The measurement of atmospheric visibility is an important element for road and air transportation safety. We propose in this paper a novel estimator of the atmospheric visibility by already existing conventional highway cameras, with a technique based on the gradient magnitude selected by applying Lambert's law with respect to changes in lighting conditions. The response of this estimator is calibrated by non-linear regression with data from a visibility meter installed in a test site which has been instrumented with a camera. Through our technique, atmospheric visibility estimates are obtained with an average error of 30% for images taken in the day, with sky luminance between 10 to 8,000 cd.m −2 and visibility distances up to 15 km. Our results allow us to envision practical implementation on roadsides in the near future to determine local visibility for the benefit of road safety, meteorological observation and air quality monitoring.
Atmospheric visibility is an important input for road and air transportation safety, as well as a good proxy to estimate the air quality. A model-driven approach is presented to monitor the meteorological visibility distance through use of ordinary outdoor cameras. Unlike in previous data-driven approaches, a physics-based model is proposed which describes the mapping function between the contrast in the image and the atmospheric visibility. The model is non-linear, which allows encompassing a large spectrum of applications. The model assumes a continuous distribution of objects with respect to the distance in the scene and is estimated by a novel process. It is more robust to illumination variations by selecting the Lambertian surfaces in the scene. To evaluate the relevance of the approach, a publicly available database is used. When the model is fitted to short range data, the proposed method is shown to be effective and to improve on existing methods. In particular, it allows envisioning an easier deployment of these camera-based techniques on multiple observation sites.
Abstract. Estimating the atmospheric or meteorological visibility distance is very important for air and ground transport safety, as well as for air quality. However, there is no holistic approach to tackle the problem by camera. Most existing methods are data-driven approaches which perform a linear regression between the contrast in the scene and the visual range estimated by means of reference additional sensors. In this paper, we propose a probabilistic model-based approach which takes into account the distribution of contrasts in the scene. It is robust to illumination variations in the scene by taking into account the Lambertian surfaces. To evaluate our model, meteorological ground truth data were collected, showing very promising results. This works opens new perspectives in the computer vision community dealing with environmental issues.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.