Urban Green Infrastructure Monitoring Using Remote Sensing from Integrated Visible and Thermal Infrared Cameras Mounted on a Moving Vehicle

Advanced Image Stitching Method for Dual-Sensor Inspection

Efficient image stitching plays a vital role in the Non-Destructive Evaluation (NDE) of infrastructures. An essential challenge in the NDE of infrastructures is precisely visualizing defects within large structures. The existing literature predominantly relies on high-resolution close-distance images to detect surface or subsurface defects. While the automatic detection of all defect types represents a significant advancement, understanding the location and continuity of defects is imperative. It is worth noting that some defects may be too small to capture from a considerable distance. Consequently, multiple image sequences are captured and processed using image stitching techniques. Additionally, visible and infrared data fusion strategies prove essential for acquiring comprehensive information to detect defects across vast structures. Hence, there is a need for an effective image stitching method appropriate for infrared and visible images of structures and industrial assets, facilitating enhanced visualization and automated inspection for structural maintenance. This paper proposes an advanced image stitching method appropriate for dual-sensor inspections. The proposed image stitching technique employs self-supervised feature detection to enhance the quality and quantity of feature detection. Subsequently, a graph neural network is employed for robust feature matching. Ultimately, the proposed method results in image stitching that effectively eliminates perspective distortion in both infrared and visible images, a prerequisite for subsequent multi-modal fusion strategies. Our results substantially enhance the visualization capabilities for infrastructure inspection. Comparative analysis with popular state-of-the-art methods confirms the effectiveness of the proposed approach.

Implementation of Non-Contact Temperature Distribution Monitoring Solutions for Railway Vehicles in a Sustainability Development System Transport

The implementation of temperature sensors represented by thermal imaging cameras is becoming increasingly rational. It is playing an important role in the socio-economic environment, in industry, scientific-research work. The main objective of the work is to assess the quality of the railway vehicles in exploitation and their thermal insulation, localise thermal bridges, and the tightness of the body using the FLIR-E6390 thermal inspection camera. An integration of test methods (research methods) was used including a diagnostic method based on a thermographic study integrated with the system approach method and system failure mode effects analysis (SFMEA). The scientific-research work included studies of seven types of railway vehicles in exploitation. A number of conclusions were reached. Specifically providing implementation of innovative and non-contact temperature distribution monitoring solutions for railway vehicles in a sustainability development system transport. Demonstrated the disparities between the different types of vehicles. Next, the identification of critical elements of their thermal insulation, the location of thermal bridges, and the tightness of the body of the rail vehicles, particularly the doors and inter-unit connections. The study covered the state of consumption of stationary electricity (for non-traction needs), implementing innovative indicators for stationary electricity consumption of railway vehicles as a new approach.

Can Remote Sensing Fill the United States’ Monitoring Gap for Watershed Management?

Remote sensing has been heralded as the silver bullet in water quality modeling and watershed management, and yet a quantitative mapping of where its applicability is likely and most useful has not been undertaken so far. Here, we combine geospatial models of cloud cover as a proxy for the likelihood of acquiring remote scenes and the shortest time of travel to population centers as a proxy for accessibility to ground-truth remote sensing data for water quality monitoring and produce maps of the potential of remote sensing in watershed management in the United States. We generate several maps with different cost-payoff relationships to help stakeholders plan and incentivize remote sensing-based monitoring campaigns. Additionally, we combine these remote sensing potential maps with spatial indices of population, water demand, ecosystem services, pollution risk, and monitoring coverage deficits to identify where remote sensing likely has the greatest role to play. We find that the Southwestern United States and the Central plains regions are generally suitable for remote sensing for watershed management even under the most stringent costing projections, but that the potential for using remote sensing can extend further North and East as constraints are relaxed. We also find large areas in the Southern United States and sporadic watersheds in the Northeast and Northwest seaboards and the Midwest would likely benefit most from using remote sensing for watershed monitoring. Although developed herein for watershed decision support in the United States, our approach is readily generalizable to other environmental domains and across the world.