Comprehensive Review of Machine Learning (ML) in Image Defogging: Taxonomy of Concepts, Scenes, Feature Extraction, and Classification techniques

Arif, Zainab Hussein; Mahmoud, Moamin A.; Abdulkareem, Karrar Hameed; Mohammed, Mazin Abed; Al-Mhiqani, Mohammed Nasser; Mutlag, Ammar Awad; Damaševičius, Robertas

doi:10.1049/ipr2.12365

Cited by 18 publications

(9 citation statements)

References 127 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various shortest path models are proposed in several research articles. Some of the shortest path estimation approaches like travelling salesman problem (TSP), ant-colony optimization models and fuzzy Topsis based models can be used in-conjunction with the DSS model [40][41][42][43][44][45]. The proposed distributed vehicular ad-hoc network (VANET) will connect the vehicles throughout a city and estimate the traffic congestion.…”

Section: Scalable Architecturementioning

confidence: 99%

Identification and evaluation of the effective criteria for detection of congestion in a smart city

Mohanty¹,

Mohanty

Jena³

et al. 2022

IET Communications

View full text Add to dashboard Cite

The delay in transportation of necessary items is due to traffic congestion throughout the world. This is a serious phenomenon which results in waste of time and fuel. The detection of road conditions and dissemination of traffic information efficiently and effectively is a big challenge to authorities. Recently, the technologies of vehicular ad hoc networks (VANETs) have been utilized and become an important part of the intelligent transportation system (ITS). For this existing problem, vehicle‐to‐vehicle (V2V) communication provides a means for cooperation and route management in transport networks. This paper proposed a novel congestion detection system based on the combination of k‐means clustering and analytical hierarchy process. In the simulation of urban mobility (SUMO) simulator, a transport network is created and parameters of vehicles facing congestion are taken to extract the key parameter by using the k‐means clustering technique and mathematical mean algorithm. This parameter is utilized in analytical hierarchy process to detect the highest priorities parameter and based on that the congestion is detected in particular lane. The result can be a better technique for congestion detection as it requires low installation cost and can be incorporate in vehicles for congestion avoidance which will alternatively improve the traffic flow.

show abstract

Section: Scalable Architecturementioning

confidence: 99%

Identification and evaluation of the effective criteria for detection of congestion in a smart city

Mohanty¹,

Mohanty

Jena³

et al. 2022

IET Communications

View full text Add to dashboard Cite

show abstract

“…Preprocessing is used to improve image data by removing undesired distortions or increasing specific graphic features relevant for further computation [11]. Feature extraction is an essential step in any computerized technique, and several methods are described in the literature, including color features, shape features, texture features, and others [12,13]. Another critical step is important feature selection, which improves accuracy by removing some redundant information.…”

Section: Introductionmentioning

confidence: 99%

Fruit Leaf Diseases Classification: A Hierarchical Deep Learning Framework

Rehman¹,

Khan²,

Alhaisoni³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Manual inspection of fruit diseases is a time-consuming and costly because it is based on naked-eye observation. The authors present computer vision techniques for detecting and classifying fruit leaf diseases. Examples of computer vision techniques are preprocessing original images for visualization of infected regions, feature extraction from raw or segmented images, feature fusion, feature selection, and classification. The following are the major challenges identified by researchers in the literature: (i) lowcontrast infected regions extract irrelevant and redundant information, which misleads classification accuracy; (ii) irrelevant and redundant information may increase computational time and reduce the designed model's accuracy. This paper proposed a framework for fruit leaf disease classification based on deep hierarchical learning and best feature selection. In the proposed framework, contrast is first improved using a hybrid approach, and then data augmentation is used to solve the problem of an imbalanced dataset. The next step is to use a pre-trained deep model named Darknet53 and fine-tune it. Next, deep transfer learning-based training is carried out, and features are extracted using an activation function on the average pooling layer. Finally, an improved butterfly optimization algorithm is proposed, which selects the best features for classification using machine learning classifiers. The experiment was carried out on augmented and original fruit datasets, yielding a maximum accuracy of 99.6% for apple diseases, 99.6% for grapes, 99.9% for peach diseases, and 100% for cherry diseases. The overall average achieved accuracy is 99.7%, higher than previous techniques.

show abstract

“…Consequently, the mean residence time of aerosol particles in the troposphere remains relatively brief, typically ranging from mere hours to a few days [4,5]. Atmospheric particles scatter and disperse light, leading to a degradation in image quality, manifesting as phenomena like color distortion and reduced contrast, among others [6,7]. In this paper, sub-pixel reconstruction method is applied to foggy image restoration for the first time.…”

Section: Introductionmentioning

confidence: 99%

“…We verify that pixel reconfiguration can improve the ability to estimate the attenuation caused by atmospheric medium. This work helps to improve the environmental adaptability of optical image acquisition equipment in foggy scenes [7].…”

Section: Introductionmentioning

confidence: 99%

Foggy image restoration using deep sub‐pixel reconstruction network

Li,

Liu,

Shi

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Light undergoes attenuation due to scattering and refraction when propagating through aerosols. In foggy conditions, Aerosol particles in the troposphere exhibit high mobility introducing intricate non‐linear noise into images. Foggy image restoration represents an ill‐posed problem, where traditional physical models and image enhancement techniques often prove inadequate in delivering effective solutions. This paper introduces a novel deep sub‐pixel reconstruction algorithm for foggy image restoration, pioneering the application of sub‐pixel reconstruction modules to this domain. This model employs convolutional layers to extract low‐level features and dense‐connected layers for high‐level feature extraction. Furthermore, a specialized sub‐pixel reconstruction module tailored for the task of foggy image restoration is designed, with the purpose of reconstructing dehazed images from latent vectors. During training, a generative adversarial training framework is adopted, incorporating a purpose‐designed discriminator. Additionally, a fusion loss is implemented to facilitate model refinement. Quantitative and qualitative evaluation experiments conducted on synthetic and real‐world image datasets demonstrate the effectiveness of the proposed method in preserving finer details. The Structural Similarity Index (SSIM) is observed to improve by 2.5%, attesting to enhanced perceptual quality for grayscale foggy images.

show abstract

Comprehensive Review of Machine Learning (ML) in Image Defogging: Taxonomy of Concepts, Scenes, Feature Extraction, and Classification techniques

Cited by 18 publications

References 127 publications

Identification and evaluation of the effective criteria for detection of congestion in a smart city

Identification and evaluation of the effective criteria for detection of congestion in a smart city

Fruit Leaf Diseases Classification: A Hierarchical Deep Learning Framework

Foggy image restoration using deep sub‐pixel reconstruction network

Contact Info

Product

Resources

About