A Neural network approach to visibility range estimation under foggy weather conditions

Chaabani, Hazar; Kamoun, Faouzi; Bargaoui, Hichem; Outay, Fatma; Yasar, Ansar-Ul-Haque

doi:10.1016/j.procs.2017.08.304

Cited by 53 publications

(28 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this method the local variance of pixel values is considered as a local contrast measure. Another interesting application of contrast notion for road visibility estimation, under bad weather conditions, based on a neural network has been proposed in [185]. Note that, among the contrasts discussed in this study, the GCF [48] contrast seems to be the most suitable measure, in terms of simplicity and efficiency, that could be used in various interesting applications such as content based image retrieval, visualization and tone mapping techniques as suggested in [48].…”

Section: G Other Potential Applicationsmentioning

confidence: 98%

A Critical Analysis on Perceptual Contrast and Its Use in Visual Information Analysis and Processing

Beghdadi¹,

Qureshi

Amirshahi

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Contrast in visible images is one of the most relevant characteristics of visual signals. Since the pioneering works performed in vision psychology and optics, different definitions have been proposed in the literature. However, for the time being there exist no definition of contrast on which the vision research and visual processing scientific community can agree on. This makes it critical to have a clear view on the notion of contrast and its use in various applications. One issue to consider is how to define and particularly use this important measure in developing image processing and analysis methods. In this paper, we present a critical review of contrast measures and associated models developed by the scientific community in vision, optics, and image processing. We also provide learned lessons and guidelines on the use of appropriate contrast measures in selected visual information processing and analysis applications. We discuss challenges and propose research avenues for models enriched by recent findings in the field of human vision research and machine learning. We believe that this work serves as a guideline and can potentially open new research perspectives to the scientific community working on visual information processing and analysis.

show abstract

Section: G Other Potential Applicationsmentioning

confidence: 98%

A Critical Analysis on Perceptual Contrast and Its Use in Visual Information Analysis and Processing

Beghdadi¹,

Qureshi

Amirshahi

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Instead of calculating global image thresholds, local thresholds were calculated based on the distribution of brightness in different regions of the image. For different regions of the image, it can calculate different thresholds adaptively [32]. Figure 7 showed the histogram of the graylevel averaged image.…”

Section: Subregion Segmentationmentioning

confidence: 99%

A Transfer Learning Method for Meteorological Visibility Estimation Based on Feature Fusion Method

Hong³

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Meteorological visibility is an important meteorological observation indicator to measure the weather transparency which is important for the transport safety. It is a challenging problem to estimate the visibilities accurately from the image characteristics. This paper proposes a transfer learning method for the meteorological visibility estimation based on image feature fusion. Different from the existing methods, the proposed method estimates the visibility based on the data processing and features’ extraction in the selected subregions of the whole image and therefore it had less computation load and higher efficiency. All the database images were gray-averaged firstly for the selection of effective subregions and features extraction. Effective subregions are extracted for static landmark objects which can provide useful information for visibility estimation. Four different feature extraction methods (Densest, ResNet50, Vgg16, and Vgg19) were used for the feature extraction of the subregions. The features extracted by the neural network were then imported into the proposed support vector regression (SVR) regression model, which derives the estimated visibilities of the subregions. Finally, based on the weight fusion of the visibility estimates from the subregion models, an overall comprehensive visibility was estimated for the whole image. Experimental results show that the visibility estimation accuracy is more than 90%. This method can estimate the visibility of the image, with high robustness and effectiveness.

show abstract

“…2008; Pokhrel and Lee 2011; Kim 2015; Chaabani et al. 2017). Such methods allow for large spatial coverage by utilizing existing camera networks (such as are commonly found along highways and at airports) in a relatively efficient and inexpensive manner (e.g., Hautiere et al.…”

Section: Introductionmentioning

confidence: 99%

Missed Fog?

Izett

Schilperoort

Coenders-Gerrits

et al. 2019

Boundary-Layer Meteorol

View full text Add to dashboard Cite

Conventional in situ observations of meteorological variables are restricted to a limited number of levels near the surface, with the lowest observation often made around 1-m height. This can result in missed observations of both shallow fog, and the initial growth stage of thicker fog layers. At the same time, numerical experiments have demonstrated the need for high vertical grid resolution in the near-surface layer to accurately simulate the onset of fog; this requires correspondingly high-resolution observational data for validation. A two-week field campaign was conducted in November 2017 at the Cabauw Experimental Site for Atmospheric Research (CESAR) in the Netherlands. The aim was to observe the growth of shallow fog layers and assess the possibility of obtaining very high-resolution observations near the surface during fog events. Temperature and relative humidity were measured at centimetre resolution in the lowest 7 m using distributed temperature sensing. Further, a novel approach was employed to estimate visibility in the lowest 2.5 m using a camera and an extended light source. These observations were supplemented by the existing conventional sensors at the site, including those along a 200-m tall tower. Comparison between the increased-resolution observations and their conventional counterparts show the errors to be small, giving confidence in the reliability of the techniques. The increased resolution of the observations subsequently allows for detailed investigations of fog growth and evolution. This includes the observation of large temperature inversions in the lowest metre (up to 5 K) and corresponding regions of (super)saturation where the fog formed. Throughout the two-week observation period, fog was observed twice at the conventional sensor height of 2.0 m. Two additional low-visibility events were observed in the lowest 0–0.5 m using the camera-based observations, but were missed by the conventional sensors. The camera observations also showed the growth of shallow radiation fog, forming in the lowest 0.5 m as early as two hours before it was observed at the conventional height of 2 m.

show abstract

A Neural network approach to visibility range estimation under foggy weather conditions

Cited by 53 publications

References 9 publications

A Critical Analysis on Perceptual Contrast and Its Use in Visual Information Analysis and Processing

A Critical Analysis on Perceptual Contrast and Its Use in Visual Information Analysis and Processing

A Transfer Learning Method for Meteorological Visibility Estimation Based on Feature Fusion Method

Missed Fog?

Contact Info

Product

Resources

About