2019
DOI: 10.1007/s00779-019-01334-w
|View full text |Cite
|
Sign up to set email alerts
|

Estimating ambient visibility in the presence of fog: a deep convolutional neural network approach

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
11
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 20 publications
(11 citation statements)
references
References 38 publications
0
11
0
Order By: Relevance
“…Based on the dataset from the camera of Korean CCTV, Giyenko [5] proposed a CNN model for visibility estimate with an accuracy of 84 percent. Fatma [6] proposed a visibility estimation approach based on a Deep Convolutional Neural Network (DC-NN) method for feature extraction and a support vector machine (SVM) for visibility range classification. Qin [23] proposed a trainable end-to-end system called traffic visibility regression network (TVRNet).…”
Section: B Visibility Estimation Methods Based On Deep Learningmentioning
confidence: 99%
See 1 more Smart Citation
“…Based on the dataset from the camera of Korean CCTV, Giyenko [5] proposed a CNN model for visibility estimate with an accuracy of 84 percent. Fatma [6] proposed a visibility estimation approach based on a Deep Convolutional Neural Network (DC-NN) method for feature extraction and a support vector machine (SVM) for visibility range classification. Qin [23] proposed a trainable end-to-end system called traffic visibility regression network (TVRNet).…”
Section: B Visibility Estimation Methods Based On Deep Learningmentioning
confidence: 99%
“…To evaluate our method better, we construct two visibility datasets, VID I (Visibility Image Dataset I) and VID II (Visibility Image Dataset II), where VID I comes from observatories of multiple weather bureaus, and VID II is synthesized based on the haze-free image and the corresponding depth information in FRIDA1 and FRIDA2 [3,4]. The experimental results illustrate that our method has better performance than Giyenko's [5], Fatma's [6], and various classical deep learning-based methods [7,8,9,10]. The following three contributions are made by this paper: 1) The real scene visibility dataset (VID Ⅰ) and the synthetic visibility dataset (VID II) are constructed to train and validate the model.…”
Section: Introductionmentioning
confidence: 99%
“…The results of the proposed method showed that the accuracy of visibility estimation can be more than 90%. Fatma Outay [22] proposed a novel method based on "learning features" to estimate the visibility under foggy weather, in which AlexNet deep convolutional neural networks (DCNN) was used for feature extraction, and support vector machine (SVM) classifier was used for visibility estimation. Chuang Zhang [23] presented a visibility prediction method based on the multimodal fusion.…”
Section: Introductionmentioning
confidence: 99%
“…Li [21] proposed a Deep Convolutional Neural Networks (DCNN) method to estimate the visibility with insufficient visibility labeled data. Fatma [22] proposed a use AlexNet Deep Convolution Neural Networks (DCNN) and Support Vector Machine (SVM) classifier to estimate visibility under foggy weather. Chuang Zhang [23] proposed a visibility prediction method by using multimodal fusion.…”
Section: Introductionmentioning
confidence: 99%