☆ 4.7 Article

Lightweight convolutional neural network driven by small data for asphalt pavement crack segmentation

AUTOMATION IN CONSTRUCTION (2024)

Related references

Note: Only part of the references are listed.

Article Construction & Building Technology

Multi-scale triple-attention network for pixelwise crack segmentation

Lei Yang et al.

Summary: Intelligent crack detection plays a significant role in maintaining infrastructure, especially roads in China. However, detecting pavement defects is challenging due to complex backgrounds, micro defects, and class imbalance issues. To address these challenges, a multiscale triple-attention network called MST-Net is proposed for end-to-end pixelwise crack detection. The proposed network utilizes a multiscale input strategy, additive attention fusion block, and triple attention block to improve the detection performance on crack segmentation. Experimental results show that the MST-Net achieves excellent performance on pixelwise crack detection.

AUTOMATION IN CONSTRUCTION (2023)

Add to Collection

Article Construction & Building Technology

Modeling automatic pavement crack object detection and pixel-level segmentation

Yuchuan Du et al.

Summary: This study proposes a lightweight pavement crack-detection model that combines object detection and semantic segmentation tasks. It utilizes a modified YOLOv4-Tiny model to predict crack bounding boxes and proposes a segmentation threshold. Additionally, an attention feature pyramid network and a denoising autoencoder network are introduced to compensate for accuracy loss and remove background noise. The proposed model achieves equivalent evaluation index values with significantly fewer parameters than conventional models.

AUTOMATION IN CONSTRUCTION (2023)

Add to Collection

Article Automation & Control Systems

A hybrid deep learning pavement crack semantic segmentation

Zaid Al-Huda et al.

Summary: Automatic pavement crack segmentation is critical in defect inspection. This study proposes a hybrid deep learning approach that exploits the relationship between classification and segmentation tasks to improve pavement crack segmentation. The proposed KTCAM-Net achieves state-of-the-art segmentation results by combining the localization abilities of a trained crack classification network with an encoder-decoder segmentation network.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2023)

Add to Collection

Article Construction & Building Technology

Automated crack segmentation on 3D asphalt surfaces with richer attention and hybrid pyramid structures

Shuo Ding et al.

Summary: This study proposes a novel pixel-level pavement crack segmentation network, PCSNet, to address the challenge of crack detection in intelligent pavement surveys. The network integrates richer attention and hybrid pyramid structures, enhancing crack feature representation and scene parsing. By capturing crack spatial dependence information and integrating contextual information at multiple receptive field scales, the network achieves superior performance with F1-score, mean intersection of union, and mean pixel accuracy of 81.21%, 77.13%, and 87.17%, respectively. The method reconstructs complete crack geometry, preserves crack edges well, and optimizes the detection of shallow and complex cracks.

INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING (2023)

Add to Collection

Review Construction & Building Technology

Semantic segmentation of cracks: Data challenges and architecture

Fabio Panella et al.

Summary: This paper analyzes the research on semantic segmentation in the presence of fine structures and the effectiveness of different approaches to address class imbalance. UNet architecture is found to outperform networks without pooling layers in both performance and training time. The authors argue that UNet architecture is the state of the art for crack segmentation. However, networks without pooling layers may become attractive when computational cost is not a concern.

AUTOMATION IN CONSTRUCTION (2022)

Add to Collection

Article Engineering, Civil

CrackW-Net: A Novel Pavement Crack Image Segmentation Convolutional Neural Network

Chengjia Han et al.

Summary: This paper introduces CrackW-Net, which achieves pixel-level semantic segmentation of pavement cracks with a novel network structure, and conducts training and comparative experiments on two datasets. Results show that CrackW-Net performs the best in crack detection tasks.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Add to Collection

Article Construction & Building Technology

Optimization and sensitivity analysis of existing deep learning models for pavement surface monitoring using low-quality images

Ronald Roberts et al.

Summary: This paper practically analyzes deep learning models for pavement distress detection using French secondary road surface images and explores the impact of augmentation and hyperparameter case studies on model instrumentation and implementation.

AUTOMATION IN CONSTRUCTION (2022)

Add to Collection

Article Construction & Building Technology

Multi-scale feature fusion network for pixel-level pavement distress detection

Jingtao Zhong et al.

Summary: This paper proposes a novel deep neural network architecture, W-segnet, based on multi-scale feature fusions for pixel-wise distress segmentation. Experimental results show that W-segnet achieves strong robustness and outperforms other state-of-the-art models.

AUTOMATION IN CONSTRUCTION (2022)

Add to Collection

Article Construction & Building Technology

Multi-scale feature fusion network for pixel-level pavement distress detection

Jingtao Zhong et al.

Summary: A novel deep neural network architecture, W-segnet, based on multi-scale feature fusions, is proposed for pixel-wise distress segmentation in pavement conditions. Experimental results demonstrate the robustness of W-segnet in various scenarios, outperforming other state-of-the-art semantic segmentation models.

AUTOMATION IN CONSTRUCTION (2022)

Add to Collection

Article Computer Science, Hardware & Architecture

A novel approach for left ventricle segmentation in tagged MRI

Xijing Zou et al.

Summary: An automatic left ventricle segmentation algorithm is proposed using deep learning and curriculum learning strategy for tagged cardiac magnetic resonance imaging. The algorithm utilizes local sine-wave modeling (SinMod) to track cardiac motion information, utilizes U-Net to segment LV endocardium and epicardium, and adopts a curriculum learning training strategy to improve segmentation accuracy. Superior performance to traditional methods is demonstrated through comparative results.

COMPUTERS & ELECTRICAL ENGINEERING (2021)

Add to Collection

Article Engineering, Multidisciplinary

Automatic recognition and analysis system of asphalt pavement cracks using interleaved low-rank group convolution hybrid deep network and SegNet fusing dense condition random field

Gang Li et al.

Summary: The paper introduces the importance of pavement crack detection, proposes a novel crack recognition and analysis system based on deep learning, and develops an interactive crack detection software. Experimental results show that the system outperforms other state-of-the-art algorithms in terms of accuracy, parameters, speed, and anti-interference ability, meeting actual engineering requirements.

MEASUREMENT (2021)

Add to Collection

Article Engineering, Multidisciplinary

An improved minimal path selection approach with new strategies for pavement crack segmentation

Yizheng Chen et al.

Summary: This study introduces an improved minimal cost path algorithm (IMPS) for crack segmentation, which demonstrates more efficient path planning and greater accuracy compared to traditional methods.

MEASUREMENT (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

Screening of Glaucoma disease from retinal vessel images using semantic segmentation

Rakhshanda Imtiaz et al.

Summary: The study presents an effective method for segmenting the optic disk (OD) and optic cup (OC) in glaucoma by semantic pixel-wise labeling, without the need for pre- and post-processing steps. Evaluated on different datasets, the method shows low computational and resource requirements, supporting its implementation in real-time screening for glaucoma disease.

COMPUTERS & ELECTRICAL ENGINEERING (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

Dynamic adaptive residual network for liver CT image segmentation

Xiwang Xie et al.

Summary: This study introduces a liver image segmentation method based on dynamic adaptive residual network, improving the accuracy and efficiency of liver image segmentation by optimizing the network structure and introducing methods such as conditional random fields.

COMPUTERS & ELECTRICAL ENGINEERING (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

Pooling Attention-based Encoder-Decoder Network for semantic segmentation

Haixia Xu et al.

Summary: This paper proposes an Encoder-Decoder network for image semantic segmentation using pooling SE-ResNet attention module, called PAEDN, to address the challenge of poor pixel-consistency in inter-category and pixel-similarity in inter-category. Experimental evaluations on PASCAL and Cityscapes datasets show that the proposed method achieves good pixel-consistency semantic label and a 15.1% improvement over FCN.

COMPUTERS & ELECTRICAL ENGINEERING (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

Multi-feature fusion network for road scene semantic segmentation

Jiaxing Sun et al.

Summary: This paper introduces a lightweight semantic segmentation model for intelligent transportation system, utilizing shallow neural networks. By simplifying the model structure and feature fusion methods, the approach achieves high accuracy while maintaining fast speed.

COMPUTERS & ELECTRICAL ENGINEERING (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Pavement defect detection with fully convolutional network and an uncertainty framework

Zheng Tong et al.

COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING (2020)

Add to Collection

Article Construction & Building Technology

Image-based concrete crack detection in tunnels using deep fully convolutional networks

Yupeng Ren et al.

CONSTRUCTION AND BUILDING MATERIALS (2020)

Add to Collection

Article Engineering, Civil

Increasing the robustness of material-specific deep learning models for crack detection across different materials

Mohamad Alipour et al.

ENGINEERING STRUCTURES (2020)

Add to Collection

Article Engineering, Civil

Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection

Fan Yang et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2020)

Add to Collection

Article Construction & Building Technology

CrackU-net: A novel deep convolutional neural network for pixelwise pavement crack detection

Huyan Ju et al.

STRUCTURAL CONTROL & HEALTH MONITORING (2020)

Add to Collection

Article Construction & Building Technology

An integrated approach to automatic pixel-level crack detection and quantification of asphalt pavement

Ankang Ji et al.

AUTOMATION IN CONSTRUCTION (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Automatic crack distress classification from concrete surface images using a novel deep-width network architecture

Li Guo et al.

NEUROCOMPUTING (2020)

Add to Collection

Article Construction & Building Technology

Fast and robust pavement crack distress segmentation utilizing steerable filtering and local order energy

Jia Liang et al.

CONSTRUCTION AND BUILDING MATERIALS (2020)

Add to Collection

Article Computer Science, Software Engineering

Optimized minimal path selection (OMPS) method for automatic and unsupervised crack segmentation within two-dimensional pavement images

Wissam Kaddah et al.

VISUAL COMPUTER (2019)

Add to Collection

Article Construction & Building Technology

Autonomous concrete crack detection using deep fully convolutional neural network

Cao Vu Dung et al.

AUTOMATION IN CONSTRUCTION (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Hybrid representation learning for cross-modal retrieval

Wenming Cao et al.

NEUROCOMPUTING (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

DeepCrack: A deep hierarchical feature learning architecture for crack segmentation

Yahui Liu et al.

NEUROCOMPUTING (2019)

Add to Collection

Article Construction & Building Technology

Computer vision-based concrete crack detection using U-net fully convolutional networks

Zhenqing Liu et al.

AUTOMATION IN CONSTRUCTION (2019)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Robust Pixel-Level Crack Detection Using Deep Fully Convolutional Neural Networks

Mohamad Alipour et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Liang-Chieh Chen et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2018)

Add to Collection

Article Computer Science, Artificial Intelligence

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Vijay Badrinarayanan et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

Add to Collection

Article Computer Science, Artificial Intelligence

Fully Convolutional Networks for Semantic Segmentation

Evan Shelhamer et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

Add to Collection

Article Engineering, Civil

Functional Evaluation of Pavement Condition Using a Complete Vision System

Y. O. Adu-Gyamfi et al.

JOURNAL OF TRANSPORTATION ENGINEERING (2014)

Add to Collection

Article Computer Science, Artificial Intelligence

Crack Tree: Automatic crack detection from pavement images

Qin Zou et al.

PATTERN RECOGNITION LETTERS (2012)

Add to Collection

Proceedings Paper Computer Science, Theory & Methods

A Survey on Monochrome Image Segmentation Methods

M. Sridevi et al.

2ND INTERNATIONAL CONFERENCE ON COMMUNICATION, COMPUTING & SECURITY [ICCCS-2012] (2012)

Add to Collection

Article Engineering, Civil

Wavelet-based pavement distress image edge detection with a trous algorithm

Kelvin C. P. Wang et al.

TRANSPORTATION RESEARCH RECORD (2007)

Add to Collection

© Peeref 2019-2024. All rights reserved.