The aim of this thesis is to implement methods for the classification and semantic segmentation of tunnel anomalies based on photographic images or laser scans. To this end, we have collected and annotated data from several infrastructures, each presenting anomalies of different appearance and scale. The first contribution of this work was to study a multi-scale semantic segmentation model, trained and then evaluated independently on each dataset. This model is capable of detecting most of the anomalies in a tunnel as long as the domain shift between the training and test sets is negligible. Otherwise, we measured uniformly low performance. A second contribution was therefore to develop an original domain adaptation method, based on the adj...
With recent developments in the field of technology and computer science, conventional methods are b...
Railway tunnel inspection and monitoring has predominantly been a visual and manual procedure, which...
In recent years terrestrial laser scanning is rapidly evolving as a surveying technique for the moni...
We describe an automated system for detecting, localising, clustering and ranking visual changes on ...
We present an automated system for detecting visual changes on tunnel linings. By registering new im...
We present an automated system for detecting visual changes on tunnel linings. By registering new im...
Tunnels in hard rock are typically supported with a thin layer of fibre-reinforced shotcrete in comb...
This study proposes a defect detection framework to improve the performance of deep learning-based d...
This paper describes the survey of a road tunnel, performed with a TOF laser scanner, and the soluti...
Having access to accurate and recent digital twins of infrastructure assets benefits the renovation,...
The deterioration of the underground infrastructure of the major cities around the world, due to age...
In recent decades, many cities have become densely populated due to increased urbanization, and the ...
In this paper, an automatic robotic inspector for tunnel assessment is presented. The proposed platf...
Laser scanning is now a common technology in the surveying and monitoring of large engineering infra...
Architectural structures require routine structural inspections, and these checks are increasingly p...
With recent developments in the field of technology and computer science, conventional methods are b...
Railway tunnel inspection and monitoring has predominantly been a visual and manual procedure, which...
In recent years terrestrial laser scanning is rapidly evolving as a surveying technique for the moni...
We describe an automated system for detecting, localising, clustering and ranking visual changes on ...
We present an automated system for detecting visual changes on tunnel linings. By registering new im...
We present an automated system for detecting visual changes on tunnel linings. By registering new im...
Tunnels in hard rock are typically supported with a thin layer of fibre-reinforced shotcrete in comb...
This study proposes a defect detection framework to improve the performance of deep learning-based d...
This paper describes the survey of a road tunnel, performed with a TOF laser scanner, and the soluti...
Having access to accurate and recent digital twins of infrastructure assets benefits the renovation,...
The deterioration of the underground infrastructure of the major cities around the world, due to age...
In recent decades, many cities have become densely populated due to increased urbanization, and the ...
In this paper, an automatic robotic inspector for tunnel assessment is presented. The proposed platf...
Laser scanning is now a common technology in the surveying and monitoring of large engineering infra...
Architectural structures require routine structural inspections, and these checks are increasingly p...
With recent developments in the field of technology and computer science, conventional methods are b...
Railway tunnel inspection and monitoring has predominantly been a visual and manual procedure, which...
In recent years terrestrial laser scanning is rapidly evolving as a surveying technique for the moni...