Multispectral water leakage detection based on a one-stage anchor-free modality fusion network for metro tunnels

Han, Lei; Chen, Jiang‐Fan; Li, Haobo; Liu, Genshuo; Leng, Biao; Ahmed, Ammar; Zhang, Zutao

doi:10.1016/j.autcon.2022.104345

Cited by 21 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Han et al [5] fused visible and thermal infrared images using a feature pyramid network. The goal is to minimize the adverse effects of visible light cameras' sensitivity to light.…”

Section: Introductionmentioning

confidence: 99%

Multi visual images fusion approach for metro tunnel defects based on saliency optimization of pixel level defect image features

Qiu,

Zhu,

Wang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The multi vision metro tunnel defect sensing system mainly consists of IRT and RGB cameras, which can automatically identify and extract small tunnel lining surface defects, greatly improving detection efficiency. However, the presence of various issues like train vibration, inconsistent lighting, fluctuations in temperature and humidity leads to the images showing inadequate uniformity in illumination, blurriness, and a decrease in the level of detail. The above issues have led to unsatisfactory fusion processing results for multiple visual images and increased missed detection rates. A multi visual images fusion approach for metro tunnel defects based on saliency optimization of pixel level defect image features is proposed. This method first takes the motion state of the train and the blurry image as constraints to eliminate dynamic blurring in the image. Secondly, Image weights are allocated based on the uniformity of visible light image illumination in the tunnel, as well as real-time temperature and humidity. Finally, image feature extraction and fusion are performed by a U-Net network that integrates channel attention mechanisms. The experimental results demonstrate that this approach improves the image pixel value variation rate by 39.7%, enhances the edge quality by 23%, and outperforms similar approach in terms of average gradient, gradient quality, and sum of difference correlation with improvements of 15.9%, 7.3%, and 26.6% respectively.

show abstract

“…Han et al [5] fused visible and thermal infrared images using a feature pyramid network. The goal is to minimize the adverse effects of visible light cameras' sensitivity to light.…”

Section: Introductionmentioning

confidence: 99%

Multi visual images fusion approach for metro tunnel defects based on saliency optimization of pixel level defect image features

Qiu,

Zhu,

Wang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Infrared thermography detection technology offers fast scanning speeds and is independent of visible light illumination, but its results can be affected by external factors such as other heat sources [11]. Han et al [20] proposed a monitoring approach based on multispectral fusion, combining the advantages of visual optics and thermal infrared sensors. However, these methods require substantial preparatory work to create extensive datasets.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Wet Area of Underwater Tunnel Lining

Lai,

Zhang,

2024

Buildings

View full text Add to dashboard Cite

The issue of water seepage poses a significant challenge in tunnel infrastructure. Wet areas are commonly used to evaluate the degree of water seepage in tunnel projects. To investigate the feasibility for numerical simulation to predict a wet area, we selected concrete test blocks with two types of defects—holes and cracks—as the research specimens. Numerical models for various seepage conditions were constructed using TOUGH2, and the results were validated through laboratory experiments. Additionally, the Shenjiamen Subsea Tunnel was simplified into a numerical model, employing TOUGH2 to forecast its future wet area performance within the scope of national standards. The outcomes of our research revealed that point seepage and line seepage exhibited circular and elliptical morphologies, respectively. Moreover, external water pressure and defect size exerted a significant influence on the expansion of the wet area. Notably, the impact of crack width surpassed that of hole diameter. Encouragingly, the numerical models generated using TOUGH2 for unsaturated concrete demonstrated excellent agreement with laboratory test results concerning the geometry, size, and pattern of the wet area. These findings signified the potential of TOUGH2 numerical simulation as a valuable tool in predicting the lifespan of tunnels.

show abstract

Research on Control Strategy of Flywheel Energy Storage System in Urban Railway System

Qi,

Zhang,

Tian

et al. 2024

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Multispectral water leakage detection based on a one-stage anchor-free modality fusion network for metro tunnels

Cited by 21 publications

References 23 publications

Multi visual images fusion approach for metro tunnel defects based on saliency optimization of pixel level defect image features

Multi visual images fusion approach for metro tunnel defects based on saliency optimization of pixel level defect image features

Prediction of Wet Area of Underwater Tunnel Lining

Research on Control Strategy of Flywheel Energy Storage System in Urban Railway System

Contact Info

Product

Resources

About