Abstract
The timely and efficient generation of detailed damage maps is of fundamental importance following disaster events to speed up first responders’ (FR) rescue activities and help trapped victims. Several works dealing with the automated detection of building damages have been published in the last decade. The increasingly widespread availability of inexpensive UAV platforms has also driven their recent adoption for rescue operations (i.e., search and rescue). Their deployment, however, remains largely limited to visual image inspection by skilled operators, limiting their applicability in time-constrained real conditions. This paper proposes a new solution to autonomously map building damages with a commercial UAV in near real-time. The solution integrates different components that allow the live streaming of the images on a laptop and their processing on the fly. Advanced photogrammetric techniques and deep learning algorithms are combined to deliver a true-orthophoto showing the position of building damages, which are already processed by the time the UAV returns to base. These algorithms have been customized to deliver fast results, fulfilling the near real-time requirements. The complete solution has been tested in different conditions, and received positive feedback by the FR involved in the EU funded project INACHUS. Two realistic pilot tests are described in the paper. The achieved results show the great potential of the presented approach, how close the proposed solution is to FR’ expectations, and where more work is still needed.
Highlights
When a catastrophic event occurs, timely and efficient response and rescue are the main elements to increase the chances to save trapped victims under collapsed structures
The simultaneous image orientation and sparse point cloud generation of the surrounding environment is often called Visual SLAM and it is assimilated to the structure from motion (SfM) for real-time applications [28]
This paper has demonstrated that building damage maps can be generated in near real-time using low-cost and commercial unmanned aerial vehicles (UAV)
Summary
When a catastrophic event occurs, timely and efficient response and rescue are the main elements to increase the chances to save trapped victims under collapsed structures. Flight execution and image interpretation are still performed manually (using UAVs for inspections from the sky), requiring a dedicated operator This can be often perceived as a waste of time by first responders given the strong time pressure on their work. The development of deep learning algorithms for image classification [22,23] has shown its potential in the remote sensing domain [24,25,26] providing very promising results in the detection of building damages such as debris or rubble piles [14,27] These works have demonstrated how the convolutional neural networks (CNN) outperform traditional classification approaches in terms of performances and transferability of the learnt features to new datasets.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
