检索结果-内蒙古大学图书馆

Erasing-inpainting-based data augmentation using denoising diffusion probabilistic models with limited samples for generalized surface defect inspection

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2024年 208卷

作者： Tao, Huanjie Northwestern Polytech Univ Sch Comp Sci Xian 710129 Peoples R China Minist Educ Engn Res Ctr Embedded Syst Integrat Xian 710129 Peoples R China Natl Engn Lab Integrated Aerosp Ground Ocean Big D Xian 710129 Peoples R China

Surface defect inspection aims to identify defective regions in product surface images to ensure product quality. Existing deep learning methods have developed rapidly on surface defect inspection. However, their excellent performances rely on a large number of training samples, which are hard to acquire in practical industrial scenarios due to the continuous improvements of the production line. To solve this issue, we propose an erasing-inpainting-based data augmentation method using a denoising diffusion probabilistic model (DDPM) with limited samples for generalized surface defect inspection. Our method is based on the idea that a defect image is difficult to recover to its previous state after undergoing a large-scale erasure operation, thus diverse defect images can be generated using different settings in the inpainting model. Specifically, we first train a DDPM model using limited defective images. Then, we erase large-scale parts of an input image to obtain a degraded image and restore the erased areas using the trained DDPM. Finally, the repaired images are further used for updating the DDPM. The main advantage of our method is to generate diverse images by only being trained using limited training samples. On the one hand, our method fundamentally avoids the dimension inconsistency between the sampled noise and the generated image by sampling from a two-dimensional noise map with the same resolution as the output image based on DDPM. On the other hand, the proposed erasing-inpainting operation promotes the recombination of the real features from the training set and the learned features from the trained DDPM to fully use the limited defective samples and the easily obtainable defect-free samples. Extensive experiments demonstrated the effectiveness and advantages of our model on data augmentation for generalized surface defect inspection.

关键词： Data augmentation defect generation defect classification defect segmentation Denoising diffusion probabilistic model

来源：评论

学校读者我要写书评

暂无评论

Spherical image acquisition and defect detection of nuclear fuel based on the line scan

引用

MEASUREMENT 2024年 229卷

作者： Gao, Wuqi Zhang, Jianxiong Liu, Kaihang Li, Liangliang Wang, Man Ma, Bei Xian Technol Univ Sch Comp Sci & Engn Xian 710021 Peoples R China Xian Technol Univ Sch Elect & Informat Engn Xian 710021 Peoples R China Xian Technol Univ Sch Mech & Elect Engn Xian 710021 Peoples R China Xian Technol Univ Off Dev & Planning Xian 710021 Peoples R China

Graphite balls are used as matrix materials of nuclear fuel. To ensure the safe use of nuclear energy, it is necessary to detect the surface defects of graphite balls to screen out the balls that do not meet safety requirements. However, due to the small surface defects and complex background of graphite balls, the detection accuracy based on traditional detection methods is difficult to meet engineering requirements. To solve the above problems, this paper designs an image acquisition device for graphite balls based on line scanning to collect spherical images and designs an improved algorithm based on the U2-Netp network to solve the problem of low accuracy of defect detection. Firstly, the algorithm replaces the up-sampling in the RSU module with cubic linear interpolation to enhance the smoothness of the image. Secondly, spatial channel attention and multi-feature fusion modules are built between the encoder and the decoder to improve the accuracy of the model to obtain interesting information. Finally, the prediction output of Sigmoid and Threshold fusion is designed to solve the problems caused by the gradient disappearance and the uneven polarity of positive and negative samples. Tested on the actual collected data set, the improved U2-Netp algorithm improved the average accuracy of detecting surface defects on graphite balls by 8.1% compared to the original U2-Netp algorithm, reaching 85.3%.

关键词： Graphite Ball defect segmentation U2-Netp CBAM attention mechanism Feature Fusion

来源：评论

学校读者我要写书评

暂无评论

Mapping and modelling defect data from UAV captured images to BIM for building external wall inspection

引用

AUTOMATION IN CONSTRUCTION 2022年 139卷

作者： Tan, Yi Li, Geng Cai, Ruying Ma, Jun Wang, Mingzhu Shenzhen Univ Minist Educ Key Lab Resilient Infrastruct Coastal Cities Shenzhen Peoples R China Univ Hong Kong Dept Urban Planning & Design Hong Kong Peoples R China Loughborough Univ Sch Architecture Bldg & Civil Engn Loughborough Leics England

With the increase of service years, external walls of high-rise buildings tend to suffer from a variety of defects which impose great safety risks. Traditional methods for inspecting high-rise building external walls require inspectors to work at height and identify defects manually, which is dangerous and inefficient. In recent years, there has been an increasing trend of using unmanned aerial vehicles (UAV) for inspecting building external walls, but how to manage the information obtained by the UAV is still a problem. In addition, although building information modelling (BIM) with rich geometric and semantic information has been applied in the construction engineering industry, BIM models usually lack updated condition data of facilities. Therefore, this paper presents a method for managing the inspection results of building external walls by mapping defect data from UAV images to BIM models and modelling defects as BIM objects. First, images of building external walls obtained by UAV are processed and useful information such as coordinates are extracted. Considering the small scale of single buildings, a simplified coordinate transformation approach is developed to transform location of real-world defects to coordinates in the BIM model. Meanwhile, a deep learning-based instance segmentation model is developed to detect defects in the captured images and extract their features. In the end, the identified defects are modelled as new objects with detailed information and mapped to the corresponding location of the related BIM component. To validate the feasibility, the proposed method has been applied to a real office building, which successfully mapped and integrated the defects of external walls with the BIM model. This study is applicable to both buildings and infrastructure, and is expected to facilitate structure inspection and decision making in maintenance with integrated data of as-is condition and as-built BIM.

关键词： Unmanned aerial vehicle (UAV) Building information modelling (BIM) Coordinate transformation Mapping Deep learning defect detection Building external wall defect segmentation

来源：评论

学校读者我要写书评

暂无评论

Lightweight pixel-level semantic segmentation and analysis for sewer defects using deep learning

引用

CONSTRUCTION AND BUILDING MATERIALS 2023年第1期371卷

作者： Dang, L. Minh Wang, Hanxiang Li, Yanfen Nguyen, Le Quan Nguyen, Tan N. Song, Hyoung-Kyu Moon, Hyeonjoon Sejong Univ Dept Informat & Commun Engn Seoul South Korea Sejong Univ Convergence Engn Intelligent Drone Seoul South Korea Sejong Univ Dept Comp Sci & Engn Seoul South Korea Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Duy Tan Univ Fac Informat Technol Da Nang 550000 Vietnam Sejong Univ Dept Architectural Engn 209 Neungdong Ro Seoul 05006 South Korea

The underground sewer network is a vital public infrastructure in charge of large-scale wastewater collection and treatment. Complex defects can occur in sewer pipes due to various internal and external factors, which increase the demand for frequent inspection. Previous defect detection research mainly depended on manual inspection, which is tedious, costly, and error-prone. This study suggests an automatic pixel-level sewer defect segmentation framework based on DeepLabV3+, which can recognize the defect's type, location, geometric information and severity. The impacts of various backbones and pre-processing methods on the model's performance were carefully evaluated. In addition, four state-of-the-art segmentation models (U-Net, SegNet, PSPNet, and FCN) were compared with the presented model to demonstrate its superiority. The experimental results revealed that the DeepLabV3+ with the Resnet-152 backbone structure efficiently identified ten defect types under challenging conditions. The obtained mean pixel accuracy and mean intersection over union (IoU) were 0.97 and 0.68, respectively. In terms of severity analysis, it was revealed that the framework outputs were consistent with the NASSCO pipeline assessment certification program (PACP). In addition, during the testing process, the proposed frame reduction algorithm only required about 16% of the original time required to process an input video. Finally, with a generated detailed report for an inspection video, the suggested framework can offer a decision-making base for more precise and efficient defect inspection and maintenance.

关键词： Deep learning Semantic segmentation Sewer network defect segmentation Severity analysis

来源：评论

学校读者我要写书评

暂无评论

Towards an automated condition assessment framework of underground sewer pipes based on closed-circuit television (CCTV) images

引用

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY 2021年 110卷 103840-103840页

作者： Wang, Mingzhu Luo, Han Cheng, Jack C. P. Hong Kong Univ Sci & Technol Dept Civil & Environm Engn Hong Kong Peoples R China

There is a growing trend of using computer vision techniques for interpreting Closed-Circuit Television (CCTV) inspection videos of sewer pipes. Previous studies mainly focus on detecting defect types and locations in CCTV images, yet limited systematic approaches are available for automatically evaluating defect severity and sewer condition with references to existing standards. This study proposes a framework for evaluating defect severity and sewer condition automatically from CCTV images using computer vision methods, which includes (1) required information definition for sewer condition assessment, (2) pipe joint detection and fitting by image processing techniques to obtain cross section area, (3) defect detection and segmentation to obtain defect type, location and area, and (4) evaluation of defect severity and sewer condition. Particularly, three deep learning -based defect detection models are developed, among which the model based on Faster R-CNN (regional convolution neural network) outperforms others with higher accuracy and is used for detecting defect type and location in the image. Meanwhile, an innovative semantic segmentation model is applied for segmenting defects to extract defect area in the image. In the validation, our framework performs well in defect detection with an average precision, recall and F1 of 88.99%, 87.96%, and 88.21% respectively. More importantly, the framework evaluates Operation and Maintenance (O&M) defects more accurately by precise calculation and generates the overall condition gradings that are mostly consistent with professional inspectors, only with an average deviation of 3.06%. Our framework can assist the review of inspection videos and lays the basis for fully automated sewer assessment and maintenance planning in the future. Without constraints on the assessment codes and computer vision methods, the framework is adaptable to evaluating sewer condition in different regions and can achieve better performance by int

关键词： Condition assessment Computer vision defect detection defect segmentation Severity assessment Sewer pipe

来源：评论

学校读者我要写书评

暂无评论

NAS-ASDet: An adaptive design method for surface defect detection network using neural architecture search

引用

ADVANCED ENGINEERING INFORMATICS 2024年 61卷

作者： Wang, Zhenrong Li, Bin Li, Weifeng Niu, Shuanlong Wang, Miao Niu, Tongzhi Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Peoples R China

Deep convolutional neural networks (CNNs) have been widely used in surface defect detection. However, no CNN architecture is suitable for all detection tasks and designing effective task -specific architectures requires considerable effort. The neural architecture search (NAS) technology makes it possible to automatically generate adaptive data -driven networks. Here, we propose a new method called NAS-ASDet to adaptively design network for surface defect detection. First, a refined and industry -appropriate search space that can adaptively adjust the feature distribution is designed, which consists of repeatedly stacked basic novel cells with searchable attention operations. Then, a progressive search strategy with a deep supervision mechanism is used to explore the search space faster and better. This method can design high-performance and lightweight defect detection networks with data scarcity in industrial scenarios. The experimental results on four datasets demonstrate that the proposed method achieves superior performance and a relatively lighter model size compared to other competitive methods, including both manual and NAS-based approaches.

关键词： Deep learning Neural architecture search (NAS) Surface defect detection defect segmentation

来源：评论

学校读者我要写书评

暂无评论

Quantitative characterization of surface defects on bridge cable based on improved YOLACT plus

引用

CASE STUDIES IN CONSTRUCTION MATERIALS 2024年 21卷

作者： Zhang, Hong He, Jiangxia Jiang, Xiaogang Gong, Yanfeng Hu, Tianyu Jiang, Tengjiao Zhou, Jianting Chongqing Jiaotong Univ State Key Lab Mt Bridge & Tunnel Engn Chongqing 400074 Peoples R China Chongqing Jiaotong Univ Sch Informat Sci & Engn Chongqing 400074 Peoples R China Chongqing Jiaotong Univ Sch Shipping & Naval Architecture Chongqing 400074 Peoples R China Norwegian Univ Sci & Technol Dept Struct Engn Rich Birkelands Vei 1a NO-7491 Trondheim Norway

The safety and reliability of cables are directly linked to the safe operation of bridges as crucial load-bearing components. The accuracy and efficiency of current methods are still insufficient to segment and quantitatively characterize surface defects on cables. This paper proposes a novel and efficient method for the refined segmentation and quantitative characterization of bridge cable surface defects based on an improved you only look at coefficients++ (YOLACT++) model. For defect segmentation, several enhancements have been made to the YOLACT++ model, including incorporating the convolutional block attention module (CBAM), optimizing the anchor box generation mechanism, and introducing the smoother Mish activation function, which enhances both the accuracy and speed of defect detection. For quantitative characterization, the method adopts surface correction algorithms, pixel statistics, and crack skeleton extraction, resulting in a more accurate representation of defect areas and the length and width of cracks. Compared to the baseline model, the optimized model achieves a 3.58 % improvement in mean average precision (mAP) and an inference speed of 25.74 frames per second (FPS). The results show that the error is within 10 % compared with the manually measured area, which offers a more objective and comprehensive foundation for cable safety assessment.

关键词： Cables defect segmentation defect quantitative characterization YOLACT plus plus Cylindrical surface correction

来源：评论

学校读者我要写书评

暂无评论

Detection and segmentation of defects in Industrial CT Images Based on Mask R-CNN

引用

电脑学刊 2020年第6期31卷 141-154页

作者： Jun-Nian Gou Xiao-Yuan Wu Li Liu

For defect detection and segmentation of industrial computed tomography (CT) images, existing methods regard them as two separate tasks, that is, the detection and the segmentation are not integrated. This paper improves mask regions with convolutional neural networks (Mask R-CNN), and the improved network is used to complete the detection and segmentation of industrial CT image defects at the same time. In this study, the three most common defects in industrial CT images are cracks, bubbles, and slags, which are taken as the research objects. The experimental results showed that the network can achieve a detection mAP value of 0.98 and a segmentation accuracy of 0.96 for three typical CT image defects (12 × 12 pixels~35 × 35 pixels). The method proposed in this paper has high accuracy, in both the defect detection and segmentation of industrial CT images. At the same time, the algorithm also has good robustness and generalization ability. It can be applied to the detection and segmentation of various defects and has great practical significance.

关键词： defect detection defect segmentation industrial CT image mask R-CNN

来源：评论

学校读者我要写书评

暂无评论

Identification of early decayed oranges using structured-illumination reflectance imaging coupled with fast demodulation and improved image processing algorithms

引用

POSTHARVEST BIOLOGY AND TECHNOLOGY 2024年 207卷

作者： Li, Jiangbo Lu, Yuzhen Lu, Renfu Beijing Acad Agr & Forestry Sci Intelligent Equipment Res Ctr Beijing Peoples R China Michigan State Univ Dept Biosyst & Agr Engn E Lansing MI 48824 USA United States Dept Agr Agr Res Serv E Lansing MI 48824 USA

Effective detection of decayed oranges (Citrus genus) at the early stage is challenging because there are no or few visual symptoms on the infected fruit. Structured-illumination reflectance imaging (SIRI) has been proven effective for enhanced detection of subsurface defects in fruit. Amplitude component (AC) images retrieved from the original SIRI patterned images are useful for defect detection, but generally require acquiring three phase shifted pattern images, which limits the imaging and detection speed. Moreover, the AC images may also suffer from noticeable uneven brightness due to fruit curvature, which affects the identification of decayed areas. This study was therefore aimed to explore faster image demodulation, enhancement and processing algorithms, based on a specially developed SIRI technology, for effective identification of early decayed oranges. Pattern images were acquired, using three phase-shifted sinusoidal illumination patterns at the wavelength of 810 nm and a spatial frequency of 0.20 cycles mm-1, from the orange samples infected with Penicillium digitatum fungus, the most serious and devastating pathogen for orange fruit. Two-dimensional spiral phase transform was used to obtain AC images from one or two pattern images. The acquired AC images were then processed by using simple brightness adjustment and integral image-based fast average filtering for brightness correction, and improved watershed algorithm and global threshold for segmentation of decayed areas. Three different combinations of these image processing procedures for single and two pattern images were proposed to distinguish decayed oranges from sound ones. The three methodologies all achieved high overall identification rates of 97.5%, 95.0% and 95.3%, when the stem-end effect was also considered. This study showed that accurate detection of early decayed orange fruit can be achieved by using one or two phase-shifted pattern images, which would be beneficial for real-time imple

关键词： Citrus decay defect segmentation Brightness transformation Image enhancement Classification

来源：评论

学校读者我要写书评

暂无评论

A new method for deep learning detection of defects in X-ray images of pressure vessel welds

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-12页

作者： Wang, Xue He, Feng Huang, Xu Chongqing Univ Sci & Technol Sch Elect Engn HuXi St Chongqing 401331 Peoples R China

Given that defect detection in weld X-ray images is a critical aspect of pressure vessel manufacturing and inspection, accurate differentiation of the type, distribution, number, and area of defects in the images serves as the foundation for judging weld quality, and the segmentation method of defects in digital X-ray images is the core technology for differentiating defects. Based on the publicly available weld seam dataset GDX-ray, this paper proposes a complete technique for fault segmentation in X-ray pictures of pressure vessel welds. The key works are as follows: (1) To address the problem of a lack of defect samples and imbalanced distribution inside GDX-ray, a DA-DCGAN based on a two-channel attention mechanism is devised to increase sample data. (2) A convolutional block attention mechanism is incorporated into the coding layer to boost the accuracy of small-scale defect identification. The proposed MAU-Net defect semantic segmentation network uses multi-scale even convolution to enhance large-scale features. The proposed method can mask electrostatic interference and non-defect-class parts in the actual weld X-ray images, achieve an average segmentation accuracy of 84.75% for the GDX-ray dataset, segment and accurately rate the valid defects with a correct rating rate of 95%, and thus realize practical value in engineering.

关键词： Pressure vessel welds X-ray images DC-GAN defect segmentation U-Net

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：