检索结果-内蒙古大学图书馆

Trans-DCN: A High-Efficiency and Adaptive Deep Network for Bridge Cable Surface defect segmentation

REMOTE SENSING 2024年第15期16卷 2711页

作者： Huang, Zhihai Guo, Bo Deng, Xiaolong Guo, Wenchao Min, Xing Guangdong Univ Technol Sch Civil & Transportat Engn Guangzhou 510006 Peoples R China Shenzhen Univ Sch Architecture & Urban Planning Shenzhen 518060 Peoples R China Guangdong Metro Design Res Inst Co Ltd Guangzhou 510499 Peoples R China

Cables are vital load-bearing components of cable-stayed bridges. Surface defects can lead to internal corrosion and fracturing, significantly impacting the stability of the bridge structure. The detection of surface defects from bridge cable images faces numerous challenges, including shadow disturbances due to uneven lighting and difficulties in addressing multiscale defect features. To address these challenges, this paper proposes a novel and cost-effective deep learning segmentation network, named Trans-DCN, to detect defects in the surface of the bridge cable. The network leverages an efficient Transformer-based encoder and integrates multiscale features to overcome the limitations associated with local feature inadequacy. The decoder implements an atrous Deformable Convolution (DCN) pyramid and dynamically fuses low-level feature information to perceive the complex distribution of defects. The effectiveness of Trans-DCN is evaluated by comparing it with state-of-the-art segmentation baseline models using a dataset comprising cable bridge defect images. Experimental results demonstrate that our network outperforms the state-of-the-art network SegFormer, achieving a 27.1% reduction in GFLOPs, a 1.2% increase in mean Intersection over Union, and a 1.5% increase in the F1 score. Ablation experiments confirmed the effectiveness of each module within our network, further substantiating the significant validity and advantages of Trans-DCN in the task of bridge cable defect segmentation. The network proposed in this paper provides an effective solution for downstream cable bridge image analysis.

关键词： deep learning defect segmentation bridge cable surface defects non-destructive cable health assessment

来源：评论

学校读者我要写书评

暂无评论

EDSV-Net: An efficient defect segmentation network based on visual attention and visual perception

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartB期237卷

作者： Huang, Yanqing Jing, Junfeng Sheng, Siyu Wang, Zhen Xian Polytech Univ Coll Elect & Informat Xian 710048 Peoples R China

In industrial production, surface defect detection algorithms based on convolutional neural networks have been widely studied to improve production quality. However, for practical applications, there are still many issues to be solved, such as the complexity and diversity of defect categories, the difficulty of obtaining defect samples, and the difficulty of existing algorithms in accurately segmenting defects. To solve these issues, we present an effective defect segmentation network based on visual attention and visual perception termed EDSV-Net. Specifically, we use ResNet18 as the backbone network in EDSV-Net. Then a multi-scale feature extraction (MSFE) module is introduced to enhance the scale invariance of high-level features and the diversity of contextual features. In addition, a spatial attention (SA) model combined with a channel attention (CA) model is applied to low level features and MSFE features, respectively, to extract more effective spatial and semantic information. Moreover, a depthwise separable convolution is introduced to reduce the network complexity. Finally, due to the issues of existing defect detection algorithms ignoring structural similarity and defects being difficult to obtain, we design a balanced defect and structural measure loss function. Meanwhile, we propose a structural similarity measure, which combines the pixel similarity for evaluation. EDSV-Net only requires no more than 60 random abnormal samples to obtain accurate segmentation results and the real-time performance meets the requirements of actual industrial production. Based on three challenging real-world defect datasets, the results of the evaluation demonstrate that EDSV-Net outperforms seven state-of-the-art methods on accuracy and real-time performance.

关键词： Surface defect detection defect segmentation Convolutional neural network Visual attention Multi-scale Structural similarity measure

来源：评论

学校读者我要写书评

暂无评论

A digital assistance system leveraging vision foundation models & 3D localization for reproducible defect segmentation in visual inspection

引用

Procedia CIRP 2024年 130卷 387-397页

作者： J. Koch D. Jevremovic K. Moenck T. Schüppstuhl Hamburg University of Technology Institute of Aircraft Production Technology Denickestr. 17 21073 Hamburg Germany

In response to the limitations of manual visual inspection in manufacturing industries, this paper presents a novel approach that combines Meta AI’s Segment Anything Model (SAM) as a current representative of a vision foundation model with marker-based localization techniques to enhance quality assurance processes. Focusing on aircraft cabin components, where product complexity and variance pose significant challenges, a digital assistance system is developed. By integrating SAM-based segmentation and defect localization on the CAD model, the proposed system facilitates significant parts of the inspection workflow, thereby increasing efficiency and reproducibility. The system also enables the collection of comprehensive data sets, which is essential for the refinement of AI models, e.g. in transfer learning approaches. A two-pronged evaluation approach includes the assessment of localization accuracies in an experimental setup as well as the evaluation of usability and workload in an industry-oriented user study. The novel segmentation approach using the SAM achieved high usability, providing an efficient and user-friendly solution for the application domain, while maintaining a reasonable workload for the operators, highlighting its significant potential for streamlining industrial inspection processes.

关键词： Digital Assistance System Visual Inspection Segment Anything Model SAM defect segmentation Worker Assistance Aircraft Manufacturing

来源：评论

学校读者我要写书评

暂无评论

Region- and Strength-Controllable GAN for defect Generation and segmentation in Industrial Images

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2022年第7期18卷 4531-4541页

作者： Niu, Shuanlong Li, Bin Wang, Xinggang Peng, Yaru Huazhong Univ Sci & Technol Sch Mech Sci & Engn Digital Mfg Equipment & Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China

Deep learning for computer vision has achieved remarkable results based on massive, diverse, and well-annotated training sets. However, it is difficult to collect defect datasets that cover all possible features, especially for small, weak defects. Therefore, in this article, a defect image generation method with controllable defect regions and strength is proposed. Regarded as image inpainting that uses a generative adversarial network, generated defect regions are controlled by using defect masks. Moreover, the defect direction vector is constructed in the latent variable space based on the feature continuity between defects and nondefects to control the defect strength, which enables a one-to-many correspondence between defect masks and images. Moreover, a defect attention loss is also designed to force the generation model to focus on the defect regions. Experimentally, our method yields generated images of better quality and diversity and thus significantly improves defect segmentation performance (an intersection over union of 63.20% and 61.86% on the Kolektor surface-defect and the metal hook defect datasets, respectively), especially for small, weak defects.

关键词： Training Image segmentation Aerospace electronics Informatics Generative adversarial networks Testing Standards Boundary defect samples data augmentation defect segmentation generative adversarial network (GAN) industrial image generation

来源：评论

学校读者我要写书评

暂无评论

Human-Machine Hybrid Strategy for defect Semantic segmentation With Limited Data

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Shan, Dexing Zhang, Yunzhou Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China

In the field of industrial intelligent inspection, two problems need to be solved urgently. One is how to integrate complex industrial inspection expertise into algorithms. The second is how to predict other similar products that have not been seen through prior knowledge of existing products. Solving these two problems can effectively solve the problems of insufficient samples and poor adaptability. Therefore, we propose a human-machine hybrid strategy to construct a promptable industrial scene segmentation task by human input of easy-to-obtain defect-free images or text as guidance information. Specifically, for unseen categories in unseen scenes, we propose to use a defect-free image as the guidance information, establish accurate pixel-level correspondence between defect-free and query images, and decode correlation maps through the 3-D residual convolutional network. For unseen categories in seen scenes, we propose a text-image model based on contrastive language-image pretraining (CLIP) to extract visual features aligned with the text. To establish more accurate text guidance, we obtain the holistic pattern of text features through global self-attention and establish global guidance between text and visual features. Extensive experiments demonstrate that our proposed approach, requiring no additional training or fine-tuning and solely relying on defect-free images and text as guidance, effectively segments previously unseen defect categories in both seen and unseen scenes. This method efficiently addresses the challenge of limited defect samples in the industrial domain.

关键词： defect segmentation few-shot learning human-machine hybrid multimodal data neural network application

来源：评论

学校读者我要写书评

暂无评论

Fabric defect Image segmentation Method Based on The Combination of Canny and Morphology 34

Fabric Defect Image Segmentation Method Based on The Combina...

引用

34th Chinese Control and Decision Conference (CCDC)

作者： Liu, Meiju Xu, Wenqiong Lin, Zixiang Dai, Yingxu Shenyang Jianzhu Univ Sch Informat & Control Engn Shenyang 110168 Peoples R China

ISBN: (纸本)9781665478960

In order to filter out the background noise while retaining the characteristics of the defects, this paper combines Canny and morphological processing to segment the fabric defects. After image preprocessing, our improved algorithm is used to detect the defects, and considering the characteristics of the fabric image, when using the morphology closed operation, the cross-shaped kernel and the rectangular kernel are combined to separate the defect and the background. The defect area obtained by the improved algorithm is compared with the defect area obtained by the expert manual marking method. The defect area obtained by the improved algorithm has a proportion of more than 85%, which proves that our proposed algorithm is effective in the field of image segmentation.

关键词： Canny,Morphological closed operation defect detection defect segmentation

来源：评论

学校读者我要写书评

暂无评论

Steering knuckle surface defect detection and segmentation based on reverse residual distillation

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartB期137卷

作者： Zhou, Shuaijie Cheng, Shuhong Zhang, Dianfan Wang, Zedai Zhang, Shijun Zhu, Yujie Wang, Hongbo Yanshan Univ Inst Elect Engn Qinhuangdao 066004 Hebei Peoples R China Yanshan Univ Hebei Key Lab Special Delivery Equipment Qinhuangdao 066004 Hebei Peoples R China BYD Automot Engn Res Inst Shenzhen 518118 Peoples R China Weichai Lovol Intelligent Agr Technol CO LTD Weifang 261206 Peoples R China Fudan Univ Acad Engn & Technol Shanghai 200433 Peoples R China

Although the supervised deep learning method effectively detects and segments the surface defects of the steering knuckle, in the absence of sufficient defect samples, the model is prone to tend to learn normal sample features and ignore defective features during the training process, leading to a higher defect detection error rate. In this paper, we propose an unsupervised defect detection method called reverse residual distillation, which can be trained using only defect-free steering knuckle surface images and can accurately detect and segment surface defects in steering knuckles. In this method, we adopt the encoder-decoder structure as the basic structure of the teacher-student network and integrate the reverse distillation and progressive distillation methods into the distillation process, which solves the overgeneralization problem in the student network and improves the distillation efficiency. Additionally, we introduce a trainable one-class bottleneck embedding module and a multi-scale channel attention feature fusion module to enhance the model's performance in detecting and segmenting defects. Experimental results on the mvtec anomaly detection (MVTec AD) dataset and the steering knuckle dataset demonstrate the effectiveness of our method in detecting and segmenting surface defects in industrial products. Especially in the steering knuckle dataset, the area under the receiver operating characteristic curve (AUROC) scores for defect detection and pixel-level segmentation achieved remarkable levels of 98.6% and 99.8%, respectively.

关键词： defect detection defect segmentation Knowledge distillation Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

defect Detection and segmentation Framework for Remote Field Eddy Current Sensor Data

引用

SENSORS 2017年第10期17卷 2276页

作者： Falque, Raphael Vidal-Calleja, Teresa Miro, Jaime Valls Univ Technol Sydney Ctr Autonomous Syst CB 11 09 300 Fac Engn & Informat Technol 15 Broadway Ultimo NSW 2007 Australia

Remote-Field Eddy-Current (RFEC) technology is often used as a Non-Destructive Evaluation (NDE) method to prevent water pipe failures. By analyzing the RFEC data, it is possible to quantify the corrosion present in pipes. Quantifying the corrosion involves detecting defects and extracting their depth and shape. For large sections of pipelines, this can be extremely time-consuming if performed manually. Automated approaches are therefore well motivated. In this article, we propose an automated framework to locate and segment defects in individual pipe segments, starting from raw RFEC measurements taken over large pipelines. The framework relies on a novel feature to robustly detect these defects and a segmentation algorithm applied to the deconvolved RFEC signal. The framework is evaluated using both simulated and real datasets, demonstrating its ability to efficiently segment the shape of corrosion defects.

关键词： Remote Field Eddy Current (RFEC) Non-Destructive Evaluation (NDE) defect segmentation active-contour

来源：评论

学校读者我要写书评

暂无评论

Fabric defect Image segmentation Method Based on The Combination of Canny and Morphology

Fabric Defect Image Segmentation Method Based on The Combina...

引用

第34届中国控制与决策会议

作者： Meiju Liu Wenqiong Xu Zixiang Lin Yingxu Dai School of Information and Control Engineering Shenyang Jianzhu University

ISBN: (纸本)9781665478977

In order to filter out the background noise while retaining the characteristics of the defects,this paper combines Canny and morphological processing to segment the fabric *** image preprocessing,our improved algorithm is used to detect the defects,and considering the characteristics of the fabric image,when using the morphology closed operation,the cross-shaped kernel and the rectangular kernel are combined to separate the defect and the *** defect area obtained by the improved algorithm is compared with the defect area obtained by the expert manual marking *** defect area obtained by the improved algorithm has a proportion of more than 85%,which proves that our proposed algorithm is effective in the field of image segmentation.

关键词： Canny Morphological closed operation defect detection defect segmentation

来源：评论

学校读者我要写书评

暂无评论

A self-configuring transformer segmentation method for welding radiographic defect detection in steel pipes

引用

NONDESTRUCTIVE TESTING AND EVALUATION 2025年

作者： Guan, Keming Zhou, Yifeng Wang, Li Chang, Baohua Du, Dong Tsinghua Univ Dept Mech Engn Beijing Peoples R China Tsinghua Univ Key Lab Adv Mat Proc Technol Minist Educ Beijing Peoples R China

Radiography is a primary non-destructive testing method and is crucial for ensuring the quality of steel pipe welds. Although deep learning-based methods have shown significant achievements, they still encounter subjective biases during the network configuration. In addition, the problems of quantitative segmentation of small defects and motion blur remains challenging. To address these issues, this study constructed a pipe weld defect detection system based on CCD camera and image intensifier. defect data are systematically collected and enhanced to establish a comprehensive pixel-level dataset of steel pipe weld defects. On this basis, a self-configuring transformer-based deep network (SCTnet) is proposed. It is capable of self-configuring parameters for any new dataset to generate a segmentation pipeline, reducing the subjectivity of the network. A multi-scale transformer module is proposed to integrate discriminative features across various semantic levels from a global perspective, effectively addressing the challenge of detecting small defects. Additionally, a hybrid loss function is proposed to effectively reduce the impact of motion blur. The results of using SCTnet on the steel pipe welds dataset demonstrate that the proposed segmentation method achieves competitive outcomes compared to other segmentation algorithms, with an average accuracy of 99.55% and an average dice coefficient of 78.91%.

关键词： Welding defect radiographic image defect segmentation deep learning transformer

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：