 3431–3440.
47.
RonnebergerOFischerPBroxT. U-Net: convolutional networks for biomedical image segmentation. In: 18th international conference on medical image computing and computer-assisted intervention (MICCAI), Munich, Germany, 5–9 October 2015. Cham: Springer International Publishing, pp. 234–241.
48.
BadrinarayananVKendallACipollaR.SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell2017; 39: 2481–2495.
49.
ChenLCPapandreouGKokkinosI, et al. DeepLab: semantic image segmentation with deep convolutional nets, Atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal2018; 40: 834–848.
50.
HeKGkioxariGDollárP, et al. Mask R-CNN. In: Proceedings of the IEEE international conference on computer vision, Venice, Italy, 22–29 October 2017, pp. 2961–2969.
51.
CaoXSuYGengX, et al. YOLO-SF: YOLO for fire segmentation detection. IEEE Access2023; 11: 111079–111092.
52.
DungCVAnhLD.Autonomous concrete crack detection using deep fully convolutional neural network. Autom Constr2019; 99: 52–58.
53.
ZhangXXRajanDStoryB.Concrete crack detection using context-aware deep semantic segmentation network. Comput Aided Civ Infrastruct Eng2019; 34: 951–971.
54.
NiFTZhangJChenZQ.Zernike-moment measurement of thin-crack width in images enabled by dual-scale deep learning. Comput Aided Civ Infrastruct Eng2019; 34: 367–384.
55.
KimBChoS.Image-based concrete crack assessment using mask and region-based convolutional neural network. Struct Control Health Monit2019; 26: 15.
56.
LaxmanKCTabassumNAiL, et al. Automated crack detection and crack depth prediction for reinforced concrete structures using deep learning. Constr Build Mater2023; 370: 130709.
KimHSimSHSpencerBF.Automated concrete crack evaluation using stereo vision with two different focal lengths. Autom Constr2022; 135: 104136.
59.
LiuYQYeohJKW. Automated crack pattern recognition from images for condition assessment of concrete structures. Autom Constr2021; 128: 103765.
60.
NaserMZ.An engineer’s guide to eXplainable Artificial Intelligence and Interpretable Machine Learning: navigating causality, forced goodness, and the false perception of inference. Autom Constr2021; 129: 103821.
61.
SelvarajuRRCogswellMDasA, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. In: 2017 IEEE international conference on computer vision (ICCV), Venice, Italy, 22–29 October 2017, pp. 618–626.
62.
MuhammadMBYeasinM. Eigen-cam: class activation map using principal components. In: 2020 international joint conference on neural networks (IJCNN), Glasgow, UK, 19–24 July 2020. New York, NY: IEEE, pp. 1–7.
63.
CardellicchioARuggieriSNettisA, et al. Physical interpretation of machine learning-based recognition of defects for the risk management of existing bridge heritage. Eng Fail Anal2023; 149: 107237.
64.
RuggieriSCardellicchioANettisA, et al. Using attention for improving defect detection in existing RC bridges. IEEE Access2025; 13: 18994–19015.
65.
SimonyanKZissermanA. Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR), Banff, AB, Canada, 14–16 April 2014, pp. 1–14.
66.
SzegedyCIoffeSVanhouckeV, et al. Inception-v4, inception-ResNet and the impact of residual connections on learning. In: 31st AAAI conference on artificial intelligence, San Francisco, CA, USA, 4–9 February 2017, pp. 4278–4284.
67.
HowardASandlerMChuG, et al. Searching for mobilenetv3. In: Proceedings of the IEEE/CVF international conference on computer vision, Seoul, South Korea, 27 October–2 November 2019, pp. 1314–1324.
68.
HuangGLiuZVan Der MaatenL, et al. Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, HI, USA, 21–26 July 2017, pp. 4700–4708.
69.
LuFZhangZGuoL, et al. HFENet: a lightweight hand-crafted feature enhanced CNN for ceramic tile surface defect detection. Int J Intell Syst2022; 37: 10670–10693.
70.
HanSLiuXYMaoHZ, et al. EIE: efficient inference engine on compressed deep neural network. In: 43rd ACM/IEEE annual international symposium on computer architecture (ISCA), Seoul, South Korea, 18–22 June 2016. New York, NY: IEEE, pp. 243–254.
71.
LuoJHWuJXLinWY, et al. ThiNet: a filter level pruning method for deep neural network compression. In: 16th IEEE international conference on computer vision (ICCV), Venice, Italy, 22–29 October 2017. New York, NY: IEEE, pp. 5068–5076.
72.
HeYHZhangXYSunJ, et al. Channel pruning for accelerating very deep neural networks. In: 16th IEEE international conference on computer vision (ICCV), Venice, Italy, 22–29 October 2017. New York, NY: IEEE, pp. 1398–1406.
73.
LebedevVLempitskyV. Fast ConvNets using group-wise brain damage. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), Seattle, WA, USA, 27–30 June 2016. New York, NY: IEEE, pp. 2554–2564.
74.
MengFChengHLiK, et al. Pruning filter in filter. In: NeurIPS2020, Canada, 6–12 December 2020.
75.
XueYJiaFCaiX, et al. An optimization strategy to improve the deep learning-based recognition model of leakage in shield tunnels. Comput Aided Civ Infrastruct Eng2022; 37: 386–402.
76.
WuRTSinglaAJahanshahiMR, et al. Pruning deep convolutional neural networks for efficient edge computing in condition assessment of infrastructures. Comput Aided Civ Infrastruct Eng2019; 34: 774–789.
77.
HintonGVinyalsODeanJ. Distilling the knowledge in a neural network. In: NIPS2014, Montréal, Canada, 8–11 December 2014.
78.
RomeroABallasNKahouSE, et al. FitNets: hints for thin deep nets. arXiv. arXiv:1412.6550, 2015.
79.
ParkWKimDLuY, et al. Relational knowledge distillation. In: 32nd IEEE/CVF conference on computer vision and pattern recognition (CVPR), Long Beach, CA, USA, 16–20 June 2019. Los Alamitos: IEEE, pp. 3962–3971.
80.
WangWSuCHanG, et al. A lightweight crack segmentation network based on knowledge distillation. J Build Eng2023; 76: 107200.
81.
YoungSIZheWTaubmanD, et al. Transform quantization for CNN compression. IEEE Trans Pattern Anal2021; 44: 5700–5714.
82.
LiuXRaoZZhangY, et al. UAVs images based real-time insulator defect detection with transformer deep learning. In: 2023 IEEE international conference on robotics and biomimetics (ROBIO), Koh Samui, Thailand, 4–9 December 2023. New York, NY: IEEE, pp. 1–6.
83.
WuZShenCVan Den HengelA.Wider or deeper: revisiting the ResNet model for visual recognition. Pattern Recognit2019; 90: 119–133.
84.
KhanamRHussainMHillR, et al. A comprehensive review of convolutional neural networks for defect detection in industrial applications. IEEE Access2024; 12: 94250–94295.
85.
HaaseRRoyerLASteinbachP, et al. CLIJ: GPU-accelerated image processing for everyone. Nat Methods2020; 17: 5–6.
86.
ZhaoBChenYJiaX, et al. Steel surface defect detection algorithm in complex background scenarios. Measurement2024; 237: 115189.
87.
AbtahiTSheaCKulkarniA, et al. Accelerating convolutional neural network with FFT on embedded hardware. IEEE Trans VLSI Syst2018; 26: 1737–1749.
88.
BottlesonJKimSAndrewsJ, et al. clcaffe: Opencl accelerated caffe for convolutional neural networks. In: 2016 IEEE international parallel and distributed processing symposium workshops (IPDPSW), Chicago, IL, USA, 23–27 May 2016. New York, NY: IEEE, pp. 50–57.
89.
KalaSJoseBRMathewJ, et al. High-performance CNN accelerator on FPGA using unified winograd-GEMM architecture. IEEE Trans VLSI Syst2019; 27: 2816–2828.
90.
RahmanAOhSLeeJ. Design space exploration of FPGA accelerators for convolutional neural networks. In: Design, automation & test in Europe conference & exhibition (DATE), 2017, Lausanne, Switzerland, 27–31 March 2017. New York, NY: IEEE, pp. 1147–1152.
91.
LiYLiuZXuK, et al. A GPU-outperforming FPGA accelerator architecture for binary convolutional neural networks. ACM J Emerg Technol Comput Syst2018; 14: 1–16.
92.
DerrienSRajopadhyeS. Loop tiling for reconfigurable accelerators. In: International conference on field programmable logic and applications, Leuven, Belgium, 30 August–1 September 2001. Cham: Springer, pp. 398–408.
JouppiNPYoungCPatilN, et al. In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th annual international symposium on computer architecture, Toronto, ON, Canada, 24–28 June 2017, pp. 1–12.
95.
ChisholmTLinsRGivigiS.FPGA-based design for real-time crack detection based on particle filter. IEEE Trans Ind Inform2019; 16: 5703–5711.
96.
SituZTengSLiaoX, et al. Real-time sewer defect detection based on YOLO network, transfer learning, and channel pruning algorithm. J Civ Struct Health2024; 14: 41–57.
97.
LiuSQiLQinHF, et al. Path aggregation network for instance segmentation. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR), Salt Lake City, UT, USA, 18–23 June 2018, pp. 8759–8768.
98.
HupkesDGiulianelliMDankersV, et al. A taxonomy and review of generalization research in NLP. Nat Mach Intell2023; 5: 1161–1174.
99.
XuJYuanCGuJ, et al. Innovative synthetic data augmentation for dam crack detection, segmentation, and quantification. Struct Health Monit2023; 22: 2402–2426.
100.
LuoWLiYUrtasunR, et al. Understanding the effective receptive field in deep convolutional neural networks. In: Proceedings of the 30th international conference on neural information processing systems, Barcelona, Spain, 5–10 December 2016.
101.
AgyemangIOZhangXAdjei-MensahI, et al. Automated vision-based structural health inspection and assessment for post-construction civil infrastructure. Autom Constr2023; 156: 105153.
102.
XieXCaiJWangH, et al. Sparse-sensing and superpixel-based segmentation model for concrete cracks. Comput Aided Civ Infrastruct Eng2022; 37: 1769–1784.
103.
WangKC.Elements of automated survey of pavements and a 3D methodology. J Modern Trans2011; 19: 51–57.
104.
ZhangAWangKCPLiBX, et al. Automated pixel-level pavement crack detection on 3D Asphalt surfaces using a deep-learning network. Comput Aided Civ Infrastruct Eng2017; 32: 805–819.
105.
ZhangAWangKCPFeiY, et al. Deep learning-based fully automated pavement crack detection on 3D Asphalt surfaces with an improved CrackNet. J Comput Civil Eng2018; 32: 14.
106.
FeiYWangKCZhangA, et al. Pixel-level cracking detection on 3D asphalt pavement images through deep-learning-based CrackNet-V. IEEE Trans Intell Trans Syst2020; 21: 273–284.
107.
ZhangAWangKCPFeiY, et al. Automated pixel-level pavement crack detection on 3D Asphalt surfaces with a recurrent neural network. Comput Aided Civ Infrastruct Eng2019; 34: 213–229.
108.
ZhouSLSongW.Concrete roadway crack segmentation using encoder-decoder networks with range images. Autom Constr2020; 120: 103403.
109.
JiangWBLiuMPengYN, et al. HDCB-Net: a neural network with the hybrid dilated convolution for pixel-level crack detection on concrete bridges. IEEE Trans Ind Inform2021; 17: 5485–5494.
110.
NiFHeZJiangS, et al. A generative adversarial learning strategy for enhanced lightweight crack delineation networks. Adv Eng Inform2022; 52: 101575.
ChatfieldKSimonyanKVedaldiA, et al. Return of the devil in the details: delving deep into convolutional nets. arXiv preprint. arXiv:14053531, 2014. DOI: 10.48550/arXiv.1405.3531.
NiYMaoJWangH, et al. Toward high-precision crack detection in concrete bridges using deep learning. J Perform Constr Fac2023; 37: 04023017.
115.
MaDFangHWangN, et al. Automatic detection and counting system for pavement cracks based on PCGAN and YOLO-MF. IEEE Trans Intell Transp Syst2022; 23: 22166–22178.
116.
ShortenCKhoshgoftaarTM.A survey on image data augmentation for deep learning. J Big Data2019; 6: 1–48.
117.
PerezLWangJ.The effectiveness of data augmentation in image classification using deep learning. arXiv preprint. arXiv:171204621, 2017. DOI: 10.48550/arXiv.1712.04621.
118.
FuRZhangYNovákD, et al. A lightweight convolutional neural network-based model and system for defect detection and navigation on bridge road surface. Adv Eng Softw2025; 208: 103972.
119.
ChowJKSuZWuJ, et al. Anomaly detection of defects on concrete structures with the convolutional autoencoder. Adv Eng Inform2020; 45: 101105.
120.
ŻarskiMWójcikBKsiążekK, et al. Finicky transfer learning—a method of pruning convolutional neural networks for cracks classification on edge devices. Comput Aided Civ Infrastruct Eng2022; 37: 500–515.
121.
HanKWangYChenH, et al. A survey on vision transformer. IEEE Trans Pattern Anal2022; 45: 87–110.
122.
NiuZZhongGYuH.A review on the attention mechanism of deep learning. Neurocomputing2021; 452: 48–62.
123.
ShamsabadiEAXuCRaoAS, et al. Vision transformer-based autonomous crack detection on asphalt and concrete surfaces. Autom Constr2022; 140: 104316.
124.
XiangCWangWDengL, et al. Crack detection algorithm for concrete structures based on super-resolution reconstruction and segmentation network. Autom Constr2022; 140: 104346.
125.
ZhangYZhangHHuangQ, et al. DsP-YOLO: an anchor-free network with DsPAN for small object detection of multiscale defects. Expert Syst Appl2024; 241: 122669.
126.
LinT-YDollárPGirshickR, et al. Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, HI, USA, 21–26 July 2017, pp. 2117–2125.
127.
ZhuWZhangHEastwoodJ, et al. Concrete crack detection using lightweight attention feature fusion single shot multibox detector. Knowl Based Syst2023; 261: 110216.
128.
KrizhevskyASutskeverIHintonGE.ImageNet classification with deep convolutional neural networks. Commun Acm2017; 60: 84–90.
129.
YuFKoltunV. Multi-scale context aggregation by dilated convolutions. In: 4th international conference on learning representations, San Juan, Puerto Rico, 2–4 May 2015.
130.
ChenHHeXQingL, et al. Real-world single image super-resolution: a brief review. Inform Fusion2022; 79: 124–145.
131.
ChuHWangWDengL.Tiny-Crack-Net: a multiscale feature fusion network with attention mechanisms for segmentation of tiny cracks. Comput Aided Civ Infrastruct Eng2022; 37: 1914–1931.
132.
AnYKongLHouC, et al. An adaptable rotated bounding box method for automatic detection of arbitrary-oriented cracks. Struct Health Monit2020; 23(6): 3312-3335.
133.
DaiJQiHXiongY, et al. Deformable convolutional networks. In: Proceedings of the IEEE international conference on computer vision, Venice, Italy, 22–29 October 2017, pp. 764–773.
134.
QiYHeYQiX, et al. Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation. In: Proceedings of the IEEE/CVF international conference on computer vision, Paris, France, 1–6 October 2023, pp. 6070–6079.
135.
LuXLiQ.Deep learning-based method for detection and feature quantification of microscopic cracks on the surface of concrete dams. Measurement2024; 240: 115587.
136.
YuLHeSLiuX, et al. Engineering-oriented bridge multiple-damage detection with damage integrity using modified faster region-based convolutional neural network. Multimed Tools Appl2022; 81: 18279–18304.
137.
LiBLQiYFanJS, et al. A grid-based classification and box-based detection fusion model for asphalt pavement crack. Comput Aided Civ Infrastruct Eng2023; 38: 2279–2299.
138.
ZhangXWanFLiuC, et al. Freeanchor: learning to match anchors for visual object detection. In: Advances in neural information processing systems, Vancouver, BC, Canada, 2019.
139.
WangLTangC.Effective small crack detection based on tunnel crack characteristics and an anchor-free convolutional neural network. Scient Rep2024; 14: 10355.
140.
ZhengZWangPLiuW, et al. Distance-IoU loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI conference on artificial intelligence, New York, NY, USA, 7–12 February 2020, pp. 12993–13000.
141.
ZhengZWangPRenD, et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans Cybernet2021; 52: 8574–8586.
142.
MaSXuMFengW.Dam crack instance segmentation algorithm based on improved YOLOv8. IEEE Access2025; 13: 84271–84283.
143.
WhiteCSafariMSukthankerRS, et al. Neural architecture search: insights from 1000 papers. ArXiv arXiv:2301.08727, 2023. DOI: 10.48550/arXiv.2301.08727.
144.
MundtMMajumderSMuraliS, et al. Meta-learning convolutional neural architectures for multi-target concrete defect classification with the concrete defect bridge image dataset. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Long Beach, CA, USA, 15–20 June 2019, pp. 11196–11205.
