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

Zhong, Jingtao; Zhu, Junqing; Huo, Ju; Zhang, Weiguang

doi:10.1016/j.autcon.2022.104436

Cited by 49 publications

(10 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One is to directly observe the semantic segmentation effect of the wear debris image, and the other is by introducing the relevant evaluation indexes. In this work, two widely used semantic segmentation model evaluation standards, i.e., the values of mIoU and mean pixel accuracy (mPA) were used [40][41][42]. The mIoU denotes the average ratio between the intersection and union of both value of the HRNetv2 model is 96.48%, and there is a high degree of pixel-level matching between the segmentation results and the true value maps.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

Small data-driven semantic segmentation of wear debris in ferrography images

Xi,

Zhang,

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The segmentation of wear debris images is a prerequisite for ferrographic analysis, and uncertainties and errors in wear debris segmentation will inevitably affect the subsequent analysis. In this work, a small-data semantic segmentation model of wear debris images is constructed based on HRNetv2 for ferrography images acquired by using an online visual ferrography (OLVF). A major advantage of the current model is that fewer ferrography images are required for training, and fewer iterations are needed. The current work is performed for ferrography images with both clean oil and contaminated oil, and good segmentation results can be found. Specially, the experimental results show that the current model can achieve accurate segmentation of wear debris images with mean intersection over union (mIoU) values of 91.47% and mean pixel accuracy (mPA) values of 96.48%.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Small data-driven semantic segmentation of wear debris in ferrography images

Xi,

Zhang,

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Different types of urban pavement distress are continuously showing up on the surface and are requiring more and more effort in terms of identification and maintenance. In addition to impairing pavement performance, pavement deterioration also contributes to traffic accidents [1,2]. Consequently, the lifespan of pavements continually shortens, demanding more frequent maintenance to address escalating distress.…”

Section: Introductionmentioning

confidence: 99%

Automatic Detection of Urban Pavement Distress and Dropped Objects with a Comprehensive Dataset Collected via Smartphone

Xu,

Fu,

et al. 2024

Buildings

Self Cite

View full text Add to dashboard Cite

Pavement distress seriously affects the quality of pavement and reduces driving comfort and safety. The dropped objects from vehicles have increased the risks of traffic accidents. Therefore, automatic detection of urban pavement distress and dropped objects is an effective method to timely evaluate pavement condition. Firstly, this paper utilized a portable platform to collect pavement distress and dropped objects to establish a high-quality dataset. Six types of pavement distresses: transverse crack, longitudinal crack, alligator crack, oblique crack, potholes, and repair, and three types of dropped objects: plastic bottle, metal bottle, and tetra pak were included in this comprehensive dataset. Secondly, the real-time YOLO series detection models were used to classify and localize the pavement distresses and dropped objects. In addition, segmentation models W-segnet, U-Net, and SegNet were utilized to achieve pixel-level detection of pavement distress and dropped objects. The results show that YOLOv8 outperformed YOLOv5 and YOLOv7 with a MAP of 0.889. W-segnet showed an overall MIoU of 70.65% and 68.33% on the training set and test set, respectively, being superior to the comparison model and being able to achieve high-precision pixel-level segmentation. Finally, the trained models were performed on the holdout dataset for the generalization test. The proposed methods integrated the detection of urban pavement distress and dropped objects, which could significantly contribute to driving safety.

show abstract

“…In addition, deep features can be extracted from image data to effectively deal with cracks with different shapes and complex backgrounds [ 7 ]. At present, deep learning algorithms based on convolutional neural networks have been tried and achieved many results in the task of accurately locating and classifying cracks [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 ]. Among them, compared with the object detection network model, the crack detection algorithm based on SSNM can not only classify and locate the crack object but also obtain the pixel-level contour of the crack, so as to provide finer and higher-level semantic information for subsequent visual applications.…”

Section: Introductionmentioning

confidence: 99%

“…Zhang et al [ 16 ] used lightweight MoblileNetv2 to replace ResNet, the original backbone feature extraction network of PSPNet, and introduced the position attention module to obtain rich contextual information, so that similar features at different positions could enhance each other and improve crack detection results. Zhong et al [ 17 ] proposed a multi-scale feature fusion deep neural network structure w-SegNet based on the SegNet network, which has strong robustness for crack detection in various scenarios. Zheng et al [ 18 ] proposed a high-precision crack detection method for lightweight concrete bridges based on SegNet and the separable convolutional residual of bottleneck depth, and they used 1500 self-collected bridge crack images for model training.…”

Section: Introductionmentioning

confidence: 99%

Study on the Influence of Label Image Accuracy on the Performance of Concrete Crack Segmentation Network Models

Ma,

Hao,

Shang

et al. 2024

Sensors

View full text Add to dashboard Cite

A high-quality dataset is a basic requirement to ensure the training quality and prediction accuracy of a deep learning network model (DLNM). To explore the influence of label image accuracy on the performance of a concrete crack segmentation network model in a semantic segmentation dataset, this study uses three labelling strategies, namely pixel-level fine labelling, outer contour widening labelling and topological structure widening labelling, respectively, to generate crack label images and construct three sets of crack semantic segmentation datasets with different accuracy. Four semantic segmentation network models (SSNMs), U-Net, High-Resolution Net (HRNet)V2, Pyramid Scene Parsing Network (PSPNet) and DeepLabV3+, were used for learning and training. The results show that the datasets constructed from the crack label images with pix-el-level fine labelling are more conducive to improving the accuracy of the network model for crack image segmentation. The U-Net had the best performance among the four SSNMs. The Mean Intersection over Union (MIoU), Mean Pixel Accuracy (MPA) and Accuracy reached 85.47%, 90.86% and 98.66%, respectively. The average difference between the quantized width of the crack image segmentation obtained by U-Net and the real crack width was 0.734 pixels, the maximum difference was 1.997 pixels, and the minimum difference was 0.141 pixels. Therefore, to improve the segmentation accuracy of crack images, the pixel-level fine labelling strategy and U-Net are the best choices.

show abstract

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

Cited by 49 publications

References 32 publications

Small data-driven semantic segmentation of wear debris in ferrography images

Small data-driven semantic segmentation of wear debris in ferrography images

Automatic Detection of Urban Pavement Distress and Dropped Objects with a Comprehensive Dataset Collected via Smartphone

Study on the Influence of Label Image Accuracy on the Performance of Concrete Crack Segmentation Network Models

Contact Info

Product

Resources

About