Vincent Boucher

Infrared thermography system for transport infrastructures survey with inline local atmospheric parameter measurements and offline model for radiation attenuation evaluations

Abstract An infrared system has been developed to monitor transport infrastructures in a standalone configuration. It is based on low cost infrared thermal cameras linked with a calculation unit in order to produce a corrected thermal map of the surveyed structure at a selected time step. With the inline version, the data collected feed simplified radiative models running a GPU. With the offline version, the thermal map can be corrected when data are collected under different atmospheric conditions up to foggy night conditions. A model for radiative transmission prediction is proposed and limitations are addressed. Furthermore, the results obtained by image and signal processing methods with data acquired on the transport infrastructure opened to traffic are presented. Finally, conclusions and perspectives for new implementation and new functionalities are presented and discussed.

Numerical and experimental evaluation of road infrastructure perception in fog and/or night conditions using infrared and photometric vision systems

Use of infrared vision in automotive industry has mainly focused on detection of pedestrians or animals at night or under poor weather conditions. In those approaches, the road infrastructure behavior in infrared range has not been investigated. So, research work was realized using numerical simulations associated with specific experiments in a fog tunnel. The present paper deals with numerical simulations developed for both visible spectrum (visibility in fog) and infrared vision applied to road infrastructure perception in foggy night conditions. Results obtained as a function of fog nature (radiation or advection) are presented and discussed.

Pattern recognition applied to infrared images for early alerts in fog

Fog conditions are the cause of severe car accidents in western countries because of the poor induced visibility. Its forecast and intensity are still very difficult to predict by weather services. Infrared cameras allow to detect and to identify objects in fog while visibility is too low for eye detection. Over the past years, the implementation of cost effective infrared cameras on some vehicles has enabled such detection. On the other hand pattern recognition algorithms based on Canny filters and Hough transformation are a common tool applied to images. Based on these facts, a joint research program between IFSTTAR and Cerema has been developed to study the benefit of infrared images obtained in a fog tunnel during its natural dissipation. Pattern recognition algorithms have been applied, specifically on road signs which shape is usually associated to a specific meaning (circular for a speed limit, triangle for an alert, …). It has been shown that road signs were detected early enough in images, with respect to images in the visible spectrum, to trigger useful alerts for Advanced Driver Assistance Systems.