Detection, analysis and monitoring of damage to masonry structures

What possibilities do drones and Artificial Intelligence offer for speeding up Comparative Simplified Visit-type inspections (CEREMA) of masonry structures?

Our SaaS solution

To optimize management of the structure, we build its 3D digital twin using aerial drone scans.

At the same time, the images acquired are automatically analyzed to detect anomalies (displacements, cracks, fractures, disjointed joints, etc.) to the nearest millimeter, geolocate them to the nearest centimeter and quantify them so that they can be tracked over time.

In addition to centralizing observations and interpretations on this shared 3D model of the structure, the digitization of the structure makes it possible to pool the annotations of the various experts to reinforce the learning bases of our Deep Learning algorithms.

Note that the raw data is always available to the Expert, to help him clarify any doubts.

Customer benefits

Save time on acquisition, delivery and follow-up, by digitizing the entire process.

Increased personal safety through remote acquisition.

Reducing our carbon footprint and contributing to the UN’s Sustainable Development Goals

In a nutshell

Our application automatically takes RTK drone shots of the structure:

obtain a 3D digital twin of the structure and virtually walk through it,
identify potential faults and geolocate them on the digital twin,
determine the evolution of each defect in relation to a previous capture,
immediate overview of areas of interest
give the User the opportunity to validate and annotate the defects highlighted by our AI,
produce data extractions for maintenance operations.

In October 2022, this solution won the Trophée Innovation Digitale at the Assises du Port du Futur.

With A2D, we developed this decision-support software tool for automatic analysis of marine infrastructure damage. The time saved is immense, as teams no longer have to travel by boat to carry out large, time-consuming inspections, as the system only brings them predefined alerts. Managers can then decide to verify the information and implement a response plan. As a result, travel and CO2 emissions are greatly reduced, and employee safety is enhanced. Digitization improves the sharing of information between all players, centralizing observations and interpretations on a shared digital twin of the structure, and enabling experts to annotate data to reinforce the learning bases of Machine Learning algorithms.