Robust multitask compressive sampling via deep generative models for crack detection in structural health monitoring

In structural health monitoring (SHM), there is an increasing demand for real-time image-based damage detection. Such a technology is essential for minimizing hazard loss caused by delayed emergency response after earthquakes or other natural disasters, or service interruption during structural inspection. Compressive sampling (CS) is a promising solution to achieve such a goal by greatly reducing the power consumption on high-resolution image transmission when using wireless devices. However, conventional CS failed to achieve high enough compression ratios, while existing generative-model-based CS requires laboriously training a high-quality generator with many large-scale images. To overcome such a bottleneck that hinders the practical use of CS in SHM, we propose a multitask CS algorithm that only relies on existing generators trained by low-pixel crack images. By exploiting the new discovery that similar crack images share a similar sparsity pattern in their latent vectors mapped by the generator, our algorithm achieves higher crack detection accuracy and robustness within a much shorter time when using a high data compression ratio. We verify the effectiveness of the proposed CS algorithm using synthetic and real image data. The results demonstrate that this work has moved a step closer toward successful implementation of operational CS-based crack detection systems in real-time SHM.

Automated summary

In the field of structural health monitoring (SHM), real-time image-based damage detection is highly demanded. Compressive sampling (CS), a promising solution to reduce power consumption, has faced limitations such as low compression ratios and the need for laborious training. To overcome these barriers, a multitask CS algorithm that relies on existing generators trained by low-pixel crack images is proposed. By exploiting the similarity in sparsity pattern among crack images, the algorithm achieves higher crack detection accuracy and efficiency. Verification using synthetic and real image data shows its potential for operational CS-based crack detection systems in real-time SHM.