Hainian Wang’s research while affiliated with Chang'an University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (36)


Forward Simulation of GPR Detection for Irregular Concealed Distresses of Road Pavement Based on the FDTD Method
  • Article

June 2025

·

5 Reads

Journal of Transportation Engineering Part B Pavements

·

·

Hainian Wang

·

[...]

·

Wei Xu

FIGURE 1 Frame work of real-time Pavement Crack Measurement, which consists of Instance-aware Hybrid Distillation (IHD), Pavement Crack Measurement.
FIGURE 3 Schematic diagram of the proposed real-time crack surface feature measurement algorithm: (a) camera projection model; (b) traditional method suffers from local branch and feature end loss during thinning; (c) overview of the proposed method flow; (d) skeleton extraction results of the proposed method; (e) extract negative contour, positive contour; (f) obtain midpoint; (g) results of skeleton extraction. distortion function, while í µí»¿ characterizes the distortion. ( , ) c d d a a
FIGURE 8 Visualization of Real-Time Pavement Crack Measurement. Robotic visual interface can display real-time FPS and crack measurement parameters.
Main components of our equipment.
Comparative assessment of crack measurement performance utilizing the proposed method on five segmentation models with three pavement crack conditions.
Crack Segmentation Guided Measurement with Lightweight Distillation Network on Edge Device
  • Article
  • Full-text available

March 2025

·

90 Reads

·

1 Citation

Pavement crack measurement (PCM) is essential for automated, precise road condition assessment. However, balancing speed and accuracy on edge artificial intelligence (AI) mobile devices remains challenging. This paper proposes a real‐time PCM framework for edge deployment, incorporating a lightweight distillation network and a surface feature measurement algorithm. Specifically, the proposed instance‐aware hybrid distillation module combines feature‐based and relation‐based knowledge distillation, leveraging crack instance‐related information for efficient knowledge transfer from teacher to student networks, which results in a more accurate and lightweight segmentation model. Additionally, a real‐time crack surface feature measurement algorithm, based on distance mapping relationships and crack edge coordinate extraction, addresses issues with crack edge branching and loss, enhancing measurement efficiency. Real‐time measurement was performed on actual roads utilizing mobile robot equipped with an edge computing unit. The crack segmentation precision reached 84.37%, with a frame per second of 77.72. Compared to the ground truth, the relative error for average crack width ranged from 6.42% to 40.65%, while the relative error for crack length varied between 1.48% and 3.76%. These findings highlight the feasibility of real‐time crack assessment and save road maintenance costs.

Download









Citations (27)


... Road cracks are a prevalent form of road damage [1], especially in high-traffic infrastructures such as highways and urban roads [2,3]. These cracks typically arise from factors such as aging materials, overload, and water erosion, and tend to expand progressively over time. ...

Reference:

Road crack detection based on improved RT-DETR
Crack Segmentation Guided Measurement with Lightweight Distillation Network on Edge Device

... zhang et al. [19] propose a new context-aware deep convolutional semantic segmentation network, which applies a pixel-by-pixel deep semantic segmentation network to segment cracks on images of any size and can effectively detect cracks in structural infrastructure under various conditions. Additionally, numerous crack detection algorithms have been widely applied [20][21][22][23][24], particularly in automated and intelligent systems. For example, Zhang et al. [25] proposed a visual tracking framework based on S2TNet for segmenting and tracking slender road cracks in complex environments, The algorithm ensures stable real-time performance and has shown excellent results in unmanned wheeled robot applications. ...

Vision-guided robot for automated pixel-level pavement crack sealing
  • Citing Article
  • December 2024

Automation in Construction

... Regardless of the treatment procedure and materials used, these researchers considered specific methodologies to determine the optimum time for crack treatment based on prioritization factors. Fourth, researchers focus on image detection using image processing [27], [28]. The concern of this research was related to the identification and classification of cracking types, but not on the treatments. ...

Self-adaptive 2D 3D image fusion for automated pixel-level pavement crack detection
  • Citing Article
  • December 2024

Automation in Construction

... Over the past decade (2013)(2014)(2015)(2016)(2017)(2018)(2019)(2020)(2021)(2022)(2023), the road transportation industry in China has developed rapidly, with the total length of road mileage increasing from 4.35 million kilometers to over 5.43 million kilometers. Among this, expressways now extend over 180,000 km, comprising 3.4% of the total length of road mileage (Gao et al. 2025). Alongside the growth in highway mileage, the traffic environment characterized by long service life and heavy loads has placed higher performance demands on highway construction. ...

Research progress of bio-asphalt towards green pavement development: Preparation, properties, and mechanism
  • Citing Article
  • October 2024

Fuel

... Various methods have been proposed for position control in low-speed rotation systems. For example, Zhang et al [14] dynamically adjusted PID controller parameters through ELM, significantly improving the system's accuracy in complex trajectory tracking tasks. Wang et al [15] used ELM to estimate trajectory errors caused by multi-task coupling and combined it with sliding mode control to compensate for the errors. ...

Robust ELM-PID tracing control on autonomous mobile robot via transformer-based pavement crack segmentation
  • Citing Article
  • October 2024

Measurement

... zhang et al. [19] propose a new context-aware deep convolutional semantic segmentation network, which applies a pixel-by-pixel deep semantic segmentation network to segment cracks on images of any size and can effectively detect cracks in structural infrastructure under various conditions. Additionally, numerous crack detection algorithms have been widely applied [20][21][22][23][24], particularly in automated and intelligent systems. For example, Zhang et al. [25] proposed a visual tracking framework based on S2TNet for segmenting and tracking slender road cracks in complex environments, The algorithm ensures stable real-time performance and has shown excellent results in unmanned wheeled robot applications. ...

Transformer-based Pavement Crack Tracking with Neural-PID Controller on Vision-guided Robot

... Additionally, numerous crack detection algorithms have been widely applied [20][21][22][23][24], particularly in automated and intelligent systems. For example, Zhang et al. [25] proposed a visual tracking framework based on S2TNet for segmenting and tracking slender road cracks in complex environments, The algorithm ensures stable real-time performance and has shown excellent results in unmanned wheeled robot applications. Despite significant progress in existing methods, challenges remain in practical applications. ...

Segment-to-track for pavement crack with light-weight neural network on unmanned wheeled robot

Automation in Construction

... This approach is a promising way to improve the quality and longevity of road surfaces. Polymer-enriched asphalt presents many advantages that greatly improve pavement sustainability and performance [3,11]. ...

Evaluation of the Thermal Stability and Micro-Modification Mechanism of SBR/PP-Modified Asphalt

... Early applications by Chang and Meegoda (1997) have been expanded with advanced computational techniques, allowing DEM to effectively model the internal structural performance of asphalt mixtures. Its adoption reflects its ability to simulate significant deformations and fractures, crucial for addressing the discrete and heterogeneous nature of asphalt materials (Jianzhong et al., 2023;Wan et al., 2024;Zhao et al., 2023), while employing straightforward constitutive laws Yi et al., 2021). Despite its strengths, current DEMbased crack models for asphalt mixture present several limitations that are the focus of ongoing research. ...

Modeling and validation of impact forces for back‐calculation of pavement surface moduli

... Xiao et al. [22] identified a limitation in previous studies, namely that most experiments require manual operation and visual observation of experimental data during testing. Operational errors in the instruments and discrepancies in reading measurements can affect the accuracy of WDF data. ...

Asphalt pavement water film thickness detection and prediction model: A review
  • Citing Article
  • June 2023

Journal of Traffic and Transportation Engineering (English Edition)