Classification of images in fog and fog-free scenes for use in vehicles

Pavlić, Mario; Rigoll, Gerhard; Ilić, Slobodan

doi:10.1109/ivs.2013.6629514

Cited by 52 publications

(27 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the above recent works on pixel-level parsing of foggy scenes, there have also been earlier works on fog detection [27], [28], [29], [30], classification of scenes into foggy and fog-free [31], and visibility estimation both for daytime [32], [33], [34] and nighttime [35], in the context of assisted and autonomous driving. The closest of these works to ours is [32], which generates synthetic fog and segments foggy images to free-space area and vertical objects.…”

Section: Related Workmentioning

confidence: 99%

Semantic Understanding of Foggy Scenes with Purely Synthetic Data

Hahner

Dai

Sakaridis

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

This work addresses the problem of semantic scene understanding under foggy road conditions. Although marked progress has been made in semantic scene understanding over the recent years, it is mainly concentrated on clear weather outdoor scenes. Extending semantic segmentation methods to adverse weather conditions like fog is crucially important for outdoor applications such as self-driving cars. In this paper, we propose a novel method, which uses purely synthetic data to improve the performance on unseen realworld foggy scenes captured in the streets of Zurich and its surroundings. Our results highlight the potential and power of photo-realistic synthetic images for training and especially fine-tuning deep neural nets. Our contributions are threefold, 1) we created a purely synthetic, high-quality foggy dataset of 25,000 unique outdoor scenes, that we call Foggy Synscapes and plan to release publicly 2) we show that with this data we outperform previous approaches on real-world foggy test data 3) we show that a combination of our data and previously used data can even further improve the performance on real-world foggy data.

show abstract

Section: Related Workmentioning

confidence: 99%

Semantic Understanding of Foggy Scenes with Purely Synthetic Data

Hahner

Dai

Sakaridis

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

show abstract

“…Hand-crafted features are popular in these works. Kurihata et al [12,24] proposed that rain drops are strong cues for the presence of rainy weather and developed a rain feature to detect rain drops on the wind- [28,16] transformed images into frequency domain and detected the presence of fog through training different scaled and oriented Gabor filters in the power spectrum. Although the aforementioned approaches have shown good performance, they are usually limited to the in-vehicle perspective and cannot be applied to wider range of applications.…”

Section: Weather Recognition With Hand-crafted Featuresmentioning

confidence: 99%

A CNN–RNN architecture for multi-label weather recognition

Zhao

et al. 2018

Neurocomputing

114

View full text Add to dashboard Cite

Weather Recognition plays an important role in our daily lives and many computer vision applications. However, recognizing the weather conditions from a single image remains challenging and has not been studied thoroughly. Generally, most previous works treat weather recognition as a single-label classification task, namely, determining whether an image belongs to a specific weather class or not. This treatment is not always appropriate, since more than one weather conditions may appear simultaneously in a single image. To address this problem, we make the first attempt to view weather recognition as a multi-label classification task, i.e., assigning an image more than one labels according to the displayed weather conditions. Specifically, a CNN-RNN based multi-label classification approach is proposed in this paper. The convolutional neural network (CNN) is extended with a channel-wise attention model to extract the most correlated visual features. The Recurrent Neural Network (RNN) further processes the features and excavates the dependencies among weather classes.Finally, the weather labels are predicted step by step. Besides, we construct two datasets for the weather recognition task and explore the relationships among different weather conditions. Experimental results demonstrate the superiority and effectiveness of the proposed approach. The new constructed datasets will be available at https: //github.com/wzgwzg/Multi-Label-Weather-Recognition.

show abstract

“…In recent years, important contributions have been made as an attempt to solve the weather classification problem. Many of these recognisable attempts target the problem from perspective of weather classification for traffic purposes were limited to single adverse condition like rain( [6], [7], [8], [9]) and fog( [10], [11], [12]). The dataset used to train the classifier in this problem contains images captured using on board camera of various weather conditions on roads and highways.…”

Section: Related Workmentioning

confidence: 99%

Weather Classification: A new multi-class dataset, data augmentation approach and comprehensive evaluations of Convolutional Neural Networks

Guerra

Khanam

Ehsan

et al. 2018

2018 NASA/ESA Conference on Adaptive Hardware and Systems (AHS)

View full text Add to dashboard Cite

Weather conditions often disrupt the proper functioning of transportation systems. Present systems either deploy an array of sensors or use an in-vehicle camera to predict weather conditions. These solutions have resulted in incremental cost and limited scope. To ensure smooth operation of all transportation services in all-weather conditions, a reliable detection system is necessary to classify weather in wild. The challenges involved in solving this problem is that weather conditions are diverse in nature and there is an absence of discriminate features among various weather conditions. The existing works to solve this problem have been scene specific and have targeted classification of two categories of weather. In this paper, we have created a new open source dataset consisting of images depicting three classes of weather i.e rain, snow and fog called RFS Dataset. A novel algorithm has also been proposed which has used super pixel delimiting masks as a form of data augmentation, leading to reasonable results with respect to ten Convolutional Neural Network architectures.

show abstract

Classification of images in fog and fog-free scenes for use in vehicles

Cited by 52 publications

References 21 publications

Semantic Understanding of Foggy Scenes with Purely Synthetic Data

Semantic Understanding of Foggy Scenes with Purely Synthetic Data

A CNN–RNN architecture for multi-label weather recognition

Weather Classification: A new multi-class dataset, data augmentation approach and comprehensive evaluations of Convolutional Neural Networks

Contact Info

Product

Resources

About