Advances in Remote Sensing and AI for Infrastructure Monitoring

The field of remote sensing and AI is moving towards more efficient and accurate methods for monitoring and assessing infrastructure damage. Researchers are exploring the use of cross-modal data, such as optical and SAR imagery, to improve detection and tracking capabilities. Additionally, there is a growing interest in using explainable AI techniques to better understand the impact of environmental factors, such as flooding, on pavement deterioration. The development of low-power and resource-efficient algorithms is also a key area of focus, particularly for onboard methane detection and other applications where computational resources are limited. Notable papers include:

  • A novel dataset and method for cross-modal ship re-identification using optical and SAR imagery, which enables all-weather tracking and shorter re-imaging cycles.
  • A deep learning framework for building damage assessment using VHR SAR and geospatial data, which demonstrates improved detection accuracy and generalizability to previously unseen areas.

Sources

Cross-modal Ship Re-Identification via Optical and SAR Imagery: A Novel Dataset and Method

A Deep Learning framework for building damage assessment using VHR SAR and geospatial data: demonstration on the 2023 Turkiye Earthquake

Evaluating Pavement Deterioration Rates Due to Flooding Events Using Explainable AI

Optimizing Methane Detection On Board Satellites: Speed, Accuracy, and Low-Power Solutions for Resource-Constrained Hardware

AI and Remote Sensing for Resilient and Sustainable Built Environments: A Review of Current Methods, Open Data and Future Directions

Built with on top of