检索结果-内蒙古大学图书馆

Adaptive Learning Filters-Embedded Vision Transformer for pixel-level segmentation of Low-Light Concrete Cracks

JOURNAL OF PERFORMANCE OF CONSTRUCTED FACILITIES 2025年第3期39卷

作者： Shen, Qi Xiao, Binggang Mi, Hongmei Yu, Jiabin Xiao, Lihua China Jiliang Univ Coll Informat Engn Hangzhou 310018 Peoples R China China Jiliang Univ Coll Informat Engn Key Lab Electromagnet Wave Informat Technol & Metr Hangzhou 310018 Peoples R China Zhejiang Univ Technol Coll Chem Engn Hangzhou 310014 Peoples R China

Crack detection is crucial for assessing structural safety. However, its performance faces challenges when dealing with thin or irregular cracks, especially in complex backgrounds under poor lighting conditions. This paper presents the adaptive learning filters vision transformer (ALF-ViT), a method for pixel-level segmentation of concrete cracks under low-light conditions. This method incorporates two adaptive learning image filter modules based on the vision transformer: a convolutional neural network-based digital image processing (DIP) parameter predictor (C-DIP) and a dilated convolutional guided image filter (DCGIF), aimed at adaptively enhancing images and guiding enhanced segmentation masks to improve the effectiveness of segmentation detection. In experiments conducted on two public data sets and one self-made mixed-lighting data set, ALF-ViT demonstrated superior adaptability and performance under both normal and low-light conditions, achieving a mean intersection over union (mIoU) of 74.5%, a precision of 85.7%, and an F1 score of 80.3% on the publicly available Crack500 data set. On the self-made mixed-lighting data set, ALF-ViT achieves an mIoU of 73.3%. Compared to traditional methods such as U-Net and SegNet, which reach mIoUs of 62.9% and 41.3%, respectively, on similar tasks, ALF-ViT showed significant improvements. It also surpasses other advanced models like DeepLabv3+ and SegNet in both detection accuracy and robustness under variable lighting conditions. These results indicate that the proposed ALF-ViT outperforms recent segmentation networks on both low-light and well-lit crack databases, demonstrating its excellent generalization capability and immense potential for crack detection tasks under low-light conditions.

关键词： Crack detection pixel-level segmentation Digital image processing (DIP)

来源：评论

学校读者我要写书评

暂无评论

A pixel-level segmentation Convolutional Neural Network Based on Deep Feature Fusion for Surface Defect Detection

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2021年 70卷 1-12页

作者： Cao, Jingang Yang, Guotian Yang, Xiyun North China Elect Power Univ Sch Control & Comp Engn Baoding 071003 Peoples R China North China Elect Power Univ Minist Educ China Engn Res Ctr Intelligent Comp Complex Energy Syst Baoding 071003 Peoples R China North China Elect Power Univ Sch Control & Comp Engn Beijing 012206 Peoples R China

Surface defect detection is very important for the quality control of product and routine maintenance of facilities, but it is still a big challenge due to the diversity and complexity of defects and environmental factors. To improve the accuracy of defect detection, we proposed a pixel-level segmentation network based on deep feature fusion for surface defect detection. The network adopts encoder-decoder structure, and it extracts low-, middle-, and high-level features via ResNet50 first. Second, by fusing adjacent feature maps at all levels and integrating the highest level feature map, multilevel feature aggregation module makes all feature maps contain context information and more details of defects. Then, multibranch decoder adopts attention modules and a multibranch structure to recover the details of defects gradually and improve the accuracy of defects segmentation. Finally, the segmentation result is produced by fusion of all branches outputs. We have evaluated the proposed network on three public data sets: MT, RSDD, and CFD. The results indicate that our proposed method outperforms the other compared methods in terms of F-measure and intersection of union (MT:73.7%, RSDD:85%, CFD:60.1%).

关键词： Convolutional neural network feature fusion multibranch decoder (MBD) pixel-level segmentation surface defect detection

来源：评论

学校读者我要写书评

暂无评论

pixel-level segmentation method of concrete cracks based on MU-Net

Pixel-level segmentation method of concrete cracks based on ...

引用

2021年第四届算法、计算和人工智能国际会议

作者： Zhili Chen Shiyuan Zhang Adamu Abubakar Abba Bing Wang Yupeng Li School of Information and Control Engineering Shenyang Jianzhu University

In order to improve the segmentation accuracy of complex crack and lightweight network, this paper proposes a concrete crack segmentation network named MU-Net(Modified U-Net). In the encoder part, depthwise separable convolution is used to reduce network parameters, and inverted residual structure and attention mechanism are combined to fully extract features while highlighting target features. The decoder part also introduces the depthwise separable convolution and attention mechanism, and improves the segmentation accuracy by integrating the deep and light layers of information. In order to strictly evaluate the effectiveness of the network, this paper constructs a dataset of concrete cracks, which contains complex backgrounds and a variety of cracks, which is more in line with the engineering practice. Experimental results of 5-fold cross validation show that the proposed semantic segmentation network has superior performance compared with other advanced semantic segmentation networks.

关键词： Concrete crack pixel-level segmentation Lightweight Deep learning

来源：评论

学校读者我要写书评

暂无评论

pixel-level segmentation method of concrete cracks based on MU-Net 21

Pixel-level segmentation method of concrete cracks based on ...

引用

Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence

作者： Zhili Chen Shiyuan Zhang Adamu Abubakar Abba Bing Wang Yupeng Li School of Information and Control Engineering Shenyang Jianzhu University China

ISBN: (纸本)9781450385053

In order to improve the segmentation accuracy of complex crack and lightweight network, this paper proposes a concrete crack segmentation network named MU-Net (Modified U-Net). In the encoder part, depthwise separable convolution is used to reduce network parameters, and inverted residual structure and attention mechanism are combined to fully extract features while highlighting target features. The decoder part also introduces the depthwise separable convolution and attention mechanism, and improves the segmentation accuracy by integrating the deep and light layers of information. In order to strictly evaluate the effectiveness of the network, this paper constructs a dataset of concrete cracks, which contains complex backgrounds and a variety of cracks, which is more in line with the engineering practice. Experimental results of 5-fold cross validation show that the proposed semantic segmentation network has superior performance compared with other advanced semantic segmentation networks.

关键词： Deep learning Concrete crack pixel-level segmentation Lightweight

来源：评论

学校读者我要写书评

暂无评论

A pixel-level segmentation Convolutional Neural Network Based on Global and Local Feature Fusion for Surface Defect Detection

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2023年 72卷 1页

作者： Zuo, Lei Xiao, Hongyong Wen, Long Gao, Liang China Univ Geosci Sch Mech Engn & Elect Informat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Peoples R China

Surface defect detection (SDD) is a fundamental task in the smart industry to ensure product quality. Due to the complexity and diversity of the industrial scenes and the low contrast and tiny sizes of the defect, it is still difficult to accurately segment the defect. To overcome these issues, this research studied the pixel-level segmentation convolutional neural network based on multi-scale features, global mapping, feature pyramid and attention mechanisms (MMPA-Net). First, the low- and high-level features are extracted as the multiscale network to enrich the defect features information. Second, the global and local feature fusion (GLF) with the global mapping branch (GMB) module is developed to gradually refine the defect details to promote the detection of defects with different sizes and shapes. Third, deep supervision is applied to the global feature map and multiscale prediction maps to train MMPA-Net. MMPA-Net has been conducted on three public SDD datasets, and the results show that MMPA-Net has achieved state-of-the-art results on the intersection over union (IoU) by comparing with other deep learning (DL) methods (NEU-Seg: 86.62%, DAGM 2007: 87.94%, MT: 84.23%).

关键词： Convolutional neural networks Surface cracks Convolutional neural network feature fusion global mapping branch (GMB) pixel-level segmentation surface defect detection (SDD)

来源：评论

学校读者我要写书评

暂无评论

pixel level segmentation Based Drivable Road Region Detection and Steering Angle Estimation Method for Autonomous Driving on Unstructured Roads

引用

IEEE ACCESS 2021年 9卷 167855-167867页

作者： Rasib, Marya Butt, Muhammad Atif Riaz, Faisal Sulaiman, Adel Akram, Muhammad Natl Ctr Robot & Automat NCRA HEC Affiliated Lab Control Automot & Robot Lab Mirpur 10250 Pakistan Mirpur Univ Sci & Technol MUST Dept Comp Sci & Informat Technol Mirpur Azad Kashmir Pakistan Najran Univ Coll Comp Sci & Informat Syst Najran 61441 Saudi Arabia

With the recent emergence of deep learning, computer vision-based applications have demonstrated better applicability in accomplishing driving tasks including drivable road region detection, lane keeping and steering control in self-driving cars. Till recently, numerous lane-marking detection based steering control and lane keeping methods have been proposed to perform autonomous driving on urban well-structured roads. But the matter of fact is that these methods are not feasible on roads where lane markings are not available or faded over time which makes drivable road region detection a crucial task. Moreover, it is highly arduous task to estimate steering angle on deteriorated roads using existing road detection and steering angle estimation methods. To the best of our knowledge, there is no standard benchmark available for drivable road region detection and steering angle estimation on unstructured roads. To this end, we present a large-scale dataset for drivable region road detection, comprising of 15,000-pixel level high quality fine annotations. Alongside dataset, we also present an end-to-end drivable road region detection and steering angle estimation method to ensure the autonomous driving on generalized urban, rural, and unstructured road conditions. The proposed method performs pixel-level segmentation to extract drivable road region and quantifies lane interception to estimate the steering angle of self-driving cars. A comprehensive qualitative and quantitative analysis has been carried out to demonstrate the effectiveness of our proposed dataset, road detection and steering angle estimation methods. Our benchmark is available at https://***/index/.

关键词： Roads Estimation Autonomous automobiles Control systems Semantics Automobiles Task analysis Unstructured road detection dataset pixel-level segmentation steering angle estimation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Crack segmentation Network with Multiple Selective Fusion Mechanisms

引用

BUILDINGS 2025年第7期15卷 1088-1088页

作者： Chen, Yang Yang, Tao Dong, Shuai Wang, Like Pei, Bida Wang, Yunlong China Construct Fifth Engn Div Changsha 410004 Peoples R China Changsha Univ Sci & Technol Sch Civil & Environm Engn Changsha 410114 Peoples R China

Automated crack detection is vital for structural maintenance in areas such as construction, roads, and bridges. Accurate crack detection allows for the timely identification and repair of cracks, reducing safety risks and extending the service life of structures. However, traditional methods struggle with fine cracks, complex backgrounds, and image noise. In recent years, although deep learning techniques excel in pixel-level crack segmentation, challenges like inadequate local feature processing, information loss, and class imbalance persist. To address these challenges, we propose an encoder-decoder network based on multiple selective fusion mechanisms. Initially, a star feature enhancement module is designed to resolve the issues of insufficient local feature processing and feature redundancy during the feature extraction process. Then, a multi-scale adaptive fusion module is developed to selective capture both global and local contextual information, mitigating the information loss. Finally, to tackle class imbalance, a multi-scale monitoring and selective output module is introduced to enhance the model's focus on crack features and suppress the interference from background and irrelevant information. Extensive experiments are conducted on three publicly available crack datasets: SCD, CFD, and DeepCrack. The results demonstrate that the proposed segmentation network achieves superior performance in pixel-level crack segmentation, with Dice scores of 66.2%, 54.2%, and 86.8% and mIoU values of 74.4%, 67.5%, and 87.9% on the SCD, CFD, and DeepCrack datasets, respectively. These results outperform those of existing models, such as U-Net, DeepLabv3+, and Attention UNet, particularly in handling complex backgrounds, fine cracks, and low-contrast images. Furthermore, the proposed MSF-CrackNet also significantly reduces computational complexity, with only 2.39 million parameters and 8.58 GFLOPs, making it a practical and efficient solution for real-world crack detecti

关键词： crack detection pixel-level segmentation encoder-decoder network multiple selective fusion mechanism

来源：评论

学校读者我要写书评

暂无评论

SBDNet: A deep learning-based method for the segmentation and quantification of fatigue cracks in steel bridges

引用

ADVANCED ENGINEERING INFORMATICS 2025年 65卷

作者： Wang, Xiao Yue, Qingrui Liu, Xiaogang Univ Sci & Technol Beijing Res Inst Urbanizat & Urban Safety Sch Future Cities Beijing Peoples R China Tianjin Univ Sch Civil Engn Tianjin 300350 Peoples R China

Employing deep learning to automate the processing of fatigue crack images in steel structure bridges is a cutting-edge research frontier in damage assessment and safe operation. However, existing methods lack pixel-level segmentation accuracy and quantitative metrics for model generalization. This paper introduces Steel Bridge Damage Networks (SBDNet), which is designed for high-precision pixel-level segmentation and quantification of fatigue cracks. We established metrics to measure domain differences between training and test sets and validated SBDNet on a fatigue crack image dataset, comparing its performance with state-of-the-art models. Results show that SBDNet achieves an average IoU of 76.8% and a crack geometric quantification error of less than 3%, exhibiting robust generalization. The proposed method enhances damage detection efficiency and provides quantitative references for maintenance decision-making.

关键词： Deep learning Steel bridges pixel-level segmentation Automated detection Fatigue cracks

来源：评论

学校读者我要写书评

暂无评论

Automated annotation of steel corrosion in UAV-captured images from beneath bridge decks using metaheuristic-optimized computer vision

引用

STRUCTURES 2025年 75卷

作者： Chou, Jui-Sheng Liu, Chi-Yun Shih, Hsin-Yu Lin, Zih-Tong Natl Taiwan Univ Sci & Technol Dept Civil & Construct Engn Taipei Taiwan Arizona State Univ Sch Sustainable Engn & Built Environm Tempe AZ USA

Steel bridges are highly susceptible to climate-induced corrosion, making inspections time-consuming and laborintensive. Traditional visual assessments are not only inefficient but also lack empirical support. This study employs deep learning models in computer vision, specifically the Mask Region-based Convolutional Neural Network (Mask R-CNN) and the You Only Look Once (YOLO) series, to automate the identification of areas deteriorated by corrosion. The severity of corrosion was evaluated according to standards set by the American Association of State Highway and Transportation Officials (AASHTO) and the Bridge Inspector's Reference Manual (BIRM). segmentation models were developed for various levels of corrosion, enabling bridge management authorities to prioritize repairs based on severity. An innovative approach was introduced by optimizing the models' hyperparameters using the Pilgrimage Walk Optimization (PWO)-Lite algorithm inspired by Taiwan's Matsu folklore. This methodology significantly accelerated the corrosion segmentation process, greatly surpassing the speed of traditional manual annotation methods and reducing labor requirements. These efficiency gains facilitate the rapid creation of training datasets for deep learning-based bridge inspection systems, ensuring more effective maintenance strategies and extending the service life of steel bridges.

关键词： Steel bridge Corrosion deterioration Unmanned aerial vehicle Computer vision-based deep learning Metaheuristic optimization pixel-level segmentation Automatic image annotation

来源：评论

学校读者我要写书评

暂无评论

WFF-Net: Trainable weight feature fusion convolutional neural networks for surface defect detection

引用

ADVANCED ENGINEERING INFORMATICS 2025年 64卷

作者： Xiao, Hongyong Zhang, Wenying Zuo, Lei Wen, Long Li, Qingzhe Li, Xinyu China Univ Geosci Sch Mech Engn & Elect Informat 388 LuMo Rd Wuhan 430074 Peoples R China China Univ Geosci Shenzhen Res Inst Shenzhen 518057 Peoples R China Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol 1037 Luoyu Rd Wuhan 430074 Peoples R China Chongqing Univ State Key Lab Mech Transmiss Chongqing 400023 Peoples R China

Deep learning-based surface defect segmentation (SDS) technique is widely used in the field of surface defect detection (SDD) for its high accuracy and robustness. However, the deep learning-based surface defect segmentation method suffers from the interference from the semantic difference between the high-dimensional features and the low-dimensional features during the process of multi-scale feature fusion, which will bring additional noise to the network and thus affect the detection accuracy. For this drawback, this paper investigates a new weight-based feature fusion method, which aims to reduce the semantic differences and information redundancy after multiscale feature fusion in the process of coupling high-dimensional semantic features with low-dimensional semantic features. First, the WFF feature fusion method is proposed in the multi-scale feature fusion stage, which uses a learnable Gate module to assign weight coefficients to neighboring features, and uses an attention mechanism to fuse weighted neighboring features, so that redundant information can be reduced both before neighboring features are coupled. It can also reduce the semantic differences between multi-highdimensional features and low-dimensional features after fusion. Second, a dual decoding module is constructed to reduce the feature loss in the decoding stage, and a structural loss function is designed to optimize the network for the multi-scale output in the dual decoder. The proposed WFF-Net has been conducted on three datasets, and it shows that the proposed WFF-Net outperforms several existing DL methods in mean intersection of union (NEU-SEG: 85.70%, DAGM 2007: 86.12%, MT defects: 82.72%) and F1-measure (NEU-SEG: 94.11 %, DAGM 2007: 96.32 %, MT defects: 93.90 %).

关键词： Feature fusion Attention mechanism pixel-level segmentation Surface defect detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：